diff --git a/README.md b/README.md index 05e521ee7da..dcac7b5cba9 100644 --- a/README.md +++ b/README.md @@ -1,11 +1,11 @@ ## Why `cecli`? -`cecli` (probably pronounced like "Cecily", aka `aider-ce`) is a community-driven fork of the [Aider](https://cecli.dev/) AI pair programming tool. -Aider is a fantastic piece of software with a wonderful community but it has been painfully slow in receiving updates in the quickly evolving AI tooling space. +`cecli` (probably pronounced like "Cecily") is yet another cli agent crafted for extensibility and customization. Originally a fork of the [Aider](https://cecli.dev/) AI pair programming tool, we aim to make agentic coding as maximally effective as it can be based on the growing capabilities of large language models. -We aim to foster an open, collaborative ecosystem where new features, experiments, and improvements can be developed and shared rapidly. We believe in genuine FOSS principles and actively welcome contributors of all skill levels. +We aim to foster an open, collaborative ecosystem where new features, experiments, and improvements can be developed and shared rapidly. We believe in the principles of FOSS and actively welcome contributors of all skill levels. If you are looking for bleeding-edge features or want to get your hands dirty with the internals of an AI coding agent, here's your sign. + LLMs are a part of our lives from here on out so join us in learning about and crafting the future. ### Links diff --git a/cecli/__init__.py b/cecli/__init__.py index 7cee4865eb4..123f22388b9 100644 --- a/cecli/__init__.py +++ b/cecli/__init__.py @@ -1,6 +1,6 @@ from packaging import version -__version__ = "0.97.3.dev" +__version__ = "0.97.4.dev" safe_version = __version__ try: diff --git a/cecli/args.py b/cecli/args.py index b87b4cfaddf..6d26d53bd13 100644 --- a/cecli/args.py +++ b/cecli/args.py @@ -260,6 +260,12 @@ def get_parser(default_config_files, git_root): default=3, help="Maximum number of retries a model gets on malformed outputs (default: 3)", ) + group.add_argument( + "--cost-limit", + type=float, + default=None, + help="Cost limit per session, exceeding this forces prompt confirmation (default: None)", + ) group.add_argument( "--file-diffs", action=argparse.BooleanOptionalAction, diff --git a/cecli/coders/agent_coder.py b/cecli/coders/agent_coder.py index eac72038b7b..080da998cd7 100644 --- a/cecli/coders/agent_coder.py +++ b/cecli/coders/agent_coder.py @@ -90,9 +90,13 @@ def __init__(self, *args, **kwargs): self.skip_cli_confirmations = False self.agent_finished = False self.agent_config = self._get_agent_config() + self._setup_agent() ToolRegistry.build_registry(agent_config=self.agent_config) super().__init__(*args, **kwargs) + def _setup_agent(self): + os.makedirs(".cecli/workspace", exist_ok=True) + def _get_agent_config(self): """ Parse and return agent configuration from args.agent_config. diff --git a/cecli/coders/architect_coder.py b/cecli/coders/architect_coder.py index 8c378efe252..ed253d80eef 100644 --- a/cecli/coders/architect_coder.py +++ b/cecli/coders/architect_coder.py @@ -1,7 +1,7 @@ import asyncio from ..commands import SwitchCoderSignal -from ..helpers.conversation import ConversationManager, MessageTag +from ..helpers.conversation import ConversationManager from .ask_coder import AskCoder from .base_coder import Coder @@ -61,9 +61,7 @@ async def reply_completed(self): editor_coder = await Coder.create(**new_kwargs) # Re-initialize ConversationManager with editor coder - ConversationManager.initialize( - editor_coder, reset=True, reformat=True, preserve_tags=[MessageTag.DONE, MessageTag.CUR] - ) + ConversationManager.initialize(editor_coder, reset=True, reformat=True, preserve_tags=True) if self.verbose: editor_coder.show_announcements() @@ -84,7 +82,7 @@ async def reply_completed(self): original_coder or self, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) self.total_cost = editor_coder.total_cost @@ -96,7 +94,7 @@ async def reply_completed(self): original_coder or self, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) raise SwitchCoderSignal(main_model=self.main_model, edit_format="architect") diff --git a/cecli/coders/base_coder.py b/cecli/coders/base_coder.py index ffeb31dae47..c77c0e6c202 100755 --- a/cecli/coders/base_coder.py +++ b/cecli/coders/base_coder.py @@ -32,7 +32,7 @@ import httpx from litellm import experimental_mcp_client -from litellm.types.utils import ChatCompletionMessageToolCall, Function, ModelResponse +from litellm.types.utils import ModelResponse from prompt_toolkit.patch_stdout import patch_stdout from rich.console import Console @@ -40,7 +40,7 @@ from cecli import __version__, models, urls, utils from cecli.commands import Commands, SwitchCoderSignal from cecli.exceptions import LiteLLMExceptions -from cecli.helpers import command_parser, coroutines, nested +from cecli.helpers import command_parser, coroutines, nested, responses from cecli.helpers.conversation import ( ConversationChunks, ConversationManager, @@ -157,6 +157,7 @@ class Coder: last_user_message = "" uuid = "" model_kwargs = {} + cost_multiplier = 1 # Task coordination state variables input_running = False @@ -211,34 +212,14 @@ async def create( use_kwargs = dict(from_coder.original_kwargs) # copy orig kwargs - # If the edit format changes, we can't leave old ASSISTANT - # messages in the chat history. The old edit format will - # confused the new LLM. It may try and imitate it, disobeying - # the system prompt. - # Get DONE messages from ConversationManager - done_messages = ConversationManager.get_messages_dict(MessageTag.DONE) - if edit_format != from_coder.edit_format and done_messages and summarize_from_coder: - try: - io.tool_warning("Summarizing messages, please wait...") - done_messages = await from_coder.summarizer.summarize_all(done_messages) - except (KeyboardInterrupt, ValueError): - # If summarization fails, keep the original messages and warn the user - io.tool_warning( - "Chat history summarization failed, continuing with full history" - ) - - # Bring along context from the old Coder - # Get CUR messages from ConversationManager - cur_messages = ConversationManager.get_messages_dict(MessageTag.CUR) - update = dict( fnames=list(from_coder.abs_fnames), read_only_fnames=list(from_coder.abs_read_only_fnames), # Copy read-only files read_only_stubs_fnames=list( from_coder.abs_read_only_stubs_fnames ), # Copy read-only stubs - done_messages=done_messages, - cur_messages=cur_messages, + done_messages=[], + cur_messages=[], coder_commit_hashes=from_coder.coder_commit_hashes, commands=from_coder.commands.clone(), total_cost=from_coder.total_cost, @@ -415,22 +396,6 @@ def __init__( self.add_gitignore_files = add_gitignore_files self.abs_read_only_stubs_fnames = set() - # Always use ConversationManager as the source of truth - # Add any provided messages to ConversationManager - if done_messages: - for msg in done_messages: - ConversationManager.add_message( - message_dict=msg, - tag=MessageTag.DONE, - ) - - if cur_messages: - for msg in cur_messages: - ConversationManager.add_message( - message_dict=msg, - tag=MessageTag.CUR, - ) - self.io = io self.io.coder = weakref.ref(self) @@ -1616,6 +1581,18 @@ async def run_one(self, user_message, preproc): self.reflected_message = None self.tool_reflection = False + if float(self.total_cost) > self.cost_multiplier * ( + nested.getter(self.args, "cost_limit", float("inf")) or float("inf") + ): + if await self.io.confirm_ask( + "You have reached your configured cost limit. Continue?", + group_response="Cost Limit", + explicit_yes_required=True, + ): + Coder.cost_multiplier += 1 + else: + return + async for _ in self.send_message(message): pass @@ -2405,7 +2382,7 @@ async def send_message(self, inp): force=True, # Force update existing message ) - if edited and self.auto_test: + if edited and self.auto_test and self.test_cmd: test_errors = await self.commands.execute("test", self.test_cmd) self.test_outcome = not test_errors if test_errors: @@ -3334,66 +3311,16 @@ def consolidate_chunks(self): # If no native tool calls, check if the content contains JSON tool calls # This handles models that write JSON in text instead of using native calling if not self.partial_response_tool_calls and self.partial_response_content: - try: - # Simple extraction of JSON-like structures that look like tool calls - # Only look for tool calls if it looks like JSON - if "{" in self.partial_response_content or "[" in self.partial_response_content: - json_chunks = utils.split_concatenated_json(self.partial_response_content) - extracted_calls = [] - chunk_index = 0 - - for chunk in json_chunks: - chunk_index += 1 - try: - json_obj = json.loads(chunk) - if ( - isinstance(json_obj, dict) - and "name" in json_obj - and "arguments" in json_obj - ): - # Create a Pydantic model for the tool call - function_obj = Function( - name=json_obj["name"], - arguments=( - json.dumps(json_obj["arguments"]) - if isinstance(json_obj["arguments"], (dict, list)) - else str(json_obj["arguments"]) - ), - ) - tool_call_obj = ChatCompletionMessageToolCall( - type="function", - function=function_obj, - id=f"call_{len(extracted_calls)}_{int(time.time())}_{chunk_index}", - ) - extracted_calls.append(tool_call_obj) - elif isinstance(json_obj, list): - for item in json_obj: - if ( - isinstance(item, dict) - and "name" in item - and "arguments" in item - ): - function_obj = Function( - name=item["name"], - arguments=( - json.dumps(item["arguments"]) - if isinstance(item["arguments"], (dict, list)) - else str(item["arguments"]) - ), - ) - tool_call_obj = ChatCompletionMessageToolCall( - type="function", - function=function_obj, - id=f"call_{len(extracted_calls)}_{int(time.time())}_{chunk_index}", - ) - extracted_calls.append(tool_call_obj) - except json.JSONDecodeError: - continue - - if extracted_calls: - self.partial_response_tool_calls = extracted_calls - except Exception: - pass + extracted_calls = responses.extract_tools_from_content_json( + self.partial_response_content + ) + if not extracted_calls: + extracted_calls = responses.extract_tools_from_content_xml( + self.partial_response_content + ) + + if extracted_calls: + self.partial_response_tool_calls = extracted_calls return response, func_err, content_err diff --git a/cecli/commands/agent_model.py b/cecli/commands/agent_model.py index 64d1e4a807c..36461a2ceea 100644 --- a/cecli/commands/agent_model.py +++ b/cecli/commands/agent_model.py @@ -3,7 +3,7 @@ import cecli.models as models from cecli.commands.utils.base_command import BaseCommand from cecli.commands.utils.helpers import format_command_result -from cecli.helpers.conversation import ConversationManager, MessageTag +from cecli.helpers.conversation import ConversationManager class AgentModelCommand(BaseCommand): @@ -69,7 +69,7 @@ async def execute(cls, io, coder, args, **kwargs): temp_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) verbose = kwargs.get("verbose", False) @@ -86,7 +86,7 @@ async def execute(cls, io, coder, args, **kwargs): original_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) # Restore the original model configuration diff --git a/cecli/commands/editor_model.py b/cecli/commands/editor_model.py index 646604f9463..78ed20368ea 100644 --- a/cecli/commands/editor_model.py +++ b/cecli/commands/editor_model.py @@ -3,7 +3,7 @@ import cecli.models as models from cecli.commands.utils.base_command import BaseCommand from cecli.commands.utils.helpers import format_command_result -from cecli.helpers.conversation import ConversationManager, MessageTag +from cecli.helpers.conversation import ConversationManager class EditorModelCommand(BaseCommand): @@ -69,7 +69,7 @@ async def execute(cls, io, coder, args, **kwargs): temp_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) verbose = kwargs.get("verbose", False) @@ -86,7 +86,7 @@ async def execute(cls, io, coder, args, **kwargs): original_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) # Restore the original model configuration diff --git a/cecli/commands/model.py b/cecli/commands/model.py index 315d4faf18b..a1a627958ec 100644 --- a/cecli/commands/model.py +++ b/cecli/commands/model.py @@ -3,7 +3,7 @@ import cecli.models as models from cecli.commands.utils.base_command import BaseCommand from cecli.commands.utils.helpers import format_command_result -from cecli.helpers.conversation import ConversationManager, MessageTag +from cecli.helpers.conversation import ConversationManager class ModelCommand(BaseCommand): @@ -73,7 +73,7 @@ async def execute(cls, io, coder, args, **kwargs): temp_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) verbose = kwargs.get("verbose", False) @@ -90,7 +90,7 @@ async def execute(cls, io, coder, args, **kwargs): original_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) # Restore the original model configuration diff --git a/cecli/commands/tokens.py b/cecli/commands/tokens.py index ca5016ffa2e..0b2d4c86657 100644 --- a/cecli/commands/tokens.py +++ b/cecli/commands/tokens.py @@ -64,6 +64,7 @@ async def execute(cls, io, coder, args, **kwargs): tokens_done = 0 tokens_cur = 0 tokens_diffs = 0 + tokens_file_contexts = 0 if msgs_done: tokens_done = coder.main_model.token_count(msgs_done) diff --git a/cecli/commands/utils/base_command.py b/cecli/commands/utils/base_command.py index a5f25ddfb78..5e5327a77f9 100644 --- a/cecli/commands/utils/base_command.py +++ b/cecli/commands/utils/base_command.py @@ -1,7 +1,7 @@ from abc import ABC, ABCMeta, abstractmethod from typing import List -from cecli.helpers.conversation import ConversationManager, MessageTag +from cecli.helpers.conversation import ConversationManager class CommandMeta(ABCMeta): @@ -152,9 +152,7 @@ async def _generic_chat_command(cls, io, coder, args, edit_format, placeholder=N new_coder = await Coder.create(**kwargs) # Re-initialize ConversationManager with new coder - ConversationManager.initialize( - new_coder, reset=True, reformat=True, preserve_tags=[MessageTag.DONE, MessageTag.CUR] - ) + ConversationManager.initialize(new_coder, reset=True, reformat=True, preserve_tags=True) await new_coder.generate(user_message=user_msg, preproc=False) coder.coder_commit_hashes = new_coder.coder_commit_hashes @@ -164,7 +162,7 @@ async def _generic_chat_command(cls, io, coder, args, edit_format, placeholder=N original_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) from cecli.commands import SwitchCoderSignal diff --git a/cecli/commands/weak_model.py b/cecli/commands/weak_model.py index ff18ef21879..15f2d0e9b4b 100644 --- a/cecli/commands/weak_model.py +++ b/cecli/commands/weak_model.py @@ -3,7 +3,7 @@ import cecli.models as models from cecli.commands.utils.base_command import BaseCommand from cecli.commands.utils.helpers import format_command_result -from cecli.helpers.conversation import ConversationManager, MessageTag +from cecli.helpers.conversation import ConversationManager class WeakModelCommand(BaseCommand): @@ -68,7 +68,7 @@ async def execute(cls, io, coder, args, **kwargs): temp_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) verbose = kwargs.get("verbose", False) @@ -85,7 +85,7 @@ async def execute(cls, io, coder, args, **kwargs): original_coder, reset=True, reformat=True, - preserve_tags=[MessageTag.DONE, MessageTag.CUR], + preserve_tags=True, ) # Restore the original model configuration diff --git a/cecli/helpers/conversation/manager.py b/cecli/helpers/conversation/manager.py index 285d8e249f8..aa83edce384 100644 --- a/cecli/helpers/conversation/manager.py +++ b/cecli/helpers/conversation/manager.py @@ -2,7 +2,7 @@ import json import time import weakref -from typing import Any, Dict, List, Optional, Tuple +from typing import Any, Dict, List, Optional, Tuple, Union from cecli.helpers import nested @@ -38,7 +38,7 @@ def initialize( coder, reset: bool = False, reformat: bool = False, - preserve_tags: Optional[List[str]] = None, + preserve_tags: Optional[Union[List[str], bool]] = None, ) -> None: """ Set up singleton with weak reference to coder. @@ -56,6 +56,14 @@ def initialize( cls._initialized = True preserved_messages = [] + if preserve_tags is True: + preserve_tags = [ + MessageTag.DONE, + MessageTag.CUR, + MessageTag.DIFFS, + MessageTag.FILE_CONTEXTS, + ] + if reset and preserve_tags: # New approach: loop over every single tag type and only clear tags NOT in preserve_tags # Get all MessageTag values @@ -78,20 +86,10 @@ def initialize( # If preserve_tags is truthy, re-add preserved messages with updated timestamps after reformat block if preserve_tags and preserved_messages: - for tag_type in preserve_tags: - cls.clear_tag(tag_type) - + offset = 0 for msg in preserved_messages: - cls.add_message( - message_dict=msg.message_dict, - tag=MessageTag(msg.tag), - priority=msg.priority, - timestamp=time.monotonic_ns(), # Updated timestamp - mark_for_delete=msg.mark_for_delete, - force=True, - update_timestamp=True, - message_id=msg.message_id, - ) + offset += 1 + msg.timestamp = time.monotonic_ns() + offset # Enable debug mode if coder has verbose attribute and it's True if hasattr(coder, "verbose") and coder.verbose: @@ -372,15 +370,22 @@ def remove_message_by_hash_key(cls, hash_key: Tuple[str, ...]) -> bool: Returns: True if a message was removed, False otherwise """ - for message in cls._messages: - if message.hash_key == hash_key: - cls._messages.remove(message) + messages_to_remove = [m for m in cls._messages if m.hash_key == hash_key] + if not messages_to_remove: + return False + + tags_to_clear = set() + for message in messages_to_remove: + cls._messages.remove(message) + if message.message_id in cls._message_index: del cls._message_index[message.message_id] - # Clear cache for this tag and all messages cache since message was removed - cls._tag_cache.pop(message.tag, None) - cls._tag_cache.pop(cls._ALL_MESSAGES_CACHE_KEY, None) - return True - return False + tags_to_clear.add(message.tag) + + for tag in tags_to_clear: + cls._tag_cache.pop(tag, None) + cls._tag_cache.pop(cls._ALL_MESSAGES_CACHE_KEY, None) + + return True @classmethod def get_tag_messages(cls, tag: str) -> List[BaseMessage]: diff --git a/cecli/helpers/hashline.py b/cecli/helpers/hashline.py index 364e539bd14..3bbea5cbf0a 100644 --- a/cecli/helpers/hashline.py +++ b/cecli/helpers/hashline.py @@ -1,13 +1,12 @@ import difflib import re +from difflib import SequenceMatcher import xxhash -# Regex patterns for hashline parsing -# Format: |{line_number}{hash_fragment}| -HASHLINE_PREFIX_RE = re.compile(r"^\|?(-?\d+)([a-zA-Z]{2})\|") # Format: |{line_number}{hash_fragment}| PARSE_NEW_FORMAT_RE = re.compile(r"^\|?(-?\d+)([a-zA-Z]{2})\|?$") +HASHLINE_PREFIX_RE = re.compile(r"^\|?(-?\d+)([a-zA-Z]{2})\|") # Format: {hash_fragment}|{line_number} PARSE_OLD_FORMAT_RE = re.compile(r"^([a-zA-Z]{2})\|(-?\d+)$") @@ -52,6 +51,21 @@ def hashline(text: str, start_line: int = 1) -> str: return "".join(result_lines) +def longest_common_substring(str1, str2): + """ + Finds the longest common substring between two strings. + """ + seq_match = SequenceMatcher(None, str1, str2) + # Find the longest matching block + match = seq_match.find_longest_match(0, len(str1), 0, len(str2)) + + if match.size != 0: + # Extract the substring using the indices from the match object + return str1[match.a : match.a + match.size] + else: + return "" + + def int_to_2digit_52(n: int) -> str: """ Convert integer to 2-digit base52 with 'a' padding. @@ -86,7 +100,7 @@ def int_to_2digit_52(n: int) -> str: digits.append("a") # Return in correct order (most significant first) - return "".join(reversed(digits)) + return "".join(reversed(digits)).lower() def strip_hashline(text: str) -> str: @@ -212,6 +226,29 @@ def normalize_hashline(hashline_str: str) -> str: ) +def find_hashline_by_content_match(hashed_lines, hash_str, expected_content): + """ + Extract the line number from the passed hash and return the hashline + if there is an exact content match. + """ + try: + _, _, line_num = parse_hashline(hash_str) + # Check the exact line and adjacent lines + for offset in [0, -1, 1, -2, 2]: # Check exact line, lines before, lines after + idx = line_num - 1 + offset + if 0 <= idx < len(hashed_lines): + line = hashed_lines[idx] + new_content = strip_hashline(line) + if new_content == expected_content: + # Return the hashline part: |{line_num}{frag}| + parts = line.split("|") + if len(parts) >= 2: + return parts[1] + except Exception: + pass + return None + + def find_hashline_by_exact_match(hashed_lines, hash_fragment, line_num_str): """ Find a hashline by |{exact line_num}{hash_fragment match}|. @@ -275,11 +312,164 @@ def find_hashline_by_fragment(hashed_lines, hash_fragment, target_line_num=None) return matches[0][1] +def find_hashline_by_line_number(hashed_lines, line_number): + """ + Find the line index for a specific line number. + + Args: + hashed_lines: List of hashed lines + line_number: Line number to look up (1-indexed) + + Returns: + int: Index of the specified line (0-indexed), or None if not found + """ + # Convert to 0-indexed for list access + idx = line_number - 1 + + # Check bounds + if idx < 0 or idx >= len(hashed_lines): + return None + + # Return the index + return idx + + +def get_adjacent_lines(hashed_lines, idx, is_start=True): + """ + Get adjacent lines for a given index, considering whether it's for start or end of a range. + + Args: + hashed_lines: List of hashed lines + idx: Index to get adjacent lines for (0-indexed) + is_start: Whether this is for start (True) or end (False) of a range + + Returns: + list: List of adjacent line contents (without hashline prefixes) + """ + adjacent = [] + + if is_start: + # For start: get lines after the index + # Get line at index (the start line itself) + if 0 <= idx < len(hashed_lines): + line_at_idx = hashed_lines[idx] + match = HASHLINE_PREFIX_RE.match(line_at_idx) + if match: + content = line_at_idx[match.end() :] + adjacent.append(content) + + # Get line after (if exists) + if idx < len(hashed_lines) - 1: + line_after = hashed_lines[idx + 1] + match = HASHLINE_PREFIX_RE.match(line_after) + if match: + content = line_after[match.end() :] + adjacent.append(content) + else: + # For end: get lines before the index + # Get line before (if exists) + if idx > 0: + line_before = hashed_lines[idx - 1] + match = HASHLINE_PREFIX_RE.match(line_before) + if match: + content = line_before[match.end() :] + adjacent.append(content) + + # Get line at index (the end line itself) + if 0 <= idx < len(hashed_lines): + line_at_idx = hashed_lines[idx] + match = HASHLINE_PREFIX_RE.match(line_at_idx) + if match: + content = line_at_idx[match.end() :] + adjacent.append(content) + + return adjacent + + +def _line_or_fragment(hashed_lines, hash_fragment, line_number, replacement_lines, is_start=True): + """ + Decide between hash-based or line-based lookup using cosine similarity. + + When exact matching fails, this function determines whether to use + find_hashline_by_fragment() or find_hashline_by_line_number() by comparing + adjacent lines with replacement text using cosine similarity of bigram vectors. + + Args: + hashed_lines: List of hashed lines + hash_fragment: Hash fragment to search for + line_number: Line number to search for (1-indexed) + replacement_lines: List of lines in replacement text + is_start: Whether this is for start (True) or end (False) fragment + + Returns: + int: Index to use (from either fragment-based or line-based lookup) + """ + # Get indices from both methods + idx_fragment = find_hashline_by_fragment(hashed_lines, hash_fragment, line_number) + idx_line = find_hashline_by_line_number(hashed_lines, line_number) + + # If one method fails, use the other + if idx_fragment is None: + return idx_line + if idx_line is None: + return idx_fragment + + # If both methods return the same index, it doesn't matter which we use + if idx_fragment == idx_line: + return idx_fragment + + # Get replacement lines to compare + if is_start: + # For start: compare with first 3 lines of replacement + compare_replacement_lines = replacement_lines[:3] + else: + # For end: compare with last 3 lines of replacement + compare_replacement_lines = replacement_lines[-3:] + + # Skip if no replacement lines to compare + if not compare_replacement_lines: + return idx_fragment # Default to fragment-based + + # Get adjacent lines for both indices using the new get_adjacent_lines function + # For start fragments, we want lines after the index (including the line itself) + # For end fragments, we want lines before the index (including the line itself) + adjacent_fragment = get_adjacent_lines(hashed_lines, idx_fragment, is_start) + adjacent_line = get_adjacent_lines(hashed_lines, idx_line, is_start) + + # Skip if no adjacent lines to compare + if not adjacent_fragment and not adjacent_line: + return idx_fragment # Default to fragment-based + + # Calculate longest common substring for fragment-based method + score_fragment = 0 + if adjacent_fragment: + adjacent_text = "".join(adjacent_fragment) + replacement_text = "".join(compare_replacement_lines) + match_fragment = longest_common_substring(adjacent_text, replacement_text) + score_fragment = len(match_fragment) + + # Calculate longest common substring for line-based method + score_line = 0 + if adjacent_line: + adjacent_text = "".join(adjacent_line) + replacement_text = "".join(compare_replacement_lines) + match_line = longest_common_substring(adjacent_text, replacement_text) + score_line = len(match_line) + + # Choose method with higher score + # If scores are equal, default to line-based matching + if score_line >= score_fragment: + return idx_line + else: + return idx_fragment + + def find_hashline_range( hashed_lines, start_line_hash, end_line_hash, allow_exact_match=True, + replacement_text=None, ): """ Find start and end line indices in hashed content. @@ -296,6 +486,11 @@ def find_hashline_range( Raises: HashlineError: If range cannot be found or is invalid """ + # Convert replacement_text to lines if provided + replacement_lines = [] + if replacement_text: + replacement_lines = replacement_text.split("\n") + # Parse start_line_hash start_hash_fragment, start_line_num_str, start_line_num = parse_hashline(start_line_hash) found_start_line = None @@ -316,9 +511,12 @@ def find_hashline_range( ) if found_start_line is None: - found_start_line = find_hashline_by_fragment( - hashed_lines, start_hash_fragment, start_line_num - ) + if replacement_text: + found_start_line = _line_or_fragment( + hashed_lines, start_hash_fragment, start_line_num, replacement_lines, is_start=True + ) + else: + found_start_line = find_hashline_by_line_number(hashed_lines, start_line_num) if found_start_line is None: raise HashlineError(f"Start line hash fragment '{start_hash_fragment}' not found in file") @@ -334,40 +532,15 @@ def find_hashline_range( ) if found_end_line is None: - # Calculate line distance - line_distance = end_line_num - start_line_num - if line_distance < 0: - raise HashlineError( - f"End line {end_line_num} must be equal to or after start line {start_line_num}" - ) - - # Check if end hash fragment exists at the expected distance - expected_found_end_line = found_start_line + line_distance - if expected_found_end_line >= len(hashed_lines): - raise HashlineError( - f"Start hash fragment found at line {found_start_line + 1}, but " - f"end line {expected_found_end_line + 1} is out of range." - ) - - # Check if end hash fragment matches at the expected position - # If not, use find_hashline_by_fragment() to find the closest match - actual_end_hashed_line = hashed_lines[expected_found_end_line] - match = HASHLINE_PREFIX_RE.match(actual_end_hashed_line) - actual_end_hash_fragment = match.group(2) if match else None - - if actual_end_hash_fragment != end_hash_fragment: - # Instead of raising an error, try to find the closest matching hash fragment - # near where the end line would be based on distance from start line - found_end_line = find_hashline_by_fragment( - hashed_lines, end_hash_fragment, expected_found_end_line + if replacement_text: + found_end_line = _line_or_fragment( + hashed_lines, end_hash_fragment, end_line_num, replacement_lines, is_start=False ) - if found_end_line is None: - raise HashlineError( - f"End line hash fragment '{end_hash_fragment}' not found near " - f"expected position {expected_found_end_line + 1}." - ) else: - found_end_line = expected_found_end_line + found_end_line = find_hashline_by_line_number(hashed_lines, end_line_num) + + if found_end_line is None: + raise HashlineError(f"End line hash fragment '{end_hash_fragment}' not found in file") # Verify end line is not before start line if found_end_line < found_start_line: @@ -379,86 +552,6 @@ def find_hashline_range( return found_start_line, found_end_line -def apply_hashline_operation( - original_content, - start_line_hash, - end_line_hash=None, - operation="replace", - text=None, -): - """ - Apply an operation (replace, insert, delete) using hashline ranges. - - Uses regex/find to locate hashline ranges in the content and applies - the specified operation directly. - - Note: Ranges are inclusive of both start and end boundaries. - For example, a range from line 3 to line 6 includes lines 3, 4, 5, and 6. - - Args: - original_content: Original file content - start_line_hash: Hashline format for start line: "{hash_fragment}:{line_num}" - end_line_hash: Hashline format for end line: "{hash_fragment}:{line_num}" (optional for insert operations) - operation: One of "replace", "insert", or "delete" - text: Text to insert or replace with (required for replace/insert operations) - - Returns: - Modified content after applying the operation - - Raises: - HashlineError: If hashline verification fails or operation is invalid - """ - # Handle empty content as a special case - if original_content == "" or original_content is None: - if operation == "insert" or operation == "replace": - if text is None: - raise HashlineError( - f"Text parameter is required for '{operation}' operation on empty file" - ) - # For empty files, just return the text to insert/replace with - return text if text.endswith("\n") else text + "\n" - elif operation == "delete": - # Deleting from empty file returns empty - return "" - else: - # Should not happen due to validation above, but handle anyway - raise HashlineError(f"Invalid operation '{operation}' for empty file") - - # Validate operation - valid_operations = {"replace", "insert", "delete"} - if operation not in valid_operations: - raise HashlineError( - f"Invalid operation '{operation}'. Must be one of: {', '.join(valid_operations)}" - ) - - # Validate text parameter for replace/insert operations - if operation in {"replace", "insert"} and text is None: - raise HashlineError(f"Text parameter is required for '{operation}' operation") - - # Build operation dictionary for apply_hashline_operations - op_dict = { - "start_line_hash": start_line_hash, - "operation": operation, - } - - if end_line_hash is not None: - op_dict["end_line_hash"] = end_line_hash - - if text is not None: - op_dict["text"] = text - - # Call apply_hashline_operations with single operation - modified_content, successful_ops, failed_ops = apply_hashline_operations( - original_content, [op_dict] - ) - - # Check if operation failed - if failed_ops: - raise HashlineError(failed_ops[0]["error"]) - - return modified_content - - def extract_hashline_range( original_content, start_line_hash, @@ -469,8 +562,8 @@ def extract_hashline_range( Args: original_content: Original file content - start_line_hash: Hashline format for start line: "{hash_fragment}:{line_num}" - end_line_hash: Hashline format for end line: "{hash_fragment}:{line_num}" + start_line_hash: Hashline format for start line: "{line_num}{hash_fragment}" + end_line_hash: Hashline format for end line: "{line_num}{hash_fragment}" Returns: str: The extracted content between the hashline markers (with hashline prefixes preserved) @@ -551,8 +644,8 @@ def get_hashline_diff( Args: original_content: Original file content - start_line_hash: Hashline format for start line: "{hash_fragment}:{line_num}" - end_line_hash: Hashline format for end line: "{hash_fragment}:{line_num}" + start_line_hash: Hashline format for start line: "{line_num}{hash_fragment}" + end_line_hash: Hashline format for end line: "{line_num}{hash_fragment}" operation: One of "replace", "insert", or "delete" text: Text to insert or replace with (required for replace/insert operations) @@ -1141,88 +1234,105 @@ def _apply_range_shifting(hashed_lines, resolved_ops): return resolved_ops -def _apply_closure_safeguard(hashed_lines, resolved_ops): - """ - Apply closure safeguard for replace operations ending with braces/brackets. +# Regex configuration +RE_CODE_NOISE = r'(#.*|//.*|/\*[\s\S]*?\*/|"(?:\\.|[^"\\])*"|\'(?:\\.|[^\'\\])*\')' - Detects when replacement text ends in a brace or bracket and if the end line - of the replacement range is also a brace or bracket but with fewer spaces/tabs - preceding it (less indented), moves the resolved end range up one line. - This prevents including outer closing braces/brackets in the replacement range - when the model includes them in the replacement text. +def get_brace_balance(lines_to_check: list[str]) -> int: + """ + Calculates the net curly brace debt of a list of lines. + Automatically strips hashlines, comments, and string literals. + """ + text = "".join(lines_to_check) + clean_code = strip_hashline(text) + clean_code = re.sub(RE_CODE_NOISE, "", clean_code) + return clean_code.count("{") - clean_code.count("}") - Args: - hashed_lines: List of hashed lines from the file - resolved_ops: List of resolved operation dictionaries - Returns: - Updated resolved_ops with adjusted ranges for closure safeguard +def _apply_closure_safeguard(hashed_lines, resolved_ops): + """ + Enhanced closure safeguard with dynamic bidirectional search. """ + # Tune these to adjust how far the 'healing' logic searches + MAX_LOOK_DOWN = 5 + # Note: We'll calculate the actual MAX_LOOK_UP per operation + # to ensure we don't scan past the start_idx. + for i, resolved in enumerate(resolved_ops): op = resolved["op"] - if op["operation"] == "replace" and op.get("text"): - replacement_lines = op["text"].splitlines(keepends=True) - if not replacement_lines: - continue + if op["operation"] not in {"replace", "delete"}: + continue - # Check if replacement text ends with a brace or bracket - last_replacement_line = strip_hashline(replacement_lines[-1]) - last_replacement_line_stripped = last_replacement_line.strip() - - # Check if it ends with a closing brace/bracket (ignoring trailing punctuation) - check_text = last_replacement_line_stripped.rstrip(";,") - if check_text and check_text[-1] in "})]": - # Get the indentation of the last replacement line - # Count leading spaces/tabs - replacement_indent = 0 - for char in last_replacement_line: - if char in " \t": - replacement_indent += 1 - else: + replacement_text = op.get("text", "") or "" + replacement_lines = replacement_text.splitlines(keepends=True) + + # --- PHASE 1: BIDIRECTIONAL STRUCTURAL HEALING --- + if get_brace_balance([replacement_text]) == 0: + start_idx = resolved["start_idx"] + orig_end_idx = resolved["end_idx"] + + if get_brace_balance(hashed_lines[start_idx : orig_end_idx + 1]) != 0: + # Dynamic Search List Generation + # We limit look-up so we don't scan before the start_idx + actual_max_up = orig_end_idx - start_idx + actual_max_down = max(MAX_LOOK_DOWN, orig_end_idx - start_idx) + search_offsets = [] + + # Generate alternating offsets: [1, -1, 2, -2, ... N] + for dist in range(1, max(actual_max_down, actual_max_up) + 1): + if dist <= actual_max_down: + search_offsets.append(dist) + if dist <= actual_max_up: + search_offsets.append(-dist) + + for offset in search_offsets: + candidate_end = orig_end_idx + offset + + # Safety: check bounds and avoid overlapping other ops + if candidate_end < start_idx or candidate_end >= len(hashed_lines): + continue + + if any( + j != i and (other["start_idx"] <= candidate_end <= other["end_idx"]) + for j, other in enumerate(resolved_ops) + ): + continue + + if get_brace_balance(hashed_lines[start_idx : candidate_end + 1]) == 0: + resolved["end_idx"] = candidate_end break - # Check if the end line of the range is also a brace/bracket - if resolved["end_idx"] < len(hashed_lines): - end_line = strip_hashline(hashed_lines[resolved["end_idx"]]) - end_line_stripped = end_line.strip() - - # Check if it ends with a closing brace/bracket (ignoring trailing punctuation) - check_end = end_line_stripped.rstrip(";,") - if check_end and check_end[-1] in "})]": - # Get indentation of the end line - end_line_indent = 0 - for char in end_line: - if char in " \t": - end_line_indent += 1 - else: - break + # --- PHASE 2: CONTRACTION (Indentation Guard) --- + # Prevents replacing an outer-scope brace if the replacement text already + # includes its own correctly indented closer. + if not replacement_lines: + continue + + last_repl_line = strip_hashline(replacement_lines[-1]) + last_repl_stripped = last_repl_line.strip().rstrip(";,") + + if last_repl_stripped and last_repl_stripped[-1] in "})]": + # Calculate replacement indent + repl_indent = len(last_repl_line) - len(last_repl_line.lstrip(" \t")) + + if resolved["end_idx"] < len(hashed_lines): + end_line = strip_hashline(hashed_lines[resolved["end_idx"]]) + check_end = end_line.strip().rstrip(";,") + + if check_end and check_end[-1] in "})]": + # Calculate indent of the existing brace in the file + file_indent = len(end_line) - len(end_line.lstrip(" \t")) + + # If the file's brace is less indented, it belongs to an outer scope + if file_indent < repl_indent and resolved["end_idx"] > resolved["start_idx"]: + new_end_idx = resolved["end_idx"] - 1 - # If end line has less indentation (fewer spaces/tabs) - # and we're not at the start of the range - if ( - end_line_indent < replacement_indent - and resolved["end_idx"] > resolved["start_idx"] + # Safety: don't contract into another operation's territory + if not any( + j != i and (other["start_idx"] <= new_end_idx <= other["end_idx"]) + for j, other in enumerate(resolved_ops) ): - # Check if moving up one line would still be valid - new_end_idx = resolved["end_idx"] - 1 - - # Safety check: ensure new range doesn't overlap with another operation - overlap = False - for j, other in enumerate(resolved_ops): - if i != j and ( - ( - other["start_idx"] - <= resolved["start_idx"] - <= other["end_idx"] - ) - or (other["start_idx"] <= new_end_idx <= other["end_idx"]) - ): - overlap = True - break - - if not overlap: - resolved["end_idx"] = new_end_idx + resolved["end_idx"] = new_end_idx return resolved_ops @@ -1313,11 +1423,14 @@ def apply_hashline_operations( # Normalize hashline inputs in operations normalized_operations = [] failed_ops = [] + # Loop through each operation to normalize hashline strings for i, op in enumerate(operations): try: normalized_op = op.copy() + # Normalize start line hash to ensure consistent format normalized_op["start_line_hash"] = normalize_hashline(op["start_line_hash"]) if "end_line_hash" in op: + # Normalize end line hash if present normalized_op["end_line_hash"] = normalize_hashline(op["end_line_hash"]) normalized_operations.append(normalized_op) except Exception as e: @@ -1327,11 +1440,13 @@ def apply_hashline_operations( return original_content, [], failed_ops # Apply hashline to original content once + # This converts content to hashed lines for line tracking hashed_content = hashline(original_content) hashed_lines = hashed_content.splitlines(keepends=True) # Resolve all operations to indices first resolved_ops = [] + # Loop to convert hashline references to line indices for i, op in enumerate(normalized_operations): try: if op["operation"] == "insert": @@ -1351,6 +1466,7 @@ def apply_hashline_operations( ) if found_start is None: + # Fall back to fragment matching if exact match fails found_start = find_hashline_by_fragment( hashed_lines, start_hash_fragment, start_line_num ) @@ -1366,13 +1482,47 @@ def apply_hashline_operations( else: # Use find_hashline_range for replace/delete to leverage its robust logic # which handles exact matches (including line numbers) and relative offsets - found_start, found_end = find_hashline_range( - hashed_lines, op["start_line_hash"], op["end_line_hash"], allow_exact_match=True - ) - resolved_ops.append( - {"index": i, "start_idx": found_start, "end_idx": found_end, "op": op} - ) + start_hash = op["start_line_hash"] + end_hash = op.get("end_line_hash") + + if "text" in op and op["text"]: + replacement_lines = op["text"].splitlines(keepends=True) + if replacement_lines: + # Try content match for start line + match = find_hashline_by_content_match( + hashed_lines, start_hash, replacement_lines[0] + ) + if match: + start_hash = match + + # Try content match for end line + if end_hash: + match = find_hashline_by_content_match( + hashed_lines, end_hash, replacement_lines[-1] + ) + if match: + end_hash = match + + # Fall back to original find_hashline_range + try: + # Get replacement text for replace operations, None for delete operations + replacement_text = op.get("text") + found_start, found_end = find_hashline_range( + hashed_lines, + start_hash, + end_hash, + allow_exact_match=True, + replacement_text=replacement_text, + ) + resolved_ops.append( + {"index": i, "start_idx": found_start, "end_idx": found_end, "op": op} + ) + except Exception as e: + raise HashlineError( + f"Could not resolve hash range {start_hash}-{end_hash}: {str(e)}" + ) + except Exception as e: failed_ops.append({"index": i, "error": str(e), "operation": op}) @@ -1381,6 +1531,7 @@ def apply_hashline_operations( deduplicated_ops = [] # Group operations by start_idx start_idx_to_ops = {} + # Loop to group operations by their start index for op in resolved_ops: start_idx = op["start_idx"] if start_idx not in start_idx_to_ops: @@ -1388,6 +1539,7 @@ def apply_hashline_operations( start_idx_to_ops[start_idx].append(op) # For each start_idx, keep only the operation with the highest original index (latest in the list) + # Loop to select only the latest operation per start index for start_idx, ops in start_idx_to_ops.items(): # Sort by original index descending and take the first one ops.sort(key=lambda x: x["index"], reverse=True) @@ -1399,6 +1551,7 @@ def apply_hashline_operations( # Optimize: discard inner ranges that are completely contained within outer ranges # This prevents redundant operations and potential errors optimized_ops = [] + # Loop to remove operations that are completely contained within other operations for i, op_a in enumerate(resolved_ops): keep_op = True @@ -1457,6 +1610,7 @@ def sort_key(op): resolved_ops.sort(key=sort_key) successful_ops = [] + # Loop to apply operations in sorted order (bottom-to-top) for resolved in resolved_ops: try: op = resolved["op"] @@ -1524,6 +1678,7 @@ def sort_key(op): # Join and strip hashlines result_with_hashes = "".join(hashed_lines) + # Remove hashline markers from final result result = strip_hashline(result_with_hashes) # Respect original trailing newline @@ -1531,3 +1686,83 @@ def sort_key(op): result = result[:-1] return result, successful_ops, failed_ops + + +def apply_hashline_operation( + original_content, + start_line_hash, + end_line_hash=None, + operation="replace", + text=None, +): + """ + Apply an operation (replace, insert, delete) using hashline ranges. + + Uses regex/find to locate hashline ranges in the content and applies + the specified operation directly. + + Note: Ranges are inclusive of both start and end boundaries. + For example, a range from line 3 to line 6 includes lines 3, 4, 5, and 6. + + Args: + original_content: Original file content + start_line_hash: Hashline format for start line: "{line_num}{hash_fragment}" + end_line_hash: Hashline format for end line: "{line_num}{hash_fragment}" (optional for insert operations) + operation: One of "replace", "insert", or "delete" + text: Text to insert or replace with (required for replace/insert operations) + + Returns: + Modified content after applying the operation + + Raises: + HashlineError: If hashline verification fails or operation is invalid + """ + # Handle empty content as a special case + if original_content == "" or original_content is None: + if operation == "insert" or operation == "replace": + if text is None: + raise HashlineError( + f"Text parameter is required for '{operation}' operation on empty file" + ) + # For empty files, just return the text to insert/replace with + return text if text.endswith("\n") else text + "\n" + elif operation == "delete": + # Deleting from empty file returns empty + return "" + else: + # Should not happen due to validation above, but handle anyway + raise HashlineError(f"Invalid operation '{operation}' for empty file") + + # Validate operation + valid_operations = {"replace", "insert", "delete"} + if operation not in valid_operations: + raise HashlineError( + f"Invalid operation '{operation}'. Must be one of: {', '.join(valid_operations)}" + ) + + # Validate text parameter for replace/insert operations + if operation in {"replace", "insert"} and text is None: + raise HashlineError(f"Text parameter is required for '{operation}' operation") + + # Build operation dictionary for apply_hashline_operations + op_dict = { + "start_line_hash": start_line_hash, + "operation": operation, + } + + if end_line_hash is not None: + op_dict["end_line_hash"] = end_line_hash + + if text is not None: + op_dict["text"] = text + + # Call apply_hashline_operations with single operation + modified_content, successful_ops, failed_ops = apply_hashline_operations( + original_content, [op_dict] + ) + + # Check if operation failed + if failed_ops: + raise HashlineError(failed_ops[0]["error"]) + + return modified_content diff --git a/cecli/helpers/responses.py b/cecli/helpers/responses.py index c6393dc0983..efeb69dac51 100644 --- a/cecli/helpers/responses.py +++ b/cecli/helpers/responses.py @@ -1,4 +1,11 @@ +import json import re +import time +from typing import List, Optional + +from litellm.types.utils import ChatCompletionMessageToolCall, Function + +from cecli import utils def preprocess_json(response: str) -> str: @@ -19,3 +26,107 @@ def normalize(match): return "\\\\" + suffix return re.sub(pattern, normalize, response) + + +def extract_tools_from_content_json(content: str) -> Optional[List[ChatCompletionMessageToolCall]]: + """ + Simple extraction of JSON-like structures that look like tool calls. + This handles models that write JSON in text instead of using native calling. + """ + if not content or ("{" not in content and "[" not in content): + return None + + try: + json_chunks = utils.split_concatenated_json(content) + extracted_calls = [] + chunk_index = 0 + + for chunk in json_chunks: + chunk_index += 1 + try: + json_obj = json.loads(chunk) + if isinstance(json_obj, dict) and "name" in json_obj and "arguments" in json_obj: + # Create a Pydantic model for the tool call + function_obj = Function( + name=json_obj["name"], + arguments=( + json.dumps(json_obj["arguments"]) + if isinstance(json_obj["arguments"], (dict, list)) + else str(json_obj["arguments"]) + ), + ) + tool_call_obj = ChatCompletionMessageToolCall( + type="function", + function=function_obj, + id=f"call_{len(extracted_calls)}_{int(time.time())}_{chunk_index}", + ) + extracted_calls.append(tool_call_obj) + elif isinstance(json_obj, list): + for item in json_obj: + if isinstance(item, dict) and "name" in item and "arguments" in item: + function_obj = Function( + name=item["name"], + arguments=( + json.dumps(item["arguments"]) + if isinstance(item["arguments"], (dict, list)) + else str(item["arguments"]) + ), + ) + tool_call_obj = ChatCompletionMessageToolCall( + type="function", + function=function_obj, + id=f"call_{len(extracted_calls)}_{int(time.time())}_{chunk_index}", + ) + extracted_calls.append(tool_call_obj) + except json.JSONDecodeError: + continue + + return extracted_calls if extracted_calls else None + except Exception: + return None + + +def extract_tools_from_content_xml(content: str) -> Optional[List[ChatCompletionMessageToolCall]]: + """ + Extraction of Qwen-style XML tool calls. + Example: + + + [{"task": "Update task list", "done": false, "current": true}] + + + """ + if not content or " and + func_blocks = re.finditer(r"(.*?)", content, re.DOTALL) + + for i, block_match in enumerate(func_blocks): + func_name = block_match.group(1).strip() + block_content = block_match.group(2).strip() + + params_dict = {} + param_pattern = r"(.*?)" + for param_match in re.finditer(param_pattern, block_content, re.DOTALL): + key = param_match.group(1).strip() + value_str = param_match.group(2).strip() + try: + params_dict[key] = json.loads(value_str) + except json.JSONDecodeError: + params_dict[key] = value_str + + function_obj = Function(name=func_name, arguments=json.dumps(params_dict)) + + tool_call_obj = ChatCompletionMessageToolCall( + type="function", + function=function_obj, + id=f"xml_call_{i}_{int(time.time())}", + ) + extracted_calls.append(tool_call_obj) + + return extracted_calls if extracted_calls else None + except Exception: + return None diff --git a/cecli/main.py b/cecli/main.py index bc6e9dfe5e9..23a4008232a 100644 --- a/cecli/main.py +++ b/cecli/main.py @@ -454,6 +454,20 @@ async def sanity_check_repo(repo, io): return False +def interpolate_env_vars(value): + """Interpolate environment variables in the form ${VAR} or $VAR.""" + if not isinstance(value, str): + return value + + def replace_var(match): + var_name = match.group(1) or match.group(2) + return os.getenv(var_name, match.group(0)) + + # Matches ${VAR} or $VAR + pattern = r"\$\{([\w_]+)\}|\$([\w_]+)" + return re.sub(pattern, replace_var, value) + + PROJECT_ROOT = os.path.abspath(os.path.dirname(__file__)) log_file = None file_excludelist = { @@ -572,6 +586,15 @@ async def main_async(argv=None, input=None, output=None, force_git_root=None, re if hasattr(args, "hooks") and args.hooks is not None: args.hooks = convert_yaml_to_json_string(args.hooks) + # Interpolate environment variables in all string arguments + for key, value in vars(args).items(): + if isinstance(value, str): + setattr(args, key, interpolate_env_vars(value)) + elif isinstance(value, list): + setattr( + args, key, [interpolate_env_vars(v) if isinstance(v, str) else v for v in value] + ) + if args.debug: global log_file os.makedirs(".cecli/logs/", exist_ok=True) @@ -661,7 +684,7 @@ def get_io(pretty): supress_tui = False except ImportError as e: print("Error: --tui requires 'textual' package") - print("Install with: pip install cecli[tui]") + print("Install with: pip install cecli-dev[tui]") print(f"Import error: {e}") sys.exit(1) diff --git a/cecli/prompts/agent.yml b/cecli/prompts/agent.yml index 32a8f9477a1..4f15c9364a3 100644 --- a/cecli/prompts/agent.yml +++ b/cecli/prompts/agent.yml @@ -37,10 +37,11 @@ main_system: | - Break complex tasks into granular steps to maintain context across long interactions. ### Editing Tools (Precision Protocol) - Files use hashline prefixes: `{{line_num}}|{{hash_fragment}}`. + Files use hashline prefixes: `{{line_num}}{{hash_fragment}}`. - **MANDATORY Two-Turn Safety Protocol**: 1. **Turn 1**: Use `ShowNumberedContext` to verify exact, current line numbers. 2. **Turn 2**: Execute the edit (Replace, Insert, Delete, Indent) using those verified numbers. + - **Atomic Scope:** Include the **entire function or logical block**. Never return partial syntax or broken closures. Do not attempt to replace just the beginning or end of a closure. - **Indentation**: Preserve all spaces and tabs. In Python, a single-space error is a syntax error. Use `IndentText` to fix structural alignment. @@ -54,7 +55,7 @@ system_reminder: | - **Context Hygiene**: Remove files or skills from context using `ContextManager` or `RemoveSkill` once they are no longer needed to save tokens and prevent confusion. - **Turn Management**: Tool calls trigger the next turn. Do not include tool calls in your final summary to the user. - **Sandbox**: Use `.cecli/workspace` for all verification and temporary logic. - - **Precision**: Never guess line numbers. Always use `ShowNumberedContext` first. + - **Novelty**: Do not repeat phrases in your responses to the user. You do not need to declare you understand the task. Simply proceed. {lazy_prompt} {shell_cmd_reminder} diff --git a/cecli/prompts/hashline.yml b/cecli/prompts/hashline.yml index aa2974fbeba..79c6e6b02e4 100644 --- a/cecli/prompts/hashline.yml +++ b/cecli/prompts/hashline.yml @@ -9,11 +9,11 @@ main_system: | Files are provided in "Hashline" format. Each line starts with a leading pipe (|), the line number and a 2-character hash, and a trailing pipe. **Example File Format :** - |1Hm|#!/usr/bin/env python3 - |2eU| - |3mL|def example_method(): + |1hm|#!/usr/bin/env python3 + |2eu| + |3ml|def example_method(): |4bk| return "example" - |5eU| + |5eu| ### 2. FILE ACCESS & WORKFLOW - If you need to edit files NOT yet in the chat, list their full paths and ask the user to add them. @@ -32,18 +32,14 @@ main_system: | >>>>>>> CONTENTS {fence[1]} - ### 4. EDITING RULES - - **JSON ONLY:** The area between `<<<<<<< LOCATE` and `=======` must contain ONLY the JSON array (e.g., `["3mL", "4bk", "replace"]`). Never include source code here. - - **Operations:** `replace` (overwrites range) or `delete` (removes range). + ### 4. EDITING PROTOCOL & VALIDATION + - **JSON ONLY:** The LOCATE block must contain ONLY the JSON array (e.g., ["3ml", "4bk", "replace"]). No source code. + - **Operations:** Use `replace` to overwrite, `delete` for removal (empty CONTENTS), or the Genesis anchor `["0aa", "0aa", "replace"]` for new files. - **Inclusion:** Ranges are inclusive of the start and end hashlines. - - **New Files:** To create a file, use the "Genesis" anchor: `["0aa", "0aa", "replace"]`. - - **Integrity:** Include full method/loop bodies. No partial syntax. - - **Constraints:** No overlapping ranges. Do not use the `end_hash` of one block as the `start_hash` of the next. - - ### 5. QUALITY STANDARDS - - Respect existing conventions and libraries. - - Include full method/function/control flow/loop bodies in edits to ensure syntactical correctness. - - Think through changes for edge cases, syntax errors and duplicated code before outputting blocks. + - **Atomic Scope:** Include the **entire function or logical block**. Never return partial syntax or broken closures. Do not attempt to replace just the beginning or end of a closure. + - **Indentation:** CONTENTS must match the exact indentation level of the target file. + - **No Adjacency:** Do not chain blocks where end_hash = next start_hash. Merge them into a single larger range instead. + - **No Overlaps:** Do not specify ranges with overlapping line numbers. You must combine or rewrite the larger range if you want to change your implementation. {shell_cmd_prompt} {final_reminders} @@ -61,7 +57,7 @@ example_messages: mathweb/flask/app.py {fence[0]}python <<<<<<< LOCATE - ["2Mk", "3Ul", "replace"] + ["2mk", "3ul", "replace"] ======= import math from flask import Flask @@ -70,15 +66,16 @@ example_messages: mathweb/flask/app.py {fence[0]}python <<<<<<< LOCATE - ["10cD", "15eF", "delete"] + ["10ca", "15je", "delete"] ======= >>>>>>> CONTENTS {fence[1]} mathweb/flask/app.py {fence[0]}python <<<<<<< LOCATE - ["20gH", "20gH", "replace"] + ["20dw", "24rb", "replace"] ======= + def get_factorial(): return str(math.factorial(n)) >>>>>>> CONTENTS {fence[1]} @@ -103,7 +100,7 @@ example_messages: main.py {fence[0]}python <<<<<<< LOCATE - ["5iJ", "8kL", "replace"] + ["5ij", "8kl", "replace"] ======= from hello import hello >>>>>>> CONTENTS diff --git a/cecli/resources/model-metadata.json b/cecli/resources/model-metadata.json index 2ee97110a60..d5ea0a5e95c 100644 --- a/cecli/resources/model-metadata.json +++ b/cecli/resources/model-metadata.json @@ -45,53 +45,9 @@ "output_cost_per_token": 7e-7, "supports_system_messages": true }, - "us.writer.palmyra-x4-v1:0": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true, - "supports_pdf_input": true - }, - "us.writer.palmyra-x5-v1:0": { - "input_cost_per_token": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_function_calling": true, - "supports_pdf_input": true - }, - "writer.palmyra-x4-v1:0": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true, - "supports_pdf_input": true - }, - "writer.palmyra-x5-v1:0": { - "input_cost_per_token": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_function_calling": true, - "supports_pdf_input": true - }, - "amazon.nova-lite-v1:0": { + "amazon-nova/nova-lite-v1": { "input_cost_per_token": 6e-8, - "litellm_provider": "bedrock_converse", + "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, @@ -103,87 +59,55 @@ "supports_response_schema": true, "supports_vision": true }, - "amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_video_input": true, - "supports_vision": true - }, - "amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-7, - "input_cost_per_token": 0.0000021875, - "input_cost_per_image_token": 0.0000021875, - "input_cost_per_audio_token": 0.0000021875, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "amazon-nova/nova-micro-v1": { + "input_cost_per_token": 3.5e-8, + "litellm_provider": "amazon_nova", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.0000175, + "output_cost_per_token": 1.4e-7, "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_video_input": true, - "supports_vision": true + "supports_response_schema": true }, - "apac.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-8, - "input_cost_per_token": 3.3e-7, - "litellm_provider": "bedrock_converse", + "amazon-nova/nova-premier-v1": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.00000275, + "output_cost_per_token": 0.0000125, "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_prompt_caching": false, "supports_response_schema": true, - "supports_video_input": true, "supports_vision": true }, - "apac.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-7, - "input_cost_per_token": 0.0000021875, - "input_cost_per_image_token": 0.0000021875, - "input_cost_per_audio_token": 0.0000021875, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "amazon-nova/nova-pro-v1": { + "input_cost_per_token": 8e-7, + "litellm_provider": "amazon_nova", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.0000175, + "output_cost_per_token": 0.0000032, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_video_input": true, "supports_vision": true }, - "eu.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-8, - "input_cost_per_token": 3.3e-7, + "amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.00000275, + "output_cost_per_token": 0.0000025, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -192,7 +116,7 @@ "supports_video_input": true, "supports_vision": true }, - "eu.amazon.nova-2-pro-preview-20251202-v1:0": { + "amazon.nova-2-pro-preview-20251202-v1:0": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, @@ -211,40 +135,18 @@ "supports_video_input": true, "supports_vision": true }, - "us.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-8, - "input_cost_per_token": 3.3e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.00000275, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_video_input": true, - "supports_vision": true - }, - "us.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-7, - "input_cost_per_token": 0.0000021875, - "input_cost_per_image_token": 0.0000021875, - "input_cost_per_audio_token": 0.0000021875, + "amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.0000175, + "output_cost_per_token": 2.4e-7, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_video_input": true, "supports_vision": true }, "amazon.nova-micro-v1:0": { @@ -273,27 +175,6 @@ "supports_response_schema": true, "supports_vision": true }, - "twelvelabs.pegasus-1-2-v1:0": { - "input_cost_per_video_per_second": 0.00049, - "output_cost_per_token": 0.0000075, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_video_input": true - }, - "us.twelvelabs.pegasus-1-2-v1:0": { - "input_cost_per_video_per_second": 0.00049, - "output_cost_per_token": 0.0000075, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_video_input": true - }, - "eu.twelvelabs.pegasus-1-2-v1:0": { - "input_cost_per_video_per_second": 0.00049, - "output_cost_per_token": 0.0000075, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_video_input": true - }, "amazon.titan-text-express-v1": { "input_cost_per_token": 0.0000013, "litellm_provider": "bedrock", @@ -338,51 +219,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.00000125, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "anthropic.claude-haiku-4-5@20251001": { - "cache_creation_input_token_cost": 0.00000125, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_native_streaming": true - }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", @@ -517,31 +353,17 @@ "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 }, - "anthropic.claude-instant-v1": { - "input_cost_per_token": 8e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.0000024, - "supports_tool_choice": true - }, - "anthropic.claude-opus-4-1-20250805-v1:0": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, + "anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -551,9 +373,42 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "tool_use_system_prompt_tokens": 346 }, - "anthropic.claude-opus-4-20250514-v1:0": { + "anthropic.claude-haiku-4-5@20251001": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "supports_native_streaming": true + }, + "anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000024, + "supports_tool_choice": true + }, + "anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, @@ -579,16 +434,16 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, - "anthropic.claude-opus-4-5-20251101-v1:0": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, + "anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000025, + "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -605,26 +460,22 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, - "anthropic.claude-opus-4-6-v1": { + "anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000125, "cache_read_input_token_cost": 5e-7, - "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token": 0.000005, - "input_cost_per_token_above_200k_tokens": 0.00001, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, - "output_cost_per_token_above_200k_tokens": 0.0000375, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": false, + "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -633,9 +484,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 159 }, - "global.anthropic.claude-opus-4-6-v1": { + "anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_200k_tokens": 0.0000125, "cache_read_input_token_cost": 5e-7, @@ -665,86 +516,26 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "us.anthropic.claude-opus-4-6-v1": { - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_200k_tokens": 0.00001375, - "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_200k_tokens": 0.0000011, - "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_200k_tokens": 0.000011, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.0000275, - "output_cost_per_token_above_200k_tokens": 0.00004125, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "eu.anthropic.claude-opus-4-6-v1": { - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_200k_tokens": 0.00001375, - "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_200k_tokens": 0.0000011, - "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_200k_tokens": 0.000011, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.0000275, - "output_cost_per_token_above_200k_tokens": 0.00004125, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "au.anthropic.claude-opus-4-6-v1": { - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_200k_tokens": 0.00001375, - "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_200k_tokens": 0.0000011, - "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_200k_tokens": 0.000011, + "anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000275, - "output_cost_per_token_above_200k_tokens": 0.00004125, + "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": false, + "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -753,22 +544,22 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 159 }, - "anthropic.claude-sonnet-4-6": { + "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, - "output_cost_per_token_above_200k_tokens": 0.0000225, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -783,9 +574,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 159 }, - "global.anthropic.claude-sonnet-4-6": { + "anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, @@ -815,174 +606,24 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "us.anthropic.claude-sonnet-4-6": { - "cache_creation_input_token_cost": 0.000004125, - "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, - "cache_read_input_token_cost": 3.3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, - "input_cost_per_token": 0.0000033, - "input_cost_per_token_above_200k_tokens": 0.0000066, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "anthropic.claude-v1": { + "input_cost_per_token": 0.000008, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.0000165, - "output_cost_per_token_above_200k_tokens": 0.00002475, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "output_cost_per_token": 0.000024 }, - "eu.anthropic.claude-sonnet-4-6": { - "cache_creation_input_token_cost": 0.000004125, - "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, - "cache_read_input_token_cost": 3.3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, - "input_cost_per_token": 0.0000033, - "input_cost_per_token_above_200k_tokens": 0.0000066, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "anthropic.claude-v2:1": { + "input_cost_per_token": 0.000008, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.0000165, - "output_cost_per_token_above_200k_tokens": 0.00002475, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "apac.anthropic.claude-sonnet-4-6": { - "cache_creation_input_token_cost": 0.000004125, - "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, - "cache_read_input_token_cost": 3.3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, - "input_cost_per_token": 0.0000033, - "input_cost_per_token_above_200k_tokens": 0.0000066, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.0000165, - "output_cost_per_token_above_200k_tokens": 0.00002475, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "anthropic.claude-sonnet-4-20250514-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 - }, - "anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 - }, - "anthropic.claude-v1": { - "input_cost_per_token": 0.000008, - "litellm_provider": "bedrock", - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.000024 - }, - "anthropic.claude-v2:1": { - "input_cost_per_token": 0.000008, - "litellm_provider": "bedrock", - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.000024, - "supports_tool_choice": true + "output_cost_per_token": 0.000024, + "supports_tool_choice": true }, "anyscale/HuggingFaceH4/zephyr-7b-beta": { "input_cost_per_token": 1.5e-7, @@ -1102,6 +743,42 @@ "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", "supports_function_calling": true }, + "apac.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 8.25e-8, + "input_cost_per_token": 3.3e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.00000275, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true + }, + "apac.amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 0.0000021875, + "input_cost_per_image_token": 0.0000021875, + "input_cost_per_audio_token": 0.0000021875, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000175, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true + }, "apac.amazon.nova-lite-v1:0": { "input_cost_per_token": 6.3e-8, "litellm_provider": "bedrock_converse", @@ -1193,6 +870,22 @@ "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7 }, + "apac.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 3e-7, + "cache_creation_input_token_cost": 0.00000375 + }, "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, @@ -1215,22 +908,6 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 - }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, @@ -1261,6 +938,57 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, + "au.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, + "au.anthropic.claude-opus-4-6-v1": { + "cache_creation_input_token_cost": 0.000006875, + "cache_creation_input_token_cost_above_200k_tokens": 0.00001375, + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.0000011, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_above_200k_tokens": 0.000011, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000275, + "output_cost_per_token_above_200k_tokens": 0.00004125, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, @@ -1291,27 +1019,25 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "azure/command-r-plus": { - "input_cost_per_token": 0.000003, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true - }, - "azure_ai/claude-haiku-4-5": { - "cache_creation_input_token_cost": 0.00000125, - "cache_creation_input_token_cost_above_1hr": 0.000002, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "azure_ai", + "au.anthropic.claude-sonnet-4-6": { + "cache_creation_input_token_cost": 0.000004125, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost": 3.3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000005, + "output_cost_per_token": 0.0000165, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1320,119 +1046,18 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "azure_ai/claude-opus-4-5": { - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/claude-opus-4-6": { - "input_cost_per_token": 0.000005, - "output_cost_per_token": 0.000025, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 - }, - "azure_ai/claude-opus-4-1": { - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/claude-sonnet-4-5": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/claude-sonnet-4-6": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, + "azure/command-r-plus": { "input_cost_per_token": 0.000003, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_function_calling": true }, "azure/computer-use-preview": { "input_cost_per_token": 0.000003, @@ -1466,28 +1091,6 @@ "litellm_provider": "azure", "mode": "chat" }, - "azure_ai/gpt-oss-120b": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "azure_ai/model_router": { - "input_cost_per_token": 1.4e-7, - "output_cost_per_token": 0, - "litellm_provider": "azure_ai", - "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", - "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" - }, "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 0.000001375, @@ -1666,15 +1269,15 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/eu/gpt-5.1": { - "cache_read_input_token_cost": 1.4e-7, - "input_cost_per_token": 0.00000138, + "azure/eu/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5.5e-9, + "input_cost_per_token": 5.5e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000011, + "output_cost_per_token": 4.4e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -1685,8 +1288,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -1699,11 +1301,11 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/eu/gpt-5.1-chat": { + "azure/eu/gpt-5.1": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -1732,15 +1334,15 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/eu/gpt-5-nano-2025-08-07": { - "cache_read_input_token_cost": 5.5e-9, - "input_cost_per_token": 5.5e-8, + "azure/eu/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.00000138, "litellm_provider": "azure", - "max_input_tokens": 272000, + "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.4e-7, + "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -1751,7 +1353,8 @@ "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -2464,99 +2067,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-audio-2025-08-28": { - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.0000025, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00001, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, - "azure/gpt-audio-1.5-2026-02-23": { - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.0000025, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00001, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, - "azure/gpt-audio-mini-2025-10-06": { - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, "azure/gpt-4o-audio-preview-2024-12-17": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, @@ -2670,102 +2180,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/gpt-realtime-2025-08-28": { - "cache_creation_input_audio_token_cost": 0.000004, - "cache_read_input_token_cost": 0.000004, - "input_cost_per_audio_token": 0.000032, - "input_cost_per_image": 0.000005, - "input_cost_per_token": 0.000004, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.000016, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/gpt-realtime-1.5-2026-02-23": { - "cache_creation_input_audio_token_cost": 0.000004, - "cache_read_input_token_cost": 0.000004, - "input_cost_per_audio_token": 0.000032, - "input_cost_per_image": 0.000005, - "input_cost_per_token": 0.000004, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.000016, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/gpt-realtime-mini-2025-10-06": { - "cache_creation_input_audio_token_cost": 3e-7, - "cache_read_input_token_cost": 6e-8, - "input_cost_per_audio_token": 0.00001, - "input_cost_per_image": 8e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "azure/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 0.00002, "cache_read_input_token_cost": 0.0000025, @@ -2811,20 +2225,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/gpt-5.1-2025-11-13": { + "azure/gpt-5": { "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -2832,8 +2244,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -2844,45 +2255,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true - }, - "azure/gpt-5.1-chat-2025-11-13": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, "supports_vision": true }, - "azure/gpt-5": { + "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", @@ -2914,15 +2289,16 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-2025-08-07": { + "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, + "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2946,7 +2322,7 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-chat": { + "azure/gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", @@ -2955,7 +2331,6 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2979,15 +2354,15 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, + "azure/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000002, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3011,7 +2386,7 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-mini": { + "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "azure", @@ -3043,15 +2418,15 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-mini-2025-08-07": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 2.5e-7, + "azure/gpt-5-nano": { + "cache_read_input_token_cost": 5e-9, + "input_cost_per_token": 5e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000002, + "output_cost_per_token": 4e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3075,7 +2450,7 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-nano": { + "azure/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-9, "input_cost_per_token": 5e-8, "litellm_provider": "azure", @@ -3107,15 +2482,15 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-nano-2025-08-07": { - "cache_read_input_token_cost": 5e-9, - "input_cost_per_token": 5e-8, + "azure/gpt-5.1": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-7, + "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3126,7 +2501,8 @@ "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3139,18 +2515,20 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5.1": { + "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -3170,6 +2548,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, "azure/gpt-5.1-chat": { @@ -3205,6 +2584,41 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/gpt-5.1-chat-2025-11-13": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, "azure/gpt-5.2": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, @@ -3343,28 +2757,217 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/mistral-large-2402": { - "input_cost_per_token": 0.000008, - "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000024, - "supports_function_calling": true - }, - "azure/mistral-large-latest": { - "input_cost_per_token": 0.000008, + "azure/gpt-audio-1.5-2026-02-23": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, "litellm_provider": "azure", - "max_input_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000024, - "supports_function_calling": true - }, - "azure/o1": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "azure", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-audio-2025-08-28": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-audio-mini-2025-10-06": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-realtime-1.5-2026-02-23": { + "cache_creation_input_audio_token_cost": 0.000004, + "cache_read_input_token_cost": 0.000004, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-2025-08-28": { + "cache_creation_input_audio_token_cost": 0.000004, + "cache_read_input_token_cost": 0.000004, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-mini-2025-10-06": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 6e-8, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_image": 8e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/mistral-large-2402": { + "input_cost_per_token": 0.000008, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true + }, + "azure/mistral-large-latest": { + "input_cost_per_token": 0.000008, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true + }, + "azure/o1": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, @@ -3513,6 +3116,38 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/o3-deep-research": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_token": 0.00001, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "azure/o3-mini": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, @@ -3542,15 +3177,16 @@ "supports_tool_choice": true, "supports_vision": false }, - "azure/o4-mini": { - "cache_read_input_token_cost": 2.75e-7, - "input_cost_per_token": 0.0000011, + "azure/o3-pro": { + "input_cost_per_token": 0.00002, + "input_cost_per_token_batches": 0.00001, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 0.0000044, + "mode": "responses", + "output_cost_per_token": 0.00008, + "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3565,21 +3201,80 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": false, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 2.75e-7, - "input_cost_per_token": 0.0000011, + "azure/o3-pro-2025-06-10": { + "input_cost_per_token": 0.00002, + "input_cost_per_token_batches": 0.00001, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 0.0000044, + "mode": "responses", + "output_cost_per_token": 0.00008, + "output_cost_per_token_batches": 0.00004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o4-mini": { + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -4137,6 +3832,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/MAI-DS-R1": { + "input_cost_per_token": 0.00000135, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure_ai/Meta-Llama-3-70B-Instruct": { "input_cost_per_token": 0.0000011, "litellm_provider": "azure_ai", @@ -4312,8 +4019,7 @@ "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", "supports_function_calling": true }, - "azure_ai/Phi-4-multimodal-instruct": { - "input_cost_per_audio_token": 0.000004, + "azure_ai/Phi-4-mini-reasoning": { "input_cost_per_token": 8e-8, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -4321,12 +4027,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-7, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_vision": true + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_function_calling": true }, - "azure_ai/Phi-4-mini-reasoning": { + "azure_ai/Phi-4-multimodal-instruct": { + "input_cost_per_audio_token": 0.000004, "input_cost_per_token": 8e-8, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -4334,8 +4039,10 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", - "supports_function_calling": true + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_vision": true }, "azure_ai/Phi-4-reasoning": { "input_cost_per_token": 1.25e-7, @@ -4350,45 +4057,138 @@ "supports_tool_choice": true, "supports_reasoning": true }, - "azure_ai/MAI-DS-R1": { - "input_cost_per_token": 0.00000135, + "azure_ai/claude-haiku-4-5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000054, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure_ai/deepseek-v3.2": { - "input_cost_per_token": 5.8e-7, + "azure_ai/claude-opus-4-1": { + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.00003, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.00000168, + "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure_ai/deepseek-v3.2-speciale": { - "input_cost_per_token": 5.8e-7, + "azure_ai/claude-opus-4-5": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.00000168, + "output_cost_per_token": 0.000025, "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/claude-opus-4-6": { + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000025, + "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "azure_ai/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/claude-sonnet-4-6": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, "azure_ai/deepseek-r1": { "input_cost_per_token": 0.00000135, @@ -4425,6 +4225,34 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "azure_ai/deepseek-v3.2": { + "input_cost_per_token": 5.8e-7, + "litellm_provider": "azure_ai", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000168, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v3.2-speciale": { + "input_cost_per_token": 5.8e-7, + "litellm_provider": "azure_ai", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000168, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure_ai/global/grok-3": { "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", @@ -4454,6 +4282,20 @@ "supports_tool_choice": true, "supports_web_search": true }, + "azure_ai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "azure_ai/grok-3": { "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", @@ -4607,18 +4449,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "azure_ai/mistral-large-latest": { - "input_cost_per_token": 0.000002, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000006, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true - }, "azure_ai/mistral-large-3": { "input_cost_per_token": 5e-7, "litellm_provider": "azure_ai", @@ -4632,6 +4462,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/mistral-large-latest": { + "input_cost_per_token": 0.000002, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, "azure_ai/mistral-medium-2505": { "input_cost_per_token": 4e-7, "litellm_provider": "azure_ai", @@ -4678,6 +4520,14 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure_ai/model_router": { + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 0, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", + "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" + }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { "input_cost_per_second": 0.001902, "litellm_provider": "bedrock", @@ -4870,32 +4720,18 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, - "bedrock/moonshotai.kimi-k2-thinking": { - "input_cost_per_token": 7.3e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.00000303, - "supports_function_calling": true, - "supports_reasoning": true - }, - "bedrock/moonshotai.kimi-k2.5": { - "input_cost_per_token": 6e-7, + "bedrock/ap-south-1/deepseek.v3.2": { + "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 0.00000303, - "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", + "output_cost_per_token": 0.00000222, "supports_function_calling": true, "supports_reasoning": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 0.00000318, @@ -4915,19 +4751,6 @@ "mode": "chat", "output_cost_per_token": 7.2e-7 }, - "bedrock/ap-south-1/deepseek.v3.2": { - "input_cost_per_token": 7.4e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 0.00000222, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/ap-south-1/minimax.minimax-m2.1": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", @@ -5050,46 +4873,6 @@ "mode": "chat", "output_cost_per_token": 6.9e-7 }, - "bedrock/eu-north-1/deepseek.v3.2": { - "input_cost_per_token": 7.4e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 0.00000222, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/eu-north-1/minimax.minimax-m2.1": { - "input_cost_per_token": 3.6e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 196000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000144, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/eu-north-1/moonshotai.kimi-k2.5": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.0000036, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { "input_cost_per_second": 0.01635, "litellm_provider": "bedrock", @@ -5203,6 +4986,72 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/eu-north-1/deepseek.v3.2": { + "input_cost_per_token": 7.4e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000222, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/eu-north-1/minimax.minimax-m2.1": { + "input_cost_per_token": 3.6e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 196000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000144, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/eu-north-1/moonshotai.kimi-k2.5": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000036, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/eu-south-1/minimax.minimax-m2.1": { + "input_cost_per_token": 3.6e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 196000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000144, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/eu-south-1/qwen.qwen3-coder-next": { + "input_cost_per_token": 6e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000144, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 0.00000286, "litellm_provider": "bedrock", @@ -5321,32 +5170,6 @@ "output_cost_per_token": 9.1e-7, "supports_tool_choice": true }, - "bedrock/eu-south-1/minimax.minimax-m2.1": { - "input_cost_per_token": 3.6e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 196000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000144, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/eu-south-1/qwen.qwen3-coder-next": { - "input_cost_per_token": 6e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000144, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", @@ -5365,23 +5188,32 @@ "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 }, - "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { - "input_cost_per_token": 0.00000445, + "bedrock/moonshotai.kimi-k2-thinking": { + "input_cost_per_token": 7.3e-7, "litellm_provider": "bedrock", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.00000588 + "output_cost_per_token": 0.00000303, + "supports_function_calling": true, + "supports_reasoning": true }, - "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { - "input_cost_per_token": 5e-7, + "bedrock/moonshotai.kimi-k2.5": { + "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.00000101 + "output_cost_per_token": 0.00000303, + "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, "bedrock/sa-east-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-7, @@ -5396,6 +5228,24 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000445, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000588 + }, + "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 5e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000101 + }, "bedrock/sa-east-1/minimax.minimax-m2.1": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", @@ -5535,7 +5385,20 @@ "output_cost_per_token": 0.000024, "supports_tool_choice": true }, - "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "bedrock/us-east-1/deepseek.v3.2": { + "input_cost_per_token": 6.2e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000185, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 0.00000265, "litellm_provider": "bedrock", "max_input_tokens": 8192, @@ -5553,6 +5416,19 @@ "mode": "chat", "output_cost_per_token": 6e-7 }, + "bedrock/us-east-1/minimax.minimax-m2.1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 196000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock", @@ -5583,32 +5459,6 @@ "output_cost_per_token": 7e-7, "supports_tool_choice": true }, - "bedrock/us-east-1/deepseek.v3.2": { - "input_cost_per_token": 6.2e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 0.00000185, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/us-east-1/minimax.minimax-m2.1": { - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 196000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", @@ -5865,9 +5715,7 @@ "mode": "chat", "output_cost_per_token": 0.0000015 }, - "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { - "cache_creation_input_token_cost": 0.0000045, - "cache_read_input_token_cost": 3.6e-7, + "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 0.0000036, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -5875,17 +5723,17 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000018, - "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.6e-7, + "cache_creation_input_token_cost": 0.0000045 }, - "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 0.0000045, + "cache_read_input_token_cost": 3.6e-7, "input_cost_per_token": 0.0000036, "litellm_provider": "bedrock", "max_input_tokens": 200000, @@ -5893,13 +5741,15 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000018, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-7, - "cache_creation_input_token_cost": 0.0000045 + "supports_vision": true }, "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { "input_cost_per_token": 3e-7, @@ -6063,6 +5913,32 @@ "output_cost_per_token": 0.000024, "supports_tool_choice": true }, + "bedrock/us-west-2/deepseek.v3.2": { + "input_cost_per_token": 6.2e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000185, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/us-west-2/minimax.minimax-m2.1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 196000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock", @@ -6093,32 +5969,6 @@ "output_cost_per_token": 7e-7, "supports_tool_choice": true }, - "bedrock/us-west-2/deepseek.v3.2": { - "input_cost_per_token": 6.2e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 0.00000185, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "bedrock/us-west-2/minimax.minimax-m2.1": { - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 196000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", @@ -6174,6 +6024,75 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "bedrock_mantle/openai.gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-20b": { + "input_cost_per_token": 7.5e-8, + "output_cost_per_token": 3e-7, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-safeguard-120b": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-safeguard-20b": { + "input_cost_per_token": 7.5e-8, + "output_cost_per_token": 3e-7, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "cerebras/gpt-oss-120b": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "cerebras", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.5e-7, + "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "cerebras/llama-3.3-70b": { "input_cost_per_token": 8.5e-7, "litellm_provider": "cerebras", @@ -6207,21 +6126,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "cerebras/gpt-oss-120b": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "cerebras", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.5e-7, - "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "cerebras/qwen-3-32b": { "input_cost_per_token": 4e-7, "litellm_provider": "cerebras", @@ -6353,6 +6257,66 @@ "supports_tool_choice": true, "supports_vision": true }, + "chatgpt/gpt-5.2": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-chat-latest": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-instant": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.4": { + "litellm_provider": "chatgpt", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, "claude-3-5-haiku-20241022": { "cache_creation_input_token_cost": 0.000001, "cache_creation_input_token_cost_above_1hr": 0.000006, @@ -6407,48 +6371,6 @@ "supports_web_search": true, "tool_use_system_prompt_tokens": 264 }, - "claude-haiku-4-5-20251001": { - "cache_creation_input_token_cost": 0.00000125, - "cache_creation_input_token_cost_above_1hr": 0.000002, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000005, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_computer_use": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-haiku-4-5": { - "cache_creation_input_token_cost": 0.00000125, - "cache_creation_input_token_cost_above_1hr": 0.000002, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000005, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_computer_use": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "claude-3-5-sonnet-20240620": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, @@ -6699,121 +6621,47 @@ "supports_web_search": true, "tool_use_system_prompt_tokens": 159 }, - "claude-sonnet-4-5": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "claude-haiku-4-5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "claude-sonnet-4-5-20250929": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, "supports_computer_use": true, - "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tool_use_system_prompt_tokens": 346 + "supports_vision": true }, - "claude-sonnet-4-6": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, + "claude-haiku-4-5-20251001": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, "supports_computer_use": true, - "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "claude-opus-4-1": { "cache_creation_input_token_cost": 0.00001875, @@ -6898,7 +6746,7 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, - "claude-opus-4-5-20251101": { + "claude-opus-4-5": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -6925,7 +6773,7 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, - "claude-opus-4-5": { + "claude-opus-4-5-20251101": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -7054,44 +6902,160 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, - "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { - "input_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "max_input_tokens": 3072, - "max_output_tokens": 3072, - "max_tokens": 3072, - "mode": "chat", - "output_cost_per_token": 0.000001923 - }, - "cloudflare/@cf/meta/llama-2-7b-chat-int8": { - "input_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "max_tokens": 2048, + "claude-sonnet-4-5": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000001923 + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { - "input_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "claude-sonnet-4-5-20250929": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000001923 + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 346 }, - "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { - "input_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000001923 + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "code-bison": { - "input_cost_per_character": 2.5e-7, + "claude-sonnet-4-6": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { + "input_cost_per_token": 0.000001923, + "litellm_provider": "cloudflare", + "max_input_tokens": 3072, + "max_output_tokens": 3072, + "max_tokens": 3072, + "mode": "chat", + "output_cost_per_token": 0.000001923 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-int8": { + "input_cost_per_token": 0.000001923, + "litellm_provider": "cloudflare", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000001923 + }, + "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { + "input_cost_per_token": 0.000001923, + "litellm_provider": "cloudflare", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000001923 + }, + "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { + "input_cost_per_token": 0.000001923, + "litellm_provider": "cloudflare", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001923 + }, + "code-bison": { + "input_cost_per_character": 2.5e-7, "input_cost_per_token": 1.25e-7, "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, @@ -7349,49 +7313,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "deepseek-chat": { - "cache_read_input_token_cost": 2.8e-8, - "input_cost_per_token": 2.8e-7, - "litellm_provider": "deepseek", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4.2e-7, - "source": "https://api-docs.deepseek.com/quick_start/pricing", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "deepseek-reasoner": { - "cache_read_input_token_cost": 2.8e-8, - "input_cost_per_token": 2.8e-7, - "litellm_provider": "deepseek", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4.2e-7, - "source": "https://api-docs.deepseek.com/quick_start/pricing", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false - }, "dashscope/qwen-coder": { "input_cost_per_token": 3e-7, "litellm_provider": "dashscope", @@ -7877,7 +7798,7 @@ } ] }, - "dashscope/qwen3-max-preview": { + "dashscope/qwen3-max": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, @@ -7914,7 +7835,7 @@ } ] }, - "dashscope/qwen3-max": { + "dashscope/qwen3-max-2026-01-23": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, @@ -7951,7 +7872,7 @@ } ] }, - "dashscope/qwen3-max-2026-01-23": { + "dashscope/qwen3-max-preview": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, @@ -8582,6 +8503,40 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, + "deep-research-pro-preview-12-2025": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 0.000012, + "output_cost_per_token_batches": 0.000006, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true + }, "deepinfra/Gryphe/MythoMax-L2-13b": { "max_tokens": 4096, "max_input_tokens": 4096, @@ -9316,6 +9271,88 @@ "supports_tool_choice": true, "supports_function_calling": true }, + "deepseek-chat": { + "cache_read_input_token_cost": 2.8e-8, + "input_cost_per_token": 2.8e-7, + "litellm_provider": "deepseek", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.2e-7, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "deepseek-reasoner": { + "cache_read_input_token_cost": 2.8e-8, + "input_cost_per_token": 2.8e-7, + "litellm_provider": "deepseek", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.2e-7, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false + }, + "deepseek-v3-2-251201": { + "input_cost_per_token": 0, + "litellm_provider": "volcengine", + "max_input_tokens": 98304, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek.v3-v1:0": { + "input_cost_per_token": 5.8e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 163840, + "max_output_tokens": 81920, + "max_tokens": 81920, + "mode": "chat", + "output_cost_per_token": 0.00000168, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek.v3.2": { + "input_cost_per_token": 6.2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000185, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.8e-8, @@ -9424,72 +9461,41 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "deepseek.v3-v1:0": { - "input_cost_per_token": 5.8e-7, + "eu.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 8.25e-8, + "input_cost_per_token": 3.3e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 81920, - "max_tokens": 81920, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.00000168, + "output_cost_per_token": 0.00000275, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true }, - "deepseek.v3.2": { - "input_cost_per_token": 6.2e-7, + "eu.amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 0.0000021875, + "input_cost_per_image_token": 0.0000021875, + "input_cost_per_audio_token": 0.0000021875, "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 0.00000185, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "deepseek-v3-2-251201": { - "input_cost_per_token": 0, - "litellm_provider": "volcengine", - "max_input_tokens": 98304, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "glm-4-7-251222": { - "input_cost_per_token": 0, - "litellm_provider": "volcengine", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "kimi-k2-thinking-251104": { - "input_cost_per_token": 0, - "litellm_provider": "volcengine", - "max_input_tokens": 229376, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.0000175, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true }, "eu.amazon.nova-lite-v1:0": { "input_cost_per_token": 7.8e-8, @@ -9549,29 +9555,6 @@ "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7 }, - "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.000001375, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 0.0000011, - "deprecation_date": "2026-10-15", - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.0000055, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", @@ -9674,6 +9657,29 @@ "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 }, + "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "deprecation_date": "2026-10-15", + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, @@ -9726,6 +9732,62 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, + "eu.anthropic.claude-opus-4-5-20251101-v1:0": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "eu.anthropic.claude-opus-4-6-v1": { + "cache_creation_input_token_cost": 0.000006875, + "cache_creation_input_token_cost_above_200k_tokens": 0.00001375, + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.0000011, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_above_200k_tokens": 0.000011, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000275, + "output_cost_per_token_above_200k_tokens": 0.00004125, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, "eu.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, @@ -9786,6 +9848,48 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, + "eu.anthropic.claude-sonnet-4-6": { + "cache_creation_input_token_cost": 0.000004125, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost": 3.3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, + "eu.deepseek.v3.2": { + "input_cost_per_token": 7.4e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000222, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "eu.meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1.3e-7, "litellm_provider": "bedrock", @@ -9819,6 +9923,13 @@ "supports_function_calling": true, "supports_tool_choice": false }, + "eu.twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 0.0000075, + "litellm_provider": "bedrock", + "mode": "chat", + "supports_video_input": true + }, "featherless_ai/featherless-ai/Qwerky-72B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, @@ -9833,5570 +9944,2434 @@ "max_tokens": 4096, "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { - "input_cost_per_token": 0.0000012, + "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1": { - "input_cost_per_token": 0.000003, + "fireworks_ai/accounts/fireworks/models/code-llama-13b": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "max_tokens": 20480, - "mode": "chat", - "output_cost_per_token": 0.000008, - "source": "https://fireworks.ai/pricing", - "supports_response_schema": true, - "supports_tool_choice": false + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { - "input_cost_per_token": 0.000003, + "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 160000, - "max_output_tokens": 160000, - "max_tokens": 160000, - "mode": "chat", - "output_cost_per_token": 0.000008, - "source": "https://fireworks.ai/pricing", - "supports_response_schema": true, - "supports_tool_choice": false + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { - "input_cost_per_token": 5.5e-7, + "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "max_tokens": 20480, - "mode": "chat", - "output_cost_per_token": 0.00000219, - "source": "https://fireworks.ai/pricing", - "supports_response_schema": true, - "supports_tool_choice": false + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3": { + "fireworks_ai/accounts/fireworks/models/code-llama-34b": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, - "source": "https://fireworks.ai/pricing", - "supports_response_schema": true, - "supports_tool_choice": false + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { + "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/code-llama-70b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, - "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", - "supports_response_schema": true, - "supports_tool_choice": false + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { - "input_cost_per_token": 5.6e-7, + "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000168, - "source": "https://fireworks.ai/pricing", - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus": { - "input_cost_per_token": 5.6e-7, + "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000168, - "source": "https://fireworks.ai/pricing", - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3p2": { - "input_cost_per_token": 5.6e-7, + "fireworks_ai/accounts/fireworks/models/code-llama-7b": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 0.00000168, - "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/firefunction-v2": { - "input_cost_per_token": 9e-7, + "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-7, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/glm-4p5": { - "input_cost_per_token": 5.5e-7, + "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 96000, - "max_tokens": 96000, - "mode": "chat", - "output_cost_per_token": 0.00000219, - "source": "https://fireworks.ai/models/fireworks/glm-4p5", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { - "input_cost_per_token": 2.2e-7, + "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 96000, - "max_tokens": 96000, - "mode": "chat", - "output_cost_per_token": 8.8e-7, - "source": "https://artificialanalysis.ai/models/glm-4-5-air", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/glm-4p6": { - "input_cost_per_token": 5.5e-7, - "output_cost_per_token": 0.00000219, + "fireworks_ai/accounts/fireworks/models/codegemma-2b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, - "max_output_tokens": 202800, - "max_tokens": 202800, - "mode": "chat", - "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/glm-4p7": { - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 6e-7, + "fireworks_ai/accounts/fireworks/models/codegemma-7b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, - "max_output_tokens": 202800, - "max_tokens": 202800, - "mode": "chat", - "output_cost_per_token": 0.0000022, - "source": "https://fireworks.ai/models/fireworks/glm-4p7", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { - "input_cost_per_token": 1.5e-7, + "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { + "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { - "input_cost_per_token": 5e-8, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { + "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { "max_tokens": 131072, - "mode": "chat", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { - "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905": { - "input_cost_per_token": 6e-7, + "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking": { - "input_cost_per_token": 6e-7, + "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/kimi-k2p5": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 6e-7, + "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { - "input_cost_per_token": 0.000003, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { + "max_input_tokens": 16384, + "max_output_tokens": 16384, "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { + "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-7, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { + "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { - "input_cost_per_token": 1e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-7, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { - "input_cost_per_token": 1e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-7, + "output_cost_per_token": 0.0000012, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { - "input_cost_per_token": 9e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 9e-7, - "source": "https://fireworks.ai/pricing", - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { - "input_cost_per_token": 2.2e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1": { + "input_cost_per_token": 0.000003, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, "mode": "chat", - "output_cost_per_token": 8.8e-7, + "output_cost_per_token": 0.000008, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { - "input_cost_per_token": 1.5e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { + "input_cost_per_token": 0.000003, "litellm_provider": "fireworks_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 160000, + "max_output_tokens": 160000, + "max_tokens": 160000, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_token": 0.000008, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/minimax-m2p1": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_token": 3e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { - "input_cost_per_token": 0.0000012, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { + "input_cost_per_token": 5.5e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, "mode": "chat", - "output_cost_per_token": 0.0000012, + "output_cost_per_token": 0.00000219, "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { + "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { + "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://fireworks.ai/pricing", - "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/yi-large": { - "input_cost_per_token": 0.000003, + "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { + "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://fireworks.ai/pricing", - "supports_function_calling": false, + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", "supports_response_schema": true, "supports_tool_choice": false }, - "fireworks_ai/glm-4p7": { - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 6e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { + "input_cost_per_token": 5.6e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, - "max_output_tokens": 202800, - "max_tokens": 202800, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000022, - "source": "https://fireworks.ai/models/fireworks/glm-4p7", - "supports_function_calling": true, + "output_cost_per_token": 0.00000168, + "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/kimi-k2p5": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 6e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus": { + "input_cost_per_token": 5.6e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000003, + "output_cost_per_token": 0.00000168, "source": "https://fireworks.ai/pricing", - "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/minimax-m2p1": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_token": 3e-7, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p2": { + "input_cost_per_token": 5.6e-7, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", + "output_cost_per_token": 0.00000168, + "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "friendliai/meta-llama-3.1-70b-instruct": { - "input_cost_per_token": 6e-7, - "litellm_provider": "friendliai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true + "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "friendliai/meta-llama-3.1-8b-instruct": { + "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 1e-7, - "litellm_provider": "friendliai", + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/fare-20b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/firefunction-v1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/firefunction-v2": { + "input_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1e-7, + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "ft:gpt-3.5-turbo": { - "input_cost_per_token": 0.000003, - "input_cost_per_token_batches": 0.0000015, - "litellm_provider": "openai", - "max_input_tokens": 16385, - "max_output_tokens": 4096, + "fireworks_ai/accounts/fireworks/models/firellava-13b": { "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000006, - "output_cost_per_token_batches": 0.000003, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo-0125": { - "input_cost_per_token": 0.000003, - "litellm_provider": "openai", - "max_input_tokens": 16385, + "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_system_messages": true, - "supports_tool_choice": true + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "ft:gpt-3.5-turbo-0613": { - "input_cost_per_token": 0.000003, - "litellm_provider": "openai", + "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/flux-1-dev": { + "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_system_messages": true, - "supports_tool_choice": true + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "ft:gpt-3.5-turbo-1106": { - "input_cost_per_token": 0.000003, - "litellm_provider": "openai", - "max_input_tokens": 16385, + "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { + "max_tokens": 4096, + "max_input_tokens": 4096, "max_output_tokens": 4096, + "input_cost_per_token": 1e-9, + "output_cost_per_token": 1e-9, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_system_messages": true, - "supports_tool_choice": true + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "ft:gpt-4-0613": { - "input_cost_per_token": 0.00003, - "litellm_provider": "openai", + "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { + "max_tokens": 8192, "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00006, - "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "max_output_tokens": 8192, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "ft:gpt-4o-2024-08-06": { - "cache_read_input_token_cost": 0.000001875, - "input_cost_per_token": 0.00000375, - "input_cost_per_token_batches": 0.000001875, - "litellm_provider": "openai", + "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/gemma-7b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5": { + "input_cost_per_token": 5.5e-7, + "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 96000, + "max_tokens": 96000, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token": 0.00000219, + "source": "https://fireworks.ai/models/fireworks/glm-4p5", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "ft:gpt-4o-2024-11-20": { - "cache_creation_input_token_cost": 0.000001875, - "input_cost_per_token": 0.00000375, - "litellm_provider": "openai", + "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { + "input_cost_per_token": 2.2e-7, + "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 96000, + "max_tokens": 96000, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 8.8e-7, + "source": "https://artificialanalysis.ai/models/glm-4-5-air", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "ft:gpt-4o-mini-2024-07-18": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 3e-7, - "input_cost_per_token_batches": 1.5e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", + "fireworks_ai/accounts/fireworks/models/glm-4p5v": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, - "output_cost_per_token_batches": 6e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "supports_reasoning": true + }, + "fireworks_ai/accounts/fireworks/models/glm-4p6": { + "input_cost_per_token": 5.5e-7, + "output_cost_per_token": 0.00000219, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, + "mode": "chat", + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "ft:gpt-4.1-2025-04-14": { - "cache_read_input_token_cost": 7.5e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_batches": 0.0000015, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "fireworks_ai/accounts/fireworks/models/glm-4p7": { + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_batches": 0.000006, + "output_cost_per_token": 0.0000022, + "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "ft:gpt-4.1-mini-2025-04-14": { - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token": 8e-7, - "input_cost_per_token_batches": 4e-7, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000032, - "output_cost_per_token_batches": 0.0000016, + "output_cost_per_token": 6e-7, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "ft:gpt-4.1-nano-2025-04-14": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_token": 2e-7, - "input_cost_per_token_batches": 1e-7, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { + "input_cost_per_token": 5e-8, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 8e-7, - "output_cost_per_token_batches": 4e-7, + "output_cost_per_token": 2e-7, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "ft:o4-mini-2025-04-16": { - "cache_read_input_token_cost": 0.000001, - "input_cost_per_token": 0.000004, - "input_cost_per_token_batches": 0.000002, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 0.000016, - "output_cost_per_token_batches": 0.000008, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.0-pro": { - "input_cost_per_character": 1.25e-7, - "input_cost_per_image": 0.0025, + "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, "input_cost_per_token": 5e-7, - "input_cost_per_video_per_second": 0.002, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 3.75e-7, - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.0-pro-001": { - "deprecation_date": "2025-04-09", - "input_cost_per_character": 1.25e-7, - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "input_cost_per_video_per_second": 0.002, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 3.75e-7, - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.0-pro-002": { - "deprecation_date": "2025-04-09", - "input_cost_per_character": 1.25e-7, - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "input_cost_per_video_per_second": 0.002, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 3.75e-7, - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "fireworks_ai/accounts/fireworks/models/internvl3-38b": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.0-pro-vision": { - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "litellm_provider": "vertex_ai-vision-models", - "max_images_per_prompt": 16, + "fireworks_ai/accounts/fireworks/models/internvl3-78b": { + "max_tokens": 16384, "max_input_tokens": 16384, - "max_output_tokens": 2048, - "max_tokens": 2048, - "max_video_length": 2, - "max_videos_per_prompt": 1, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "max_output_tokens": 16384, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.0-pro-vision-001": { - "deprecation_date": "2025-04-09", - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "litellm_provider": "vertex_ai-vision-models", - "max_images_per_prompt": 16, + "fireworks_ai/accounts/fireworks/models/internvl3-8b": { + "max_tokens": 16384, "max_input_tokens": 16384, - "max_output_tokens": 2048, - "max_tokens": 2048, - "max_video_length": 2, - "max_videos_per_prompt": 1, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.0-ultra": { - "input_cost_per_character": 1.25e-7, - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "input_cost_per_video_per_second": 0.002, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, + "fireworks_ai/accounts/fireworks/models/kat-coder": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { + "input_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_character": 3.75e-7, - "output_cost_per_token": 0.0000015, - "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_token": 0.0000025, + "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "gemini-1.0-ultra-001": { - "input_cost_per_character": 1.25e-7, - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "input_cost_per_video_per_second": 0.002, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, + "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905": { + "input_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_character": 3.75e-7, - "output_cost_per_token": 0.0000015, - "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_token": 0.0000025, + "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "gemini-1.5-flash": { - "deprecation_date": "2025-09-29", - "input_cost_per_audio_per_second": 0.000002, - "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, - "input_cost_per_character": 1.875e-8, - "input_cost_per_character_above_128k_tokens": 2.5e-7, - "input_cost_per_image": 0.00002, - "input_cost_per_image_above_128k_tokens": 0.00004, - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 0.000001, - "input_cost_per_video_per_second": 0.00002, - "input_cost_per_video_per_second_above_128k_tokens": 0.00004, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking": { + "input_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_character": 7.5e-8, - "output_cost_per_character_above_128k_tokens": 1.5e-7, - "output_cost_per_token": 3e-7, - "output_cost_per_token_above_128k_tokens": 6e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_token": 0.0000025, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_web_search": true }, - "gemini-1.5-flash-001": { - "deprecation_date": "2025-05-24", - "input_cost_per_audio_per_second": 0.000002, - "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, - "input_cost_per_character": 1.875e-8, - "input_cost_per_character_above_128k_tokens": 2.5e-7, - "input_cost_per_image": 0.00002, - "input_cost_per_image_above_128k_tokens": 0.00004, - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 0.000001, - "input_cost_per_video_per_second": 0.00002, - "input_cost_per_video_per_second_above_128k_tokens": 0.00004, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "fireworks_ai/accounts/fireworks/models/kimi-k2p5": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_character": 7.5e-8, - "output_cost_per_character_above_128k_tokens": 1.5e-7, - "output_cost_per_token": 3e-7, - "output_cost_per_token_above_128k_tokens": 6e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_token": 0.000003, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "gemini-1.5-flash-002": { - "deprecation_date": "2025-09-24", - "input_cost_per_audio_per_second": 0.000002, - "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, - "input_cost_per_character": 1.875e-8, - "input_cost_per_character_above_128k_tokens": 2.5e-7, - "input_cost_per_image": 0.00002, - "input_cost_per_image_above_128k_tokens": 0.00004, - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 0.000001, - "input_cost_per_video_per_second": 0.00002, - "input_cost_per_video_per_second_above_128k_tokens": 0.00004, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, + "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_character": 7.5e-8, - "output_cost_per_character_above_128k_tokens": 1.5e-7, - "output_cost_per_token": 3e-7, - "output_cost_per_token_above_128k_tokens": 6e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.5-flash-exp-0827": { - "deprecation_date": "2025-09-29", - "input_cost_per_audio_per_second": 0.000002, - "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, - "input_cost_per_character": 1.875e-8, - "input_cost_per_character_above_128k_tokens": 2.5e-7, - "input_cost_per_image": 0.00002, - "input_cost_per_image_above_128k_tokens": 0.00004, - "input_cost_per_token": 4.688e-9, - "input_cost_per_token_above_128k_tokens": 0.000001, - "input_cost_per_video_per_second": 0.00002, - "input_cost_per_video_per_second_above_128k_tokens": 0.00004, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1000000, + "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { + "max_tokens": 2048, + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_pdf_size_mb": 30, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_character": 1.875e-8, - "output_cost_per_character_above_128k_tokens": 3.75e-8, - "output_cost_per_token": 4.6875e-9, - "output_cost_per_token_above_128k_tokens": 9.375e-9, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.5-flash-preview-0514": { - "deprecation_date": "2025-09-29", - "input_cost_per_audio_per_second": 0.000002, - "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, - "input_cost_per_character": 1.875e-8, - "input_cost_per_character_above_128k_tokens": 2.5e-7, - "input_cost_per_image": 0.00002, - "input_cost_per_image_above_128k_tokens": 0.00004, - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 0.000001, - "input_cost_per_video_per_second": 0.00002, - "input_cost_per_video_per_second_above_128k_tokens": 0.00004, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1000000, + "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { + "max_tokens": 8192, + "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_pdf_size_mb": 30, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { + "input_cost_per_token": 0.000003, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_character": 1.875e-8, - "output_cost_per_character_above_128k_tokens": 3.75e-8, - "output_cost_per_token": 4.6875e-9, - "output_cost_per_token_above_128k_tokens": 9.375e-9, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_token": 0.000003, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "gemini-1.5-pro": { - "deprecation_date": "2025-09-29", - "input_cost_per_audio_per_second": 0.00003125, - "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, - "input_cost_per_character": 3.125e-7, - "input_cost_per_character_above_128k_tokens": 6.25e-7, - "input_cost_per_image": 0.00032875, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_128k_tokens": 0.0000025, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 0.00000125, - "output_cost_per_character_above_128k_tokens": 0.0000025, - "output_cost_per_token": 0.000005, - "output_cost_per_token_above_128k_tokens": 0.00001, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-1.5-pro-001": { - "deprecation_date": "2025-05-24", - "input_cost_per_audio_per_second": 0.00003125, - "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, - "input_cost_per_character": 3.125e-7, - "input_cost_per_character_above_128k_tokens": 6.25e-7, - "input_cost_per_image": 0.00032875, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_128k_tokens": 0.0000025, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_character": 0.00000125, - "output_cost_per_character_above_128k_tokens": 0.0000025, - "output_cost_per_token": 0.000005, - "output_cost_per_token_above_128k_tokens": 0.00001, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 1e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": false }, - "gemini-1.5-pro-002": { - "deprecation_date": "2025-09-24", - "input_cost_per_audio_per_second": 0.00003125, - "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, - "input_cost_per_character": 3.125e-7, - "input_cost_per_character_above_128k_tokens": 6.25e-7, - "input_cost_per_image": 0.00032875, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_128k_tokens": 0.0000025, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_tokens": 8192, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { + "input_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_character": 0.00000125, - "output_cost_per_character_above_128k_tokens": 0.0000025, - "output_cost_per_token": 0.000005, - "output_cost_per_token_above_128k_tokens": 0.00001, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 2e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "supports_tool_choice": false, "supports_vision": true }, - "gemini-1.5-pro-preview-0215": { - "deprecation_date": "2025-09-29", - "input_cost_per_audio_per_second": 0.00003125, - "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, - "input_cost_per_character": 3.125e-7, - "input_cost_per_character_above_128k_tokens": 6.25e-7, - "input_cost_per_image": 0.00032875, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_token": 7.8125e-8, - "input_cost_per_token_above_128k_tokens": 1.5625e-7, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_character": 0.00000125, - "output_cost_per_character_above_128k_tokens": 0.0000025, - "output_cost_per_token": 3.125e-7, - "output_cost_per_token_above_128k_tokens": 6.25e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 1e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": false }, - "gemini-1.5-pro-preview-0409": { - "deprecation_date": "2025-09-29", - "input_cost_per_audio_per_second": 0.00003125, - "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, - "input_cost_per_character": 3.125e-7, - "input_cost_per_character_above_128k_tokens": 6.25e-7, - "input_cost_per_image": 0.00032875, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_token": 7.8125e-8, - "input_cost_per_token_above_128k_tokens": 1.5625e-7, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_character": 0.00000125, - "output_cost_per_character_above_128k_tokens": 0.0000025, - "output_cost_per_token": 3.125e-7, - "output_cost_per_token_above_128k_tokens": 6.25e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 1e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": false }, - "gemini-1.5-pro-preview-0514": { - "deprecation_date": "2025-09-29", - "input_cost_per_audio_per_second": 0.00003125, - "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, - "input_cost_per_character": 3.125e-7, - "input_cost_per_character_above_128k_tokens": 6.25e-7, - "input_cost_per_image": 0.00032875, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_token": 7.8125e-8, - "input_cost_per_token_above_128k_tokens": 1.5625e-7, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { + "input_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_character": 0.00000125, - "output_cost_per_character_above_128k_tokens": 0.0000025, - "output_cost_per_token": 3.125e-7, - "output_cost_per_token_above_128k_tokens": 6.25e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": false, + "supports_vision": true }, - "gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 4e-7, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.0-flash-001": { - "cache_read_input_token_cost": 3.75e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { + "input_cost_per_token": 2.2e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "output_cost_per_token": 8.8e-7, + "source": "https://fireworks.ai/pricing", "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_tool_choice": false }, - "gemini-2.0-flash-exp": { - "cache_read_input_token_cost": 3.75e-8, - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, + "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { "input_cost_per_token": 1.5e-7, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 6e-7, - "output_cost_per_token_above_128k_tokens": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "source": "https://fireworks.ai/pricing", "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_tool_choice": false }, - "gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 50, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 50, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/minimax-m2": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/minimax-m2p1": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 3e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 204800, "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, + "output_cost_per_token": 0.0000012, + "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_tool_choice": true }, - "gemini-2.0-flash-live-preview-04-09": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000003, - "input_cost_per_image": 0.000003, - "input_cost_per_token": 5e-7, - "input_cost_per_video_per_second": 0.000003, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_audio_token": 0.000012, - "output_cost_per_token": 0.000002, - "rpm": 10, - "source": "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 + "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.0-flash-preview-image-generation": { - "deprecation_date": "2025-11-14", - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 7e-7, + "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, "input_cost_per_token": 1e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 4e-7, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.0-flash-thinking-exp": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { + "input_cost_per_token": 0.0000012, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, + "output_cost_per_token": 0.0000012, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_tool_choice": true }, - "gemini-2.0-flash-thinking-exp-01-21": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": false, - "supports_function_calling": false, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.0-pro-exp-02-05": { - "cache_read_input_token_cost": 3.125e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-flash": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-8, - "cache_read_input_token_cost_per_audio_token": 5e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000015, - "output_cost_per_token": 0.0000015, - "source": "https://ai.google.dev/gemini-api/docs/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_code_execution": true, - "supports_file_search": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true + "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-flash-lite": { - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 3e-7, + "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 1e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-live-2.5-flash-preview-native-audio-09-2025": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000003, - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_audio_token": 0.000012, - "output_cost_per_token": 0.000002, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000003, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_audio_token": 0.000012, - "output_cost_per_token": 0.000002, - "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 8000000 + "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-flash-preview-04-17": { - "cache_read_input_token_cost": 3.75e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000035, - "output_cost_per_token": 6e-7, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-flash-preview-05-20": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-2.5-pro": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true + "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-3-pro-preview": { - "deprecation_date": "2026-03-26", - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true + "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-3.1-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true - }, - "gemini-3.1-pro-preview-customtools": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true - }, - "vertex_ai/gemini-3-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "vertex_ai", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true - }, - "vertex_ai/gemini-3-flash-preview": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_token": 5e-7, - "input_cost_per_audio_token": 0.000001, - "litellm_provider": "vertex_ai", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-7, - "input_cost_per_audio_token_priority": 0.0000018, - "output_cost_per_token_priority": 0.0000054, - "cache_read_input_token_cost_priority": 9e-8, - "supports_service_tier": true - }, - "vertex_ai/gemini-3.1-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "vertex_ai", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true - }, - "vertex_ai/gemini-3.1-pro-preview-customtools": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "vertex_ai", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true - }, - "gemini-2.5-pro-exp-03-25": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true - }, - "gemini-2.5-pro-preview-03-25": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 0.00000125, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "gemini-2.5-pro-preview-05-06": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 0.00000125, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supported_regions": [ - "global" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "gemini-2.5-pro-preview-06-05": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 0.00000125, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "gemini-2.5-pro-preview-tts": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "gemini-robotics-er-1.5-preview": { - "cache_read_input_token_cost": 0, - "input_cost_per_token": 3e-7, - "input_cost_per_audio_token": 0.000001, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "output_cost_per_reasoning_token": 0.0000025, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "video", - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true - }, - "gemini/gemini-robotics-er-1.5-preview": { - "cache_read_input_token_cost": 0, - "input_cost_per_token": 3e-7, - "input_cost_per_audio_token": 0.000001, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "output_cost_per_reasoning_token": 0.0000025, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "video", - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "rpm": 10 - }, - "gemini-2.5-computer-use-preview-10-2025": { - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "vertex_ai-language-models", - "max_images_per_prompt": 3000, - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "gemini-flash-experimental": { - "input_cost_per_character": 0, - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_token": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", - "supports_function_calling": false, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "gemini-pro": { - "input_cost_per_character": 1.25e-7, - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "input_cost_per_video_per_second": 0.002, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 3.75e-7, - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "gemini-pro-experimental": { - "input_cost_per_character": 0, - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_token": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", - "supports_function_calling": false, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "gemini-pro-vision": { - "input_cost_per_image": 0.0025, - "input_cost_per_token": 5e-7, - "litellm_provider": "vertex_ai-vision-models", - "max_images_per_prompt": 16, - "max_input_tokens": 16384, - "max_output_tokens": 2048, - "max_tokens": 2048, - "max_video_length": 2, - "max_videos_per_prompt": 1, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "gemini/gemini-1.5-flash": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 1.5e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 3e-7, - "output_cost_per_token_above_128k_tokens": 6e-7, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-flash-001": { - "cache_creation_input_token_cost": 0.000001, - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2025-05-24", - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 1.5e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 3e-7, - "output_cost_per_token_above_128k_tokens": 6e-7, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-flash-002": { - "cache_creation_input_token_cost": 0.000001, - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2025-09-24", - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 1.5e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 3e-7, - "output_cost_per_token_above_128k_tokens": 6e-7, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-flash-8b": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-flash-8b-exp-0827": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-flash-8b-exp-0924": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-flash-exp-0827": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-flash-latest": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 7.5e-8, - "input_cost_per_token_above_128k_tokens": 1.5e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 3e-7, - "output_cost_per_token_above_128k_tokens": 6e-7, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-pro": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0.0000035, - "input_cost_per_token_above_128k_tokens": 0.000007, - "litellm_provider": "gemini", - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0000105, - "output_cost_per_token_above_128k_tokens": 0.000021, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-pro-001": { - "deprecation_date": "2025-05-24", - "input_cost_per_token": 0.0000035, - "input_cost_per_token_above_128k_tokens": 0.000007, - "litellm_provider": "gemini", - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0000105, - "output_cost_per_token_above_128k_tokens": 0.000021, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-pro-002": { - "deprecation_date": "2025-09-24", - "input_cost_per_token": 0.0000035, - "input_cost_per_token_above_128k_tokens": 0.000007, - "litellm_provider": "gemini", - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0000105, - "output_cost_per_token_above_128k_tokens": 0.000021, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-pro-exp-0801": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0.0000035, - "input_cost_per_token_above_128k_tokens": 0.000007, - "litellm_provider": "gemini", - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0000105, - "output_cost_per_token_above_128k_tokens": 0.000021, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-pro-exp-0827": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-1.5-pro-latest": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 0.0000035, - "input_cost_per_token_above_128k_tokens": 0.000007, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000105, - "output_cost_per_token_above_128k_tokens": 0.000021, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 - }, - "gemini/gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 4e-7, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 - }, - "gemini/gemini-2.0-flash-001": { - "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 4e-7, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 - }, - "gemini/gemini-2.0-flash-exp": { - "cache_read_input_token_cost": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 10, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000 - }, - "gemini/gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 50, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 3e-7, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000 - }, - "gemini/gemini-2.0-flash-lite-preview-02-05": { - "deprecation_date": "2025-12-09", - "cache_read_input_token_cost": 1.875e-8, - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 3e-7, - "rpm": 60000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 - }, - "gemini/gemini-2.0-flash-live-001": { - "deprecation_date": "2025-12-09", - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.0000021, - "input_cost_per_image": 0.0000021, - "input_cost_per_token": 3.5e-7, - "input_cost_per_video_per_second": 0.0000021, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_audio_token": 0.0000085, - "output_cost_per_token": 0.0000015, - "rpm": 10, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-2.0-flash-preview-image-generation": { - "deprecation_date": "2025-11-14", - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 4e-7, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 - }, - "gemini/gemini-2.0-flash-thinking-exp": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 10, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000 - }, - "gemini/gemini-2.0-flash-thinking-exp-01-21": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 10, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000 - }, - "gemini/gemini-2.0-pro-exp-02-05": { - "cache_read_input_token_cost": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 2, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 1000000 - }, - "gemini/gemini-2.5-flash": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 8000000 - }, - "gemini/gemini-2.5-flash-lite": { - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-flash-latest": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-2.5-flash-preview-04-17": { - "cache_read_input_token_cost": 3.75e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000035, - "output_cost_per_token": 6e-7, - "rpm": 10, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-2.5-flash-preview-05-20": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "rpm": 10, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 - }, - "gemini/gemini-2.5-pro": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "input_cost_per_token_priority": 0.00000125, - "input_cost_per_token_above_200k_tokens_priority": 0.0000025, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "output_cost_per_token_priority": 0.00001, - "output_cost_per_token_above_200k_tokens_priority": 0.000015, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_service_tier": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 - }, - "gemini/gemini-2.5-computer-use-preview-10-2025": { - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "gemini", - "max_images_per_prompt": 3000, - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/computer-use", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 800000 + "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-3-pro-preview": { - "deprecation_date": "2026-03-09", - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true + "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-8, - "cache_read_input_token_cost_per_audio_token": 5e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 2.5e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000015, - "output_cost_per_token": 0.0000015, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_code_execution": true, - "supports_file_search": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "tpm": 250000 + "fireworks_ai/accounts/fireworks/models/openorca-7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-3-flash-preview": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 5e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.000003, - "output_cost_per_token": 0.000003, - "rpm": 2000, - "source": "https://ai.google.dev/pricing/gemini-3", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "tpm": 800000, - "input_cost_per_token_priority": 9e-7, - "input_cost_per_audio_token_priority": 0.0000018, - "output_cost_per_token_priority": 0.0000054, - "cache_read_input_token_cost_priority": 9e-8, - "supports_service_tier": true + "fireworks_ai/accounts/fireworks/models/phi-2-3b": { + "max_tokens": 2048, + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-3.1-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "tpm": 800000, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true + "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-3.1-pro-preview-customtools": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "tpm": 800000, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "supports_service_tier": true + "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { + "max_tokens": 32064, + "max_input_tokens": 32064, + "max_output_tokens": 32064, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini-3-flash-preview": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_reasoning_token": 0.000003, - "output_cost_per_token": 0.000003, - "source": "https://ai.google.dev/pricing/gemini-3", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-7, - "input_cost_per_audio_token_priority": 0.0000018, - "output_cost_per_token_priority": 0.0000054, - "cache_read_input_token_cost_priority": 9e-8, - "supports_service_tier": true + "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-2.5-pro-exp-03-25": { - "cache_read_input_token_cost": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_200k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_200k_tokens": 0, - "rpm": 5, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 + "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-2.5-pro-preview-03-25": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 + "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-2.5-pro-preview-05-06": { - "deprecation_date": "2025-12-02", - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 + "fireworks_ai/accounts/fireworks/models/pythia-12b": { + "max_tokens": 2048, + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-2.5-pro-preview-06-05": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 + "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-2.5-pro-preview-tts": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000 + "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-exp-1114": { - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "metadata": { - "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", - "supports_tool_choice": true - }, - "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 + "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-exp-1206": { - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, - "metadata": { - "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", - "supports_tool_choice": true - }, + "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { + "input_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "supports_function_calling": true, + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 4000000 + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-gemma-2-27b-it": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "gemini", - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000105, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 250000, - "rpm": 10 + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-gemma-2-9b-it": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "gemini", - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000105, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 250000, - "rpm": 10 + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-pro": { - "input_cost_per_token": 3.5e-7, - "input_cost_per_token_above_128k_tokens": 7e-7, - "litellm_provider": "gemini", - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000105, - "output_cost_per_token_above_128k_tokens": 0.0000021, - "rpd": 30000, - "rpm": 360, - "source": "https://ai.google.dev/gemini-api/docs/models/gemini", - "supports_function_calling": true, - "supports_tool_choice": true, - "tpm": 120000 + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemini-pro-vision": { - "input_cost_per_token": 3.5e-7, - "input_cost_per_token_above_128k_tokens": 7e-7, - "litellm_provider": "gemini", - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 0.00000105, - "output_cost_per_token_above_128k_tokens": 0.0000021, - "rpd": 30000, - "rpm": 360, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "tpm": 120000 + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gemini/gemma-3-27b-it": { - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { + "input_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "source": "https://aistudio.google.com", - "supports_audio_output": false, - "supports_function_calling": true, + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": false }, - "gemini/learnlm-1.5-pro-experimental": { - "input_cost_per_audio_per_second": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "input_cost_per_character": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "litellm_provider": "gemini", - "max_input_tokens": 32767, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 0, - "output_cost_per_character_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "source": "https://aistudio.google.com", - "supports_audio_output": false, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/claude-haiku-4.5": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/claude-opus-4.5": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/claude-opus-4.6-fast": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/claude-opus-41": { - "litellm_provider": "github_copilot", - "max_input_tokens": 80000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/claude-sonnet-4": { - "litellm_provider": "github_copilot", + "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { + "max_tokens": 128000, "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "max_output_tokens": 128000, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/claude-sonnet-4.5": { - "litellm_provider": "github_copilot", + "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { + "max_tokens": 128000, "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "max_output_tokens": 128000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gemini-2.5-pro": { - "litellm_provider": "github_copilot", + "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { + "max_tokens": 128000, "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "max_output_tokens": 128000, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gemini-3-pro-preview": { - "litellm_provider": "github_copilot", + "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { + "max_tokens": 128000, "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "max_output_tokens": 128000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-3.5-turbo": { - "litellm_provider": "github_copilot", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-3.5-turbo-0613": { - "litellm_provider": "github_copilot", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-14b": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4": { - "litellm_provider": "github_copilot", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4-0613": { - "litellm_provider": "github_copilot", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4-o-preview": { - "litellm_provider": "github_copilot", - "max_input_tokens": 64000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4.1": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4.1-2025-04-14": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2.2e-7, + "output_cost_per_token": 8.8e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4o": { - "litellm_provider": "github_copilot", - "max_input_tokens": 64000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2.2e-7, + "output_cost_per_token": 8.8e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4o-2024-05-13": { - "litellm_provider": "github_copilot", - "max_input_tokens": 64000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2.2e-7, + "output_cost_per_token": 8.8e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4o-2024-08-06": { - "litellm_provider": "github_copilot", - "max_input_tokens": 64000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4o-2024-11-20": { - "litellm_provider": "github_copilot", - "max_input_tokens": 64000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4o-mini": { - "litellm_provider": "github_copilot", - "max_input_tokens": 64000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-4o-mini-2024-07-18": { - "litellm_provider": "github_copilot", - "max_input_tokens": 64000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "fireworks_ai/accounts/fireworks/models/qwen3-32b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true + "supports_reasoning": true }, - "github_copilot/gpt-5": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-4b": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-5-mini": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "github_copilot/gpt-5.1": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "fireworks_ai/accounts/fireworks/models/qwen3-8b": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true + "supports_reasoning": true }, - "github_copilot/gpt-5.2": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gigachat/GigaChat-2-Lite": { - "input_cost_per_token": 0, - "litellm_provider": "gigachat", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 4.5e-7, + "output_cost_per_token": 0.0000018, + "litellm_provider": "fireworks_ai", "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true, - "supports_system_messages": true + "supports_reasoning": true }, - "gigachat/GigaChat-2-Max": { - "input_cost_per_token": 0, - "litellm_provider": "gigachat", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gigachat/GigaChat-2-Pro": { - "input_cost_per_token": 0, - "litellm_provider": "gigachat", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/anthropic/claude-opus-4.5": { - "input_cost_per_token": 0.000005, - "litellm_provider": "gmi", - "max_input_tokens": 409600, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/anthropic/claude-sonnet-4.5": { - "input_cost_per_token": 0.000003, - "litellm_provider": "gmi", - "max_input_tokens": 409600, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2.2e-7, + "output_cost_per_token": 8.8e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/anthropic/claude-sonnet-4": { - "input_cost_per_token": 0.000003, - "litellm_provider": "gmi", - "max_input_tokens": 409600, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2.2e-7, + "output_cost_per_token": 8.8e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/anthropic/claude-opus-4": { - "input_cost_per_token": 0.000015, - "litellm_provider": "gmi", - "max_input_tokens": 409600, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/openai/gpt-5.2": { - "input_cost_per_token": 0.00000175, - "litellm_provider": "gmi", - "max_input_tokens": 409600, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000014, - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/openai/gpt-5.1": { - "input_cost_per_token": 0.00000125, - "litellm_provider": "gmi", - "max_input_tokens": 409600, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/openai/gpt-5": { - "input_cost_per_token": 0.00000125, - "litellm_provider": "gmi", - "max_input_tokens": 409600, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/openai/gpt-4o": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "gmi", + "fireworks_ai/accounts/fireworks/models/qwq-32b": { + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true, - "supports_vision": true + "max_output_tokens": 131072, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/openai/gpt-4o-mini": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "gmi", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/rolm-ocr": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/deepseek-ai/DeepSeek-V3.2": { - "input_cost_per_token": 2.8e-7, - "litellm_provider": "gmi", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/deepseek-ai/DeepSeek-V3-0324": { - "input_cost_per_token": 2.8e-7, - "litellm_provider": "gmi", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8.8e-7, - "supports_function_calling": true + "fireworks_ai/accounts/fireworks/models/stablecode-3b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/google/gemini-3-pro-preview": { - "input_cost_per_token": 0.000002, - "litellm_provider": "gmi", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 0.000012, - "supports_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/starcoder-16b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/google/gemini-3-flash-preview": { - "input_cost_per_token": 5e-7, - "litellm_provider": "gmi", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 0.000003, - "supports_function_calling": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/starcoder-7b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/moonshotai/Kimi-K2-Thinking": { - "input_cost_per_token": 8e-7, - "litellm_provider": "gmi", - "max_input_tokens": 262144, - "max_output_tokens": 16384, + "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.0000012 - }, - "gmi/MiniMaxAI/MiniMax-M2.1": { - "input_cost_per_token": 3e-7, - "litellm_provider": "gmi", - "max_input_tokens": 196608, + "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.0000012 + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8": { - "input_cost_per_token": 3e-7, - "litellm_provider": "gmi", - "max_input_tokens": 262144, - "max_output_tokens": 16384, + "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.0000014, - "supports_vision": true - }, - "gmi/zai-org/GLM-4.7-FP8": { - "input_cost_per_token": 4e-7, - "litellm_provider": "gmi", - "max_input_tokens": 202752, + "max_input_tokens": 16384, "max_output_tokens": 16384, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.000002 + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "google.gemma-3-12b-it": { - "input_cost_per_token": 9e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.9e-7, - "supports_system_messages": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "google.gemma-3-27b-it": { - "input_cost_per_token": 2.3e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3.8e-7, - "supports_system_messages": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/yi-34b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "google.gemma-3-4b-it": { - "input_cost_per_token": 4e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-8, - "supports_system_messages": true, - "supports_vision": true + "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" }, - "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, + "fireworks_ai/accounts/fireworks/models/yi-6b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/accounts/fireworks/models/yi-large": { "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "output_cost_per_token": 0.000003, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_tool_choice": false }, - "global.anthropic.claude-sonnet-4-20250514-v1:0": { - "cache_creation_input_token_cost": 0.00000375, + "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "fireworks_ai", + "mode": "chat" + }, + "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "input_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000022, + "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_tool_choice": true }, - "global.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.00000125, + "fireworks_ai/kimi-k2p5": { "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "input_cost_per_token": 6e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000003, + "source": "https://fireworks.ai/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_tool_choice": true }, - "global.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 7.5e-8, + "fireworks_ai/minimax-m2p1": { + "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 204800, "mode": "chat", - "output_cost_per_token": 0.0000025, + "output_cost_per_token": 0.0000012, + "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_video_input": true, - "supports_vision": true - }, - "gpt-3.5-turbo": { - "input_cost_per_token": 5e-7, - "litellm_provider": "openai", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-3.5-turbo-0125": { - "input_cost_per_token": 5e-7, - "litellm_provider": "openai", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, + "friendliai/meta-llama-3.1-70b-instruct": { + "input_cost_per_token": 6e-7, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000015, + "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-3.5-turbo-0301": { - "input_cost_per_token": 0.0000015, - "litellm_provider": "openai", - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "max_tokens": 4096, + "friendliai/meta-llama-3.1-8b-instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_prompt_caching": true, + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-3.5-turbo-0613": { - "input_cost_per_token": 0.0000015, + "ft:gpt-3.5-turbo": { + "input_cost_per_token": 0.000003, + "input_cost_per_token_batches": 0.0000015, "litellm_provider": "openai", - "max_input_tokens": 4097, + "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_function_calling": true, - "supports_prompt_caching": true, + "output_cost_per_token": 0.000006, + "output_cost_per_token_batches": 0.000003, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-3.5-turbo-1106": { - "deprecation_date": "2026-09-28", - "input_cost_per_token": 0.000001, + "ft:gpt-3.5-turbo-0125": { + "input_cost_per_token": 0.000003, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "output_cost_per_token": 0.000006, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-3.5-turbo-16k": { + "ft:gpt-3.5-turbo-0613": { "input_cost_per_token": 0.000003, "litellm_provider": "openai", - "max_input_tokens": 16385, + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000004, - "supports_prompt_caching": true, + "output_cost_per_token": 0.000006, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-3.5-turbo-16k-0613": { + "ft:gpt-3.5-turbo-1106": { "input_cost_per_token": 0.000003, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000004, - "supports_prompt_caching": true, + "output_cost_per_token": 0.000006, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4": { + "ft:gpt-4-0613": { "input_cost_per_token": 0.00003, "litellm_provider": "openai", "max_input_tokens": 8192, @@ -15404,815 +12379,1142 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, + "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-0125-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 0.00001, + "ft:gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 7.5e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_batches": 0.0000015, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00003, + "output_cost_per_token": 0.000012, + "output_cost_per_token_batches": 0.000006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-0314": { - "input_cost_per_token": 0.00003, - "litellm_provider": "openai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0613": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 0.00003, - "litellm_provider": "openai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "ft:gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 8e-7, + "input_cost_per_token_batches": 4e-7, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00006, + "output_cost_per_token": 0.0000032, + "output_cost_per_token_batches": 0.0000016, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-1106-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 0.00001, + "ft:gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_batches": 1e-7, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00003, + "output_cost_per_token": 8e-7, + "output_cost_per_token_batches": 4e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-1106-vision-preview": { - "deprecation_date": "2024-12-06", - "input_cost_per_token": 0.00001, + "ft:gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 0.000001875, + "input_cost_per_token": 0.00000375, + "input_cost_per_token_batches": 0.000001875, "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00003, + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "gpt-4-32k": { - "input_cost_per_token": 0.00006, + "ft:gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 0.000001875, + "input_cost_per_token": 0.00000375, "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00012, + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-32k-0314": { - "input_cost_per_token": 0.00006, + "ft:gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 3e-7, + "input_cost_per_token_batches": 1.5e-7, "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00012, + "output_cost_per_token": 0.0000012, + "output_cost_per_token_batches": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-32k-0613": { - "input_cost_per_token": 0.00006, + "ft:o4-mini-2025-04-16": { + "cache_read_input_token_cost": 0.000001, + "input_cost_per_token": 0.000004, + "input_cost_per_token_batches": 0.000002, "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.00012, + "output_cost_per_token": 0.000016, + "output_cost_per_token_batches": 0.000008, + "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, - "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "gpt-4-turbo": { - "input_cost_per_token": 0.00001, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-1.0-pro": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.00003, + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-pro-001": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-pro-002": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "gpt-4-turbo-2024-04-09": { - "input_cost_per_token": 0.00001, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-1.0-pro-vision-001": { + "deprecation_date": "2025-04-09", + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.0-ultra": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-ultra-001": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.5-flash": { + "deprecation_date": "2025-09-29", + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.00003, + "output_cost_per_character": 7.5e-8, + "output_cost_per_character_above_128k_tokens": 1.5e-7, + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "gpt-4-turbo-preview": { - "input_cost_per_token": 0.00001, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-1.5-flash-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.00003, + "output_cost_per_character": 7.5e-8, + "output_cost_per_character_above_128k_tokens": 1.5e-7, + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-vision-preview": { - "deprecation_date": "2024-12-06", - "input_cost_per_token": 0.00001, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "gpt-4.1": { - "cache_read_input_token_cost": 5e-7, - "cache_read_input_token_cost_priority": 8.75e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_batches": 0.000001, - "input_cost_per_token_priority": 0.0000035, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini-1.5-flash-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000008, - "output_cost_per_token_batches": 0.000004, - "output_cost_per_token_priority": 0.000014, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_character": 7.5e-8, + "output_cost_per_character_above_128k_tokens": 1.5e-7, + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, "supports_vision": true }, - "gpt-4.1-2025-04-14": { - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini-1.5-flash-exp-0827": { + "deprecation_date": "2025-09-29", + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 4.688e-9, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000008, - "output_cost_per_token_batches": 0.000004, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_character": 1.875e-8, + "output_cost_per_character_above_128k_tokens": 3.75e-8, + "output_cost_per_token": 4.6875e-9, + "output_cost_per_token_above_128k_tokens": 9.375e-9, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, "supports_vision": true }, - "gpt-4.1-mini": { - "cache_read_input_token_cost": 1e-7, - "cache_read_input_token_cost_priority": 1.75e-7, - "input_cost_per_token": 4e-7, - "input_cost_per_token_batches": 2e-7, - "input_cost_per_token_priority": 7e-7, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini-1.5-flash-preview-0514": { + "deprecation_date": "2025-09-29", + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.0000016, - "output_cost_per_token_batches": 8e-7, - "output_cost_per_token_priority": 0.0000028, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_character": 1.875e-8, + "output_cost_per_character_above_128k_tokens": 3.75e-8, + "output_cost_per_token": 4.6875e-9, + "output_cost_per_token_above_128k_tokens": 9.375e-9, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, "supports_vision": true }, - "gpt-4.1-mini-2025-04-14": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 4e-7, - "input_cost_per_token_batches": 2e-7, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0000016, - "output_cost_per_token_batches": 8e-7, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "gemini-1.5-pro": { + "deprecation_date": "2025-09-29", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_128k_tokens": 0.0000025, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_128k_tokens": 0.00001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, "supports_vision": true }, - "gpt-4.1-nano": { - "cache_read_input_token_cost": 2.5e-8, - "cache_read_input_token_cost_priority": 5e-8, - "input_cost_per_token": 1e-7, - "input_cost_per_token_batches": 5e-8, - "input_cost_per_token_priority": 2e-7, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_128k_tokens": 0.0000025, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-7, - "output_cost_per_token_batches": 2e-7, - "output_cost_per_token_priority": 8e-7, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_128k_tokens": 0.00001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, "supports_vision": true }, - "gpt-4.1-nano-2025-04-14": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 1e-7, - "input_cost_per_token_batches": 5e-8, - "litellm_provider": "openai", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_128k_tokens": 0.0000025, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-7, - "output_cost_per_token_batches": 2e-7, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_128k_tokens": 0.00001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, "supports_vision": true }, - "gpt-4.5-preview": { - "cache_read_input_token_cost": 0.0000375, - "input_cost_per_token": 0.000075, - "input_cost_per_token_batches": 0.0000375, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-1.5-pro-preview-0215": { + "deprecation_date": "2025-09-29", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-8, + "input_cost_per_token_above_128k_tokens": 1.5625e-7, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_batches": 0.000075, + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 3.125e-7, + "output_cost_per_token_above_128k_tokens": 6.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "gpt-4.5-preview-2025-02-27": { - "cache_read_input_token_cost": 0.0000375, - "deprecation_date": "2025-07-14", - "input_cost_per_token": 0.000075, - "input_cost_per_token_batches": 0.0000375, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-1.5-pro-preview-0409": { + "deprecation_date": "2025-09-29", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-8, + "input_cost_per_token_above_128k_tokens": 1.5625e-7, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_batches": 0.000075, + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 3.125e-7, + "output_cost_per_token_above_128k_tokens": 6.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "gemini-1.5-pro-preview-0514": { + "deprecation_date": "2025-09-29", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-8, + "input_cost_per_token_above_128k_tokens": 1.5625e-7, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 3.125e-7, + "output_cost_per_token_above_128k_tokens": 6.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "gpt-4o": { - "cache_read_input_token_cost": 0.00000125, - "cache_read_input_token_cost_priority": 0.000002125, - "input_cost_per_token": 0.0000025, - "input_cost_per_token_batches": 0.00000125, - "input_cost_per_token_priority": 0.00000425, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_batches": 0.000005, - "output_cost_per_token_priority": 0.000017, + "output_cost_per_token": 4e-7, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-2024-05-13": { - "input_cost_per_token": 0.000005, - "input_cost_per_token_batches": 0.0000025, - "input_cost_per_token_priority": 0.00000875, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-2.0-flash-001": { + "cache_read_input_token_cost": 3.75e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_batches": 0.0000075, - "output_cost_per_token_priority": 0.00002625, + "output_cost_per_token": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-2024-08-06": { - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, - "input_cost_per_token_batches": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_batches": 0.000005, + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 6e-7, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-2024-11-20": { - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, - "input_cost_per_token_batches": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_batches": 0.000005, + "output_cost_per_token": 3e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true - }, - "gpt-4o-audio-preview": { - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00001, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-audio-preview-2024-10-01": { - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash-lite-001": { + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00001, - "supports_audio_input": true, + "output_cost_per_token": 3e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash-live-preview-04-09": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000003, + "input_cost_per_image": 0.000003, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.000003, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00001, - "supports_audio_input": true, + "output_cost_per_audio_token": 0.000012, + "output_cost_per_token": 0.000002, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], "supports_audio_output": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "gpt-4o-audio-preview-2025-06-03": { - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash-preview-image-generation": { + "deprecation_date": "2025-11-14", + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00001, + "output_cost_per_token": 4e-7, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-audio": { - "input_cost_per_audio_token": 0.000032, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash-thinking-exp": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.00001, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" - ], + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", - "audio" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text", - "audio" + "image" ], - "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true, + "supports_web_search": true }, - "gpt-audio-1.5": { - "input_cost_per_audio_token": 0.000032, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-flash-thinking-exp-01-21": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.00001, - "supported_endpoints": [ - "/v1/chat/completions" - ], + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", - "audio" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text", - "audio" + "image" ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_native_streaming": true, + "supports_audio_output": false, + "supports_function_calling": false, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true, + "supports_web_search": true }, - "gpt-audio-2025-08-28": { - "input_cost_per_audio_token": 0.000032, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" + "/v1/completions" ], "supported_modalities": [ "text", - "audio" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "audio" + "text" ], "supports_audio_input": true, - "supports_audio_output": true, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-audio-mini": { - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", + "gemini-2.5-computer-use-preview-10-2025": { + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_images_per_prompt": 3000, "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" - ], + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use", "supported_modalities": [ "text", - "audio" + "image" ], "supported_output_modalities": [ - "text", - "audio" + "text" ], - "supports_audio_input": true, - "supports_audio_output": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, - "gpt-audio-mini-2025-10-06": { - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.5-flash": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", + "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", - "audio" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "audio" + "text" ], - "supports_audio_input": true, - "supports_audio_output": true, + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-audio-mini-2025-12-15": { - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, + "gemini-2.5-flash-image": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "max_pdf_size_mb": 30, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 0.00003, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", + "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", - "audio" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text", - "audio" + "image" ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, - "gpt-4o-mini": { - "cache_read_input_token_cost": 7.5e-8, - "cache_read_input_token_cost_priority": 1.25e-7, - "input_cost_per_token": 1.5e-7, - "input_cost_per_token_batches": 7.5e-8, - "input_cost_per_token_priority": 2.5e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 6e-7, - "output_cost_per_token_batches": 3e-7, - "output_cost_per_token_priority": 0.000001, + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -16220,25 +13522,50 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": false, + "tpm": 8000000 }, - "gpt-4o-mini-2024-07-18": { + "gemini-2.5-flash-image-preview": { + "deprecation_date": "2026-01-15", "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 1.5e-7, - "input_cost_per_token_batches": 7.5e-8, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 6e-7, - "output_cost_per_token_batches": 3e-7, - "search_context_cost_per_query": { - "search_context_size_high": 0.03, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275 - }, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_image_token": 3e-7, + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 0.00003, + "output_cost_per_reasoning_token": 0.00003, + "output_cost_per_token": 0.00003, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -16246,237 +13573,432 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true - }, - "gpt-4o-mini-audio-preview": { - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 6e-7, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 6e-7, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-realtime-preview": { - "cache_creation_input_audio_token_cost": 3e-7, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "gpt-4o-mini-realtime-preview-2024-12-17": { - "cache_creation_input_audio_token_cost": 3e-7, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, - "supports_audio_input": true, - "supports_audio_output": true, + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-mini-search-preview": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 1.5e-7, - "input_cost_per_token_batches": 7.5e-8, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.5-flash-lite-preview-06-17": { + "deprecation_date": "2025-11-18", + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 6e-7, - "output_cost_per_token_batches": 3e-7, - "search_context_cost_per_query": { - "search_context_size_high": 0.03, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275 - }, + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_vision": true, "supports_web_search": true }, - "gpt-4o-mini-search-preview-2025-03-11": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 1.5e-7, - "input_cost_per_token_batches": 7.5e-8, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.5-flash-lite-preview-09-2025": { + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 6e-7, - "output_cost_per_token_batches": 3e-7, + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-realtime-preview": { - "cache_read_input_token_cost": 0.0000025, - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-2.5-flash-native-audio-latest": { + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00002, + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_audio_output": true }, - "gpt-4o-realtime-preview-2024-10-01": { - "cache_creation_input_audio_token_cost": 0.00002, - "cache_read_input_token_cost": 0.0000025, - "input_cost_per_audio_token": 0.0001, - "input_cost_per_token": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-2.5-flash-native-audio-preview-09-2025": { + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_audio_token": 0.0002, - "output_cost_per_token": 0.00002, + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], "supports_audio_input": true, - "supports_audio_output": true, + "supports_audio_output": true + }, + "gemini-2.5-flash-native-audio-preview-12-2025": { + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true + }, + "gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000035, + "output_cost_per_token": 6e-7, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_token_cost": 0.0000025, - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-2.5-flash-preview-05-20": { + "deprecation_date": "2025-11-18", + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00002, - "supports_audio_input": true, - "supports_audio_output": true, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-realtime-preview-2025-06-03": { - "cache_read_input_token_cost": 0.0000025, - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-2.5-flash-preview-09-2025": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00002, - "supports_audio_input": true, - "supports_audio_output": true, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-4o-search-preview": { - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, - "input_cost_per_token_batches": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.5-pro": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, - "output_cost_per_token_batches": 0.000005, - "search_context_cost_per_query": { - "search_context_size_high": 0.05, - "search_context_size_low": 0.03, - "search_context_size_medium": 0.035 - }, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, - "gpt-4o-search-preview-2025-03-11": { - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, - "input_cost_per_token_batches": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, - "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -16484,37 +14006,47 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true }, - "gpt-5": { + "gemini-2.5-pro-preview-03-25": { + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_flex": 6.25e-8, - "cache_read_input_token_cost_priority": 2.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, - "input_cost_per_token_flex": 6.25e-7, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, - "output_cost_per_token_flex": 0.000005, - "output_cost_per_token_priority": 0.00002, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -16522,35 +14054,49 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-5.1": { + "gemini-2.5-pro-preview-05-06": { + "deprecation_date": "2025-12-02", "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "image" + "text" + ], + "supported_regions": [ + "global" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -16558,35 +14104,45 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-5.1-2025-11-13": { + "gemini-2.5-pro-preview-06-05": { "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "image" + "text" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -16594,108 +14150,79 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-5.1-chat-latest": { + "gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "gpt-5.2": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", "supported_modalities": [ - "text", - "image" + "text" ], "supported_output_modalities": [ - "text", - "image" + "audio" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-5.2-2025-12-11": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 5e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, + "output_cost_per_reasoning_token": 0.000003, + "output_cost_per_token": 0.000003, + "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "image" + "text" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -16703,248 +14230,334 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 9e-7, + "input_cost_per_audio_token_priority": 0.0000018, + "output_cost_per_token_priority": 0.0000054, + "cache_read_input_token_cost_priority": 9e-8, + "supports_service_tier": true }, - "gpt-5.2-chat-latest": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, + "gemini-3-pro-image-preview": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 0.000012, + "output_cost_per_token_batches": 0.000006, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_function_calling": false, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-5.3-chat-latest": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-3-pro-preview": { + "deprecation_date": "2026-03-26", + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "gpt-5-2025-08-07": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_flex": 6.25e-8, - "cache_read_input_token_cost_priority": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_flex": 6.25e-7, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_flex": 0.000005, - "output_cost_per_token_priority": 0.00002, + "gemini-3.1-flash-image-preview": { + "input_cost_per_image": 0.00056, + "input_cost_per_token": 5e-7, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0672, + "output_cost_per_image_token": 0.00006, + "output_cost_per_token": 0.000003, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_function_calling": false, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_per_audio_token": 5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_reasoning_token": 0.0000015, + "output_cost_per_token": 0.0000015, + "source": "https://ai.google.dev/gemini-api/docs/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true }, - "gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "output_cost_per_image": 0.00012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, + "supports_audio_input": true, + "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_url_context": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-8, - "cache_read_input_token_cost_flex": 1.25e-8, - "cache_read_input_token_cost_priority": 4.5e-8, - "input_cost_per_token": 2.5e-7, - "input_cost_per_token_flex": 1.25e-7, - "input_cost_per_token_priority": 4.5e-7, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gemini-3.1-pro-preview-customtools": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000002, - "output_cost_per_token_flex": 0.000001, - "output_cost_per_token_priority": 0.0000036, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "output_cost_per_image": 0.00012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_url_context": true, + "supports_native_streaming": true }, - "gpt-5-mini-2025-08-07": { - "cache_read_input_token_cost": 2.5e-8, - "cache_read_input_token_cost_flex": 1.25e-8, - "cache_read_input_token_cost_priority": 4.5e-8, - "input_cost_per_token": 2.5e-7, - "input_cost_per_token_flex": 1.25e-7, - "input_cost_per_token_priority": 4.5e-7, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gemini-exp-1206": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000002, - "output_cost_per_token_flex": 0.000001, - "output_cost_per_token_priority": 0.0000036, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -16952,36 +14565,61 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "gpt-5-nano": { - "cache_read_input_token_cost": 5e-9, - "cache_read_input_token_cost_flex": 2.5e-9, - "input_cost_per_token": 5e-8, - "input_cost_per_token_flex": 2.5e-8, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gemini-flash-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-7, - "output_cost_per_token_flex": 2e-7, + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-flash-latest": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -16989,34 +14627,46 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "gpt-5-nano-2025-08-07": { - "cache_read_input_token_cost": 5e-9, - "cache_read_input_token_cost_flex": 2.5e-9, - "input_cost_per_token": 5e-8, - "input_cost_per_token_flex": 2.5e-8, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gemini-flash-lite-latest": { + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, - "output_cost_per_token_flex": 2e-7, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ "text" ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -17024,4636 +14674,6761 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "gpt-realtime": { - "cache_creation_input_audio_token_cost": 4e-7, - "cache_read_input_token_cost": 4e-7, - "input_cost_per_audio_token": 0.000032, - "input_cost_per_image": 0.000005, - "input_cost_per_token": 0.000004, - "litellm_provider": "openai", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-pro": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.000016, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-realtime-1.5": { - "cache_creation_input_audio_token_cost": 4e-7, - "cache_read_input_token_cost": 4e-7, - "input_cost_per_audio_token": 0.000032, - "input_cost_per_image": 0.000005, - "input_cost_per_token": 0.000004, - "litellm_provider": "openai", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-pro-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.000016, + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro-latest": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 2000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ - "/v1/realtime" + "/v1/chat/completions", + "/v1/completions" ], "supported_modalities": [ "text", "image", - "audio" + "audio", + "video" ], "supported_output_modalities": [ - "text", - "audio" + "text" ], "supports_audio_input": true, - "supports_audio_output": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 }, - "gpt-realtime-mini": { - "cache_creation_input_audio_token_cost": 3e-7, - "cache_read_input_audio_token_cost": 3e-7, - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-robotics-er-1.5-preview": { + "cache_read_input_token_cost": 0, + "input_cost_per_token": 3e-7, + "input_cost_per_audio_token": 0.000001, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, + "output_cost_per_token": 0.0000025, + "output_cost_per_reasoning_token": 0.0000025, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supported_endpoints": [ - "/v1/realtime" + "/v1/chat/completions", + "/v1/completions" ], "supported_modalities": [ "text", "image", + "video", "audio" ], "supported_output_modalities": [ - "text", - "audio" + "text" ], - "supports_audio_input": true, - "supports_audio_output": true, + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true }, - "gpt-realtime-2025-08-28": { - "cache_creation_input_audio_token_cost": 4e-7, - "cache_read_input_token_cost": 4e-7, - "input_cost_per_audio_token": 0.000032, - "input_cost_per_image": 0.000005, - "input_cost_per_token": 0.000004, - "litellm_provider": "openai", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.000016, + "gemini/deep-research-pro-preview-12-2025": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 0.000012, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 0.000006, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ - "/v1/realtime" + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", - "image", - "audio" + "image" ], "supported_output_modalities": [ "text", - "audio" + "image" ], - "supports_audio_input": true, - "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini/gemini-1.5-flash": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/alibaba-qwen3-32b": { - "litellm_provider": "gradient_ai", - "max_tokens": 2048, + "gemini/gemini-1.5-flash-001": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2025-05-24", + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/anthropic-claude-3-opus": { - "input_cost_per_token": 0.000015, - "litellm_provider": "gradient_ai", - "max_tokens": 1024, + "gemini/gemini-1.5-flash-002": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2025-09-24", + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000075, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/anthropic-claude-3.5-haiku": { - "input_cost_per_token": 8e-7, - "litellm_provider": "gradient_ai", - "max_tokens": 1024, + "gemini/gemini-1.5-flash-8b": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000004, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b-exp-0827": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b-exp-0924": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/anthropic-claude-3.5-sonnet": { - "input_cost_per_token": 0.000003, - "litellm_provider": "gradient_ai", - "max_tokens": 1024, + "gemini/gemini-1.5-flash-exp-0827": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000015, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/anthropic-claude-3.7-sonnet": { - "input_cost_per_token": 0.000003, - "litellm_provider": "gradient_ai", - "max_tokens": 1024, + "gemini/gemini-1.5-flash-latest": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000015, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/deepseek-r1-distill-llama-70b": { - "input_cost_per_token": 9.9e-7, - "litellm_provider": "gradient_ai", - "max_tokens": 8000, + "gemini/gemini-1.5-pro": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9.9e-7, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/llama3-8b-instruct": { - "input_cost_per_token": 2e-7, - "litellm_provider": "gradient_ai", - "max_tokens": 512, + "gemini/gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2e-7, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/llama3.3-70b-instruct": { - "input_cost_per_token": 6.5e-7, - "litellm_provider": "gradient_ai", - "max_tokens": 2048, + "gemini/gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.5e-7, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/mistral-nemo-instruct-2407": { - "input_cost_per_token": 3e-7, - "litellm_provider": "gradient_ai", - "max_tokens": 512, + "gemini/gemini-1.5-pro-exp-0801": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-7, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/openai-gpt-4o": { - "litellm_provider": "gradient_ai", - "max_tokens": 16384, + "gemini/gemini-1.5-pro-exp-0827": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/openai-gpt-4o-mini": { - "litellm_provider": "gradient_ai", - "max_tokens": 16384, + "gemini/gemini-1.5-pro-latest": { + "deprecation_date": "2025-09-29", + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text" - ], - "supports_tool_choice": false + "output_cost_per_token": 0.00000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "gradient_ai/openai-o3": { - "input_cost_per_token": 0.000002, - "litellm_provider": "gradient_ai", - "max_tokens": 100000, + "gemini/gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000008, - "supported_endpoints": [ - "/v1/chat/completions" - ], + "output_cost_per_token": 4e-7, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ - "text" - ], - "supports_tool_choice": false - }, - "gradient_ai/openai-o3-mini": { - "input_cost_per_token": 0.0000011, - "litellm_provider": "gradient_ai", - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 0.0000044, - "supported_endpoints": [ - "/v1/chat/completions" + "text", + "image", + "audio", + "video" ], - "supported_modalities": [ - "text" + "supported_output_modalities": [ + "text", + "image" ], - "supports_tool_choice": false - }, - "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { - "input_cost_per_token": 0, - "litellm_provider": "lemonade", - "max_tokens": 32768, - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "lemonade/gpt-oss-20b-mxfp4-GGUF": { - "input_cost_per_token": 0, - "litellm_provider": "lemonade", - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, + "gemini/gemini-2.0-flash-001": { + "cache_read_input_token_cost": 2.5e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0, + "output_cost_per_token": 4e-7, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "lemonade/gpt-oss-120b-mxfp-GGUF": { + "gemini/gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, - "litellm_provider": "lemonade", - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 }, - "lemonade/Gemma-3-4b-it-GGUF": { - "input_cost_per_token": 0, - "litellm_provider": "lemonade", - "max_tokens": 8192, - "max_input_tokens": 128000, + "gemini/gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0, + "output_cost_per_token": 3e-7, + "rpm": 4000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 }, - "lemonade/Qwen3-4B-Instruct-2507-GGUF": { - "input_cost_per_token": 0, - "litellm_provider": "lemonade", - "max_tokens": 32768, - "max_input_tokens": 262144, - "max_output_tokens": 32768, + "gemini/gemini-2.0-flash-lite-001": { + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0, + "output_cost_per_token": 3e-7, + "rpm": 4000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 }, - "amazon-nova/nova-micro-v1": { - "input_cost_per_token": 3.5e-8, - "litellm_provider": "amazon_nova", - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "gemini/gemini-2.0-flash-lite-preview-02-05": { + "deprecation_date": "2025-12-09", + "cache_read_input_token_cost": 1.875e-8, + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 1.4e-7, + "output_cost_per_token": 3e-7, + "rpm": 60000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "amazon-nova/nova-lite-v1": { - "input_cost_per_token": 6e-8, - "litellm_provider": "amazon_nova", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "gemini/gemini-2.0-flash-live-001": { + "deprecation_date": "2025-12-09", + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.0000021, + "input_cost_per_image": 0.0000021, + "input_cost_per_token": 3.5e-7, + "input_cost_per_video_per_second": 0.0000021, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 2.4e-7, + "output_cost_per_audio_token": 0.0000085, + "output_cost_per_token": 0.0000015, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_output": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "amazon-nova/nova-premier-v1": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "amazon_nova", - "max_input_tokens": 1000000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "gemini/gemini-2.0-flash-preview-image-generation": { + "deprecation_date": "2025-11-14", + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.0000125, + "output_cost_per_token": 4e-7, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "amazon-nova/nova-pro-v1": { - "input_cost_per_token": 8e-7, - "litellm_provider": "amazon_nova", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "gemini/gemini-2.0-flash-thinking-exp": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.0000032, + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true - }, - "groq/llama-3.1-8b-instant": { - "input_cost_per_token": 5e-8, - "litellm_provider": "groq", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-8, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 }, - "groq/llama-3.3-70b-versatile": { - "input_cost_per_token": 5.9e-7, - "litellm_provider": "groq", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.0-flash-thinking-exp-01-21": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 7.9e-7, + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 }, - "groq/gemma-7b-it": { - "input_cost_per_token": 5e-8, - "litellm_provider": "groq", - "max_input_tokens": 8192, + "gemini/gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, "max_output_tokens": 8192, + "max_pdf_size_mb": 30, "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 8e-8, + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_audio_input": true, "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 1000000 }, - "groq/meta-llama/llama-guard-4-12b": { - "input_cost_per_token": 2e-7, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gemini/gemini-2.5-computer-use-preview-10-2025": { + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "gemini", + "max_images_per_prompt": 3000, + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2e-7 + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/computer-use", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 800000 }, - "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "input_cost_per_token": 2e-7, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gemini/gemini-2.5-flash": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "input_cost_per_token": 1.1e-7, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3.4e-7, + "gemini/gemini-2.5-flash-image": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "supports_reasoning": false, + "max_images_per_prompt": 3000, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "max_pdf_size_mb": 30, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 0.00003, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "groq/moonshotai/kimi-k2-instruct-0905": { - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000003, - "cache_read_input_token_cost": 5e-7, - "litellm_provider": "groq", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", + "gemini/gemini-2.5-flash-image-preview": { + "deprecation_date": "2026-01-15", + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 0.00003, + "output_cost_per_reasoning_token": 0.00003, + "output_cost_per_token": 0.00003, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "groq/openai/gpt-oss-120b": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 32766, - "max_tokens": 32766, + "gemini/gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "groq/openai/gpt-oss-20b": { - "cache_read_input_token_cost": 3.75e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-flash-lite-preview-06-17": { + "deprecation_date": "2025-11-18", + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "groq/openai/gpt-oss-safeguard-20b": { - "cache_read_input_token_cost": 3.7e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "gemini/gemini-2.5-flash-lite-preview-09-2025": { + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "groq/qwen/qwen3-32b": { - "input_cost_per_token": 2.9e-7, - "litellm_provider": "groq", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 5.9e-7, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "heroku/claude-3-5-haiku": { - "litellm_provider": "heroku", - "max_tokens": 4096, - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "heroku/claude-3-5-sonnet-latest": { - "litellm_provider": "heroku", - "max_tokens": 8192, - "mode": "chat", - "supports_function_calling": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "heroku/claude-3-7-sonnet": { - "litellm_provider": "heroku", + "gemini/gemini-2.5-flash-native-audio-latest": { + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "tpm": 250000, + "rpm": 10 }, - "heroku/claude-4-sonnet": { - "litellm_provider": "heroku", + "gemini/gemini-2.5-flash-native-audio-preview-09-2025": { + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/QwQ-32B": { - "input_cost_per_token": 2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen3-235B-A22B": { - "input_cost_per_token": 0.000002, - "litellm_provider": "hyperbolic", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "tpm": 250000, + "rpm": 10 }, - "hyperbolic/deepseek-ai/DeepSeek-R1": { - "input_cost_per_token": 4e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "tpm": 250000, + "rpm": 10 }, - "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 2.5e-7, + "output_cost_per_reasoning_token": 0.0000035, + "output_cost_per_token": 6e-7, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "hyperbolic/deepseek-ai/DeepSeek-V3": { - "input_cost_per_token": 2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-flash-preview-05-20": { + "deprecation_date": "2025-11-18", + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 2e-7, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { - "input_cost_per_token": 4e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-flash-preview-09-2025": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 4e-7, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-pro": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "input_cost_per_token_priority": 0.00000125, + "input_cost_per_token_above_200k_tokens_priority": 0.0000025, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "output_cost_per_token_priority": 0.00001, + "output_cost_per_token_above_200k_tokens_priority": 0.000015, + "rpm": 2000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_service_tier": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 }, - "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_200k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0, + "output_cost_per_token_above_200k_tokens": 0, + "rpm": 5, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-2.5-pro-preview-03-25": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-pro-preview-05-06": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "hyperbolic", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gemini/gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, - "hyperbolic/moonshotai/Kimi-K2-Instruct": { - "input_cost_per_token": 0.000002, - "litellm_provider": "hyperbolic", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 5e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000002, + "output_cost_per_reasoning_token": 0.000003, + "output_cost_per_token": 0.000003, + "rpm": 2000, + "source": "https://ai.google.dev/pricing/gemini-3", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true - }, - "jamba-1.5": { - "input_cost_per_token": 2e-7, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_tool_choice": true - }, - "jamba-1.5-large": { - "input_cost_per_token": 0.000002, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.000008, - "supports_tool_choice": true - }, - "jamba-1.5-large@001": { - "input_cost_per_token": 0.000002, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.000008, - "supports_tool_choice": true - }, - "jamba-1.5-mini": { - "input_cost_per_token": 2e-7, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_tool_choice": true - }, - "jamba-1.5-mini@001": { - "input_cost_per_token": 2e-7, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 800000, + "input_cost_per_token_priority": 9e-7, + "input_cost_per_audio_token_priority": 0.0000018, + "output_cost_per_token_priority": 0.0000054, + "cache_read_input_token_cost_priority": 9e-8, + "supports_service_tier": true }, - "jamba-large-1.6": { + "gemini/gemini-3-pro-image-preview": { + "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.000008, - "supports_tool_choice": true + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 0.000012, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 0.000006, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true }, - "jamba-large-1.7": { + "gemini/gemini-3-pro-preview": { + "deprecation_date": "2026-03-09", + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.000002, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.000008, - "supports_tool_choice": true - }, - "jamba-mini-1.6": { - "input_cost_per_token": 2e-7, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_tool_choice": true - }, - "jamba-mini-1.7": { - "input_cost_per_token": 2e-7, - "litellm_provider": "ai21", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_tool_choice": true - }, - "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 0.000004125, - "cache_read_input_token_cost": 3.3e-7, - "input_cost_per_token": 0.0000033, - "input_cost_per_token_above_200k_tokens": 0.0000066, - "output_cost_per_token_above_200k_tokens": 0.00002475, - "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.0000165, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "rpm": 2000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_video_input": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_web_search": true, + "tpm": 800000, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.000001375, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "gemini/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_per_audio_token": 5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.0000055, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_reasoning_token": 0.0000015, + "output_cost_per_token": 0.0000015, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "lambda_ai/deepseek-llama3.3-70b": { - "input_cost_per_token": 2e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000 }, - "lambda_ai/deepseek-r1-0528": { - "input_cost_per_token": 2e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_url_context": true, + "supports_native_streaming": true, + "tpm": 800000, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "lambda_ai/deepseek-r1-671b": { - "input_cost_per_token": 8e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-3.1-pro-preview-customtools": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 8e-7, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/deepseek-v3-0324": { - "input_cost_per_token": 2e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_url_context": true, + "supports_native_streaming": true, + "tpm": 800000, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "lambda_ai/hermes3-405b": { - "input_cost_per_token": 8e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-exp-1114": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "metadata": { + "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", + "supports_tool_choice": true + }, "mode": "chat", - "output_cost_per_token": 8e-7, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "lambda_ai/hermes3-70b": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-exp-1206": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "metadata": { + "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", + "supports_tool_choice": true + }, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 }, - "lambda_ai/hermes3-8b": { - "input_cost_per_token": 2.5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 4e-8, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "lambda_ai/lfm-40b": { + "gemini/gemini-flash-lite-latest": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 2e-7, + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "lambda_ai/lfm-7b": { - "input_cost_per_token": 2.5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-gemma-2-27b-it": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "gemini", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-8, + "output_cost_per_token": 0.00000105, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 250000, + "rpm": 10 }, - "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { - "input_cost_per_token": 5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, + "gemini/gemini-gemma-2-9b-it": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "gemini", "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1e-7, + "output_cost_per_token": 0.00000105, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 250000, + "rpm": 10 }, - "lambda_ai/llama-4-scout-17b-16e-instruct": { - "input_cost_per_token": 5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 16384, + "gemini/gemini-pro": { + "input_cost_per_token": 3.5e-7, + "input_cost_per_token_above_128k_tokens": 7e-7, + "litellm_provider": "gemini", + "max_input_tokens": 32760, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1e-7, + "output_cost_per_token": 0.00000105, + "output_cost_per_token_above_128k_tokens": 0.0000021, + "rpd": 30000, + "rpm": 360, + "source": "https://ai.google.dev/gemini-api/docs/models/gemini", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "tpm": 120000 + }, + "gemini/gemini-pro-latest": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 2000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 }, - "lambda_ai/llama3.1-405b-instruct-fp8": { - "input_cost_per_token": 8e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/gemini-pro-vision": { + "input_cost_per_token": 3.5e-7, + "input_cost_per_token_above_128k_tokens": 7e-7, + "litellm_provider": "gemini", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 8e-7, + "output_cost_per_token": 0.00000105, + "output_cost_per_token_above_128k_tokens": 0.0000021, + "rpd": 30000, + "rpm": 360, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 120000 + }, + "gemini/gemini-robotics-er-1.5-preview": { + "cache_read_input_token_cost": 0, + "input_cost_per_token": 3e-7, + "input_cost_per_audio_token": 0.000001, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "output_cost_per_reasoning_token": 0.0000025, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "rpm": 10 }, - "lambda_ai/llama3.1-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "lambda_ai", + "gemini/gemma-3-27b-it": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true }, - "lambda_ai/llama3.1-8b-instruct": { - "input_cost_per_token": 2.5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gemini/learnlm-1.5-pro-experimental": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 32767, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-8, + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, - "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gigachat/GigaChat-2-Lite": { + "input_cost_per_token": 0, + "litellm_provider": "gigachat", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "lambda_ai/llama3.2-11b-vision-instruct": { - "input_cost_per_token": 1.5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gigachat/GigaChat-2-Max": { + "input_cost_per_token": 0, + "litellm_provider": "gigachat", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.5e-8, + "output_cost_per_token": 0, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_tool_choice": true, "supports_vision": true }, - "lambda_ai/llama3.2-3b-instruct": { - "input_cost_per_token": 1.5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gigachat/GigaChat-2-Pro": { + "input_cost_per_token": 0, + "litellm_provider": "gigachat", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.5e-8, + "output_cost_per_token": 0, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_vision": true }, - "lambda_ai/llama3.3-70b-instruct-fp8": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "github_copilot/claude-haiku-4.5": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 3e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_vision": true }, - "lambda_ai/qwen25-coder-32b-instruct": { - "input_cost_per_token": 5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "github_copilot/claude-opus-4.5": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 1e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_vision": true }, - "lambda_ai/qwen3-32b-fp8": { - "input_cost_per_token": 5e-8, - "litellm_provider": "lambda_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "github_copilot/claude-opus-4.6-fast": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 1e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "luminous-base-control": { - "input_cost_per_token": 0.0000375, - "litellm_provider": "aleph_alpha", - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 0.00004125 - }, - "luminous-extended-control": { - "input_cost_per_token": 0.00005625, - "litellm_provider": "aleph_alpha", - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 0.000061875 - }, - "luminous-supreme-control": { - "input_cost_per_token": 0.00021875, - "litellm_provider": "aleph_alpha", - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 0.000240625 - }, - "medlm-large": { - "input_cost_per_character": 0.000005, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "chat", - "output_cost_per_character": 0.000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "medlm-medium": { - "input_cost_per_character": 5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_character": 0.000001, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "meta.llama2-13b-chat-v1": { - "input_cost_per_token": 7.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000001 + "supports_vision": true }, - "meta.llama2-70b-chat-v1": { - "input_cost_per_token": 0.00000195, - "litellm_provider": "bedrock", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "github_copilot/claude-opus-41": { + "litellm_provider": "github_copilot", + "max_input_tokens": 80000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 0.00000256 + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_vision": true }, - "meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 0.00000532, - "litellm_provider": "bedrock", + "github_copilot/claude-sonnet-4": { + "litellm_provider": "github_copilot", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 0.000016, + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, - "supports_tool_choice": false + "supports_parallel_function_calling": true, + "supports_vision": true }, - "meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-7, - "litellm_provider": "bedrock", + "github_copilot/claude-sonnet-4.5": { + "litellm_provider": "github_copilot", "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 9.9e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], "supports_function_calling": true, - "supports_tool_choice": false + "supports_parallel_function_calling": true, + "supports_vision": true }, - "meta.llama3-1-8b-instruct-v1:0": { - "input_cost_per_token": 2.2e-7, - "litellm_provider": "bedrock", + "github_copilot/gemini-2.5-pro": { + "litellm_provider": "github_copilot", "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.2e-7, "supports_function_calling": true, - "supports_tool_choice": false + "supports_parallel_function_calling": true, + "supports_vision": true }, - "meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "bedrock", + "github_copilot/gemini-3-pro-preview": { + "litellm_provider": "github_copilot", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 3.5e-7, "supports_function_calling": true, - "supports_tool_choice": false, + "supports_parallel_function_calling": true, "supports_vision": true }, - "meta.llama3-2-1b-instruct-v1:0": { - "input_cost_per_token": 1e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "github_copilot/gpt-3.5-turbo": { + "litellm_provider": "github_copilot", + "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "supports_function_calling": true }, - "meta.llama3-2-3b-instruct-v1:0": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "github_copilot/gpt-3.5-turbo-0613": { + "litellm_provider": "github_copilot", + "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "supports_function_calling": true }, - "meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 0.000002, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "github_copilot/gpt-4": { + "litellm_provider": "github_copilot", + "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true + "supports_function_calling": true }, - "meta.llama3-3-70b-instruct-v1:0": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "github_copilot/gpt-4-0613": { + "litellm_provider": "github_copilot", + "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7.2e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "supports_function_calling": true }, - "meta.llama3-70b-instruct-v1:0": { - "input_cost_per_token": 0.00000265, - "litellm_provider": "bedrock", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "github_copilot/gpt-4-o-preview": { + "litellm_provider": "github_copilot", + "max_input_tokens": 64000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000035 + "supports_function_calling": true, + "supports_parallel_function_calling": true }, - "meta.llama3-8b-instruct-v1:0": { - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "github_copilot/gpt-4.1": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6e-7 + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true }, - "meta.llama4-maverick-17b-instruct-v1:0": { - "input_cost_per_token": 2.4e-7, - "input_cost_per_token_batches": 1.2e-7, - "litellm_provider": "bedrock_converse", + "github_copilot/gpt-4.1-2025-04-14": { + "litellm_provider": "github_copilot", "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-4o": { + "litellm_provider": "github_copilot", + "max_input_tokens": 64000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 9.7e-7, - "output_cost_per_token_batches": 4.85e-7, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], "supports_function_calling": true, - "supports_tool_choice": false + "supports_parallel_function_calling": true, + "supports_vision": true }, - "meta.llama4-scout-17b-instruct-v1:0": { - "input_cost_per_token": 1.7e-7, - "input_cost_per_token_batches": 8.5e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "github_copilot/gpt-4o-2024-05-13": { + "litellm_provider": "github_copilot", + "max_input_tokens": 64000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 6.6e-7, - "output_cost_per_token_batches": 3.3e-7, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], "supports_function_calling": true, - "supports_tool_choice": false + "supports_parallel_function_calling": true, + "supports_vision": true }, - "meta_llama/Llama-3.3-70B-Instruct": { - "litellm_provider": "meta_llama", - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "github_copilot/gpt-4o-2024-08-06": { + "litellm_provider": "github_copilot", + "max_input_tokens": 64000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true }, - "meta_llama/Llama-3.3-8B-Instruct": { - "litellm_provider": "meta_llama", - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "github_copilot/gpt-4o-2024-11-20": { + "litellm_provider": "github_copilot", + "max_input_tokens": 64000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_vision": true }, - "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "litellm_provider": "meta_llama", - "max_input_tokens": 1000000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "github_copilot/gpt-4o-mini": { + "litellm_provider": "github_copilot", + "max_input_tokens": 64000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true }, - "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { - "litellm_provider": "meta_llama", - "max_input_tokens": 10000000, - "max_output_tokens": 4028, - "max_tokens": 4028, + "github_copilot/gpt-4o-mini-2024-07-18": { + "litellm_provider": "github_copilot", + "max_input_tokens": 64000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" + "supports_function_calling": true, + "supports_parallel_function_calling": true + }, + "github_copilot/gpt-5": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true }, - "minimax.minimax-m2": { - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock_converse", + "github_copilot/gpt-5-mini": { + "litellm_provider": "github_copilot", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000012, - "supports_system_messages": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true }, - "minimax.minimax-m2.1": { - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 196000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "github_copilot/gpt-5.1": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000012, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true }, - "minimax/MiniMax-M2.1": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7, - "litellm_provider": "minimax", + "github_copilot/gpt-5.2": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], "supports_function_calling": true, - "supports_tool_choice": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true }, - "minimax/MiniMax-M2.1-lightning": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000024, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7, - "litellm_provider": "minimax", + "glm-4-7-251222": { + "input_cost_per_token": 0, + "litellm_provider": "volcengine", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 0, + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_tool_choice": true }, - "minimax/MiniMax-M2.5": { + "global.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7, - "litellm_provider": "minimax", + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 0.0000025, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true }, - "minimax/MiniMax-M2.5-lightning": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000024, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7, - "litellm_provider": "minimax", + "global.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "minimax/MiniMax-M2": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7, - "litellm_provider": "minimax", + "global.anthropic.claude-opus-4-5-20251101-v1:0": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 0.000025, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "max_input_tokens": 200000, - "max_output_tokens": 8192 + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "mistral.magistral-small-2509": { - "input_cost_per_token": 5e-7, + "global.anthropic.claude-opus-4-6-v1": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000125, + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.000001, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_200k_tokens": 0.00001, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000025, + "output_cost_per_token_above_200k_tokens": 0.0000375, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "mistral.ministral-3-14b-instruct": { - "input_cost_per_token": 2e-7, + "global.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2e-7, + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_system_messages": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "mistral.ministral-3-3b-instruct": { - "input_cost_per_token": 1e-7, + "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1e-7, + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_system_messages": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "mistral.ministral-3-8b-instruct": { - "input_cost_per_token": 1.5e-7, + "global.anthropic.claude-sonnet-4-6": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.5e-7, + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_system_messages": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "mistral.mistral-7b-instruct-v0:2": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gmi/MiniMaxAI/MiniMax-M2.1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2e-7, - "supports_tool_choice": true + "output_cost_per_token": 0.0000012 }, - "mistral.mistral-large-2402-v1:0": { - "input_cost_per_token": 0.000008, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8": { + "input_cost_per_token": 3e-7, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000024, - "supports_function_calling": true + "output_cost_per_token": 0.0000014, + "supports_vision": true }, - "mistral.mistral-large-2407-v1:0": { - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gmi/anthropic/claude-opus-4": { + "input_cost_per_token": 0.000015, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000009, + "output_cost_per_token": 0.000075, "supports_function_calling": true, - "supports_tool_choice": true + "supports_vision": true }, - "mistral.mistral-large-3-675b-instruct": { - "input_cost_per_token": 5e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gmi/anthropic/claude-opus-4.5": { + "input_cost_per_token": 0.000005, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000025, "supports_function_calling": true, - "supports_system_messages": true + "supports_vision": true }, - "mistral.mistral-small-2402-v1:0": { - "input_cost_per_token": 0.000001, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gmi/anthropic/claude-sonnet-4": { + "input_cost_per_token": 0.000003, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000003, - "supports_function_calling": true + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_vision": true }, - "mistral.mixtral-8x7b-instruct-v0:1": { - "input_cost_per_token": 4.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gmi/anthropic/claude-sonnet-4.5": { + "input_cost_per_token": 0.000003, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 7e-7, - "supports_tool_choice": true + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_vision": true }, - "mistral.voxtral-mini-3b-2507": { - "input_cost_per_token": 4e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gmi/deepseek-ai/DeepSeek-V3-0324": { + "input_cost_per_token": 2.8e-7, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 4e-8, - "supports_audio_input": true, - "supports_system_messages": true + "output_cost_per_token": 8.8e-7, + "supports_function_calling": true }, - "mistral.voxtral-small-24b-2507": { - "input_cost_per_token": 1e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gmi/deepseek-ai/DeepSeek-V3.2": { + "input_cost_per_token": 2.8e-7, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_audio_input": true, - "supports_system_messages": true + "output_cost_per_token": 4e-7, + "supports_function_calling": true }, - "mistral/codestral-2405": { - "input_cost_per_token": 0.000001, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gmi/google/gemini-3-flash-preview": { + "input_cost_per_token": 5e-7, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.000003, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/codestral-2508": { - "input_cost_per_token": 3e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 9e-7, - "source": "https://mistral.ai/news/codestral-25-08", - "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_vision": true }, - "mistral/codestral-latest": { - "input_cost_per_token": 0.000001, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gmi/google/gemini-3-pro-preview": { + "input_cost_per_token": 0.000002, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000003, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 0.000012, + "supports_function_calling": true, + "supports_vision": true }, - "mistral/codestral-mamba-latest": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "gmi/moonshotai/Kimi-K2-Thinking": { + "input_cost_per_token": 8e-7, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.5e-7, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000012 }, - "mistral/devstral-medium-2507": { - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gmi/openai/gpt-4o": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_vision": true }, - "mistral/devstral-small-2505": { - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gmi/openai/gpt-4o-mini": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, + "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_vision": true }, - "mistral/devstral-small-2507": { - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gmi/openai/gpt-5": { + "input_cost_per_token": 0.00000125, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 0.00001, + "supports_function_calling": true }, - "mistral/devstral-small-latest": { - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "gmi/openai/gpt-5.1": { + "input_cost_per_token": 0.00000125, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 0.00001, + "supports_function_calling": true }, - "mistral/labs-devstral-small-2512": { - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "gmi/openai/gpt-5.2": { + "input_cost_per_token": 0.00000175, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 0.000014, + "supports_function_calling": true }, - "mistral/devstral-latest": { + "gmi/zai-org/GLM-4.7-FP8": { "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 0.000002 }, - "mistral/devstral-medium-latest": { - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "google.gemma-3-12b-it": { + "input_cost_per_token": 9e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 2.9e-7, + "supports_system_messages": true, + "supports_vision": true }, - "mistral/devstral-2512": { - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "google.gemma-3-27b-it": { + "input_cost_per_token": 2.3e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 3.8e-7, + "supports_system_messages": true, + "supports_vision": true }, - "mistral/magistral-medium-2506": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "google.gemma-3-4b-it": { + "input_cost_per_token": 4e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, + "output_cost_per_token": 8e-8, + "supports_system_messages": true, + "supports_vision": true + }, + "gpt-3.5-turbo": { + "input_cost_per_token": 5e-7, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/magistral-medium-2509": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "gpt-3.5-turbo-0125": { + "input_cost_per_token": 5e-7, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.0000015, "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/magistral-medium-1-2-2509": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "gpt-3.5-turbo-0301": { + "input_cost_per_token": 0.0000015, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "output_cost_per_token": 0.000002, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/magistral-medium-latest": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "gpt-3.5-turbo-0613": { + "input_cost_per_token": 0.0000015, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/magistral-small-2506": { - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "gpt-3.5-turbo-1106": { + "deprecation_date": "2026-09-28", + "input_cost_per_token": 0.000001, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/magistral-small-latest": { - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "gpt-3.5-turbo-16k": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "output_cost_per_token": 0.000004, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/magistral-small-1-2-2509": { - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "gpt-3.5-turbo-16k-0613": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, + "output_cost_per_token": 0.000004, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-large-2402": { - "input_cost_per_token": 0.000004, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gpt-4": { + "input_cost_per_token": 0.00003, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000012, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00006, "supports_function_calling": true, - "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-large-2407": { - "input_cost_per_token": 0.000003, - "litellm_provider": "mistral", + "gpt-4-0125-preview": { + "deprecation_date": "2026-03-26", + "input_cost_per_token": 0.00001, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000009, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00003, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-large-2411": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gpt-4-0314": { + "input_cost_per_token": 0.00003, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_token": 0.00006, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-large-latest": { - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4-0613": { + "deprecation_date": "2025-06-06", + "input_cost_per_token": 0.00003, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00006, "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "mistral/mistral-large-3": { - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4-1106-preview": { + "deprecation_date": "2026-03-26", + "input_cost_per_token": 0.00001, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00003, "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "mistral/mistral-large-2512": { - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4-1106-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 0.00001, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_token": 0.00003, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium": { - "input_cost_per_token": 0.0000027, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gpt-4-32k": { + "input_cost_per_token": 0.00006, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000081, - "supports_assistant_prefill": true, - "supports_response_schema": true, + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-medium-2312": { - "input_cost_per_token": 0.0000027, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gpt-4-32k-0314": { + "input_cost_per_token": 0.00006, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000081, - "supports_assistant_prefill": true, - "supports_response_schema": true, + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-medium-2505": { - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gpt-4-32k-0613": { + "input_cost_per_token": 0.00006, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-medium-latest": { - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4-turbo": { + "input_cost_per_token": 0.00001, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00003, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-3-1-2508": { - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 0.00001, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00003, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-small": { - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gpt-4-turbo-preview": { + "input_cost_per_token": 0.00001, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00003, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "mistral/mistral-small-latest": { - "input_cost_per_token": 6e-8, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 0.00001, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.8e-7, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_token": 0.00003, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-small-3-2-2506": { - "input_cost_per_token": 6e-8, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4.1": { + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_priority": 8.75e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_priority": 0.0000035, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.8e-7, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "output_cost_per_token_priority": 0.000014, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "mistral/ministral-3-3b-2512": { - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1e-7, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "mistral/ministral-3-8b-2512": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_priority": 1.75e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "input_cost_per_token_priority": 7e-7, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "output_cost_per_token_priority": 0.0000028, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "mistral/ministral-3-14b-2512": { - "input_cost_per_token": 2e-7, - "litellm_provider": "mistral", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "mistral/mistral-tiny": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-codestral-mamba": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-7, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/open-mistral-7b": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mistral-nemo": { - "input_cost_per_token": 3e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mistral-nemo-2407": { - "input_cost_per_token": 3e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_priority": 5e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, + "input_cost_per_token_priority": 2e-7, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "output_cost_per_token_priority": 8e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true }, - "mistral/open-mixtral-8x22b": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 65336, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_assistant_prefill": true, + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true }, - "mistral/open-mixtral-8x7b": { - "input_cost_per_token": 7e-7, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "gpt-4.5-preview": { + "cache_read_input_token_cost": 0.0000375, + "input_cost_per_token": 0.000075, + "input_cost_per_token_batches": 0.0000375, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 7e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 0.000075, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "mistral/pixtral-12b-2409": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "mistral", + "gpt-4.5-preview-2025-02-27": { + "cache_read_input_token_cost": 0.0000375, + "deprecation_date": "2025-07-14", + "input_cost_per_token": 0.000075, + "input_cost_per_token_batches": 0.0000375, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 0.000075, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "mistral/pixtral-large-2411": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", + "gpt-4o": { + "cache_read_input_token_cost": 0.00000125, + "cache_read_input_token_cost_priority": 0.000002125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "input_cost_per_token_priority": 0.00000425, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_priority": 0.000017, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "mistral/pixtral-large-latest": { - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", + "gpt-4o-2024-05-13": { + "input_cost_per_token": 0.000005, + "input_cost_per_token_batches": 0.0000025, + "input_cost_per_token_priority": 0.00000875, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token_priority": 0.00002625, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "moonshot.kimi-k2-thinking": { - "input_cost_per_token": 6e-7, - "litellm_provider": "bedrock_converse", + "gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000025, - "supports_reasoning": true, - "supports_system_messages": true + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true }, - "moonshotai.kimi-k2.5": { - "input_cost_per_token": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000003, + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_service_tier": true, + "supports_vision": true }, - "moonshot/kimi-k2-0711-preview": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4o-audio-preview": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2-0905-preview": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4o-audio-preview-2024-10-01": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2-turbo-preview": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 0.00000115, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000008, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2.5": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4o-audio-preview-2025-06-03": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-latest": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_priority": 1.25e-7, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "input_cost_per_token_priority": 2.5e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "output_cost_per_token_priority": 0.000001, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "moonshot/kimi-latest-128k": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "moonshot/kimi-latest-32k": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gpt-4o-mini-audio-preview": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 6e-7, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-latest-8k": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 2e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 6e-7, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-thinking-preview": { - "cache_read_input_token_cost": 1.5e-7, + "gpt-4o-mini-realtime-preview": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_vision": true + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2-thinking": { - "cache_read_input_token_cost": 1.5e-7, + "gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2-thinking-turbo": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 0.00000115, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "gpt-4o-mini-search-preview": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000008, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true }, - "moonshot/moonshot-v1-128k": { - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "moonshot/moonshot-v1-128k-0430": { - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "moonshot/moonshot-v1-128k-vision-preview": { - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-4o-mini-search-preview-2025-03-11": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "moonshot/moonshot-v1-32k": { - "input_cost_per_token": 0.000001, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gpt-4o-realtime-preview": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.000005, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-32k-0430": { - "input_cost_per_token": 0.000001, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 0.00002, + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 0.000005, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-32k-vision-preview": { - "input_cost_per_token": 0.000001, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.000005, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "moonshot/moonshot-v1-8k": { - "input_cost_per_token": 2e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gpt-4o-realtime-preview-2025-06-03": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.000005, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-8k-0430": { - "input_cost_per_token": 2e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gpt-4o-search-preview": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "search_context_cost_per_query": { + "search_context_size_high": 0.05, + "search_context_size_low": 0.03, + "search_context_size_medium": 0.035 + }, "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "moonshot/moonshot-v1-8k-vision-preview": { - "input_cost_per_token": 2e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gpt-4o-search-preview-2025-03-11": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "moonshot/moonshot-v1-auto": { - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "gpt-5": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_flex": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_flex": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", + "output_cost_per_token": 0.00001, + "output_cost_per_token_flex": 0.000005, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "morph/morph-v3-fast": { - "input_cost_per_token": 8e-7, - "litellm_provider": "morph", - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_flex": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_flex": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_flex": 0.000005, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false + }, + "gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000012, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": false, + "supports_native_streaming": true, "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": false + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "morph/morph-v3-large": { - "input_cost_per_token": 9e-7, - "litellm_provider": "morph", - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000019, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": false, + "supports_native_streaming": true, "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": false - }, - "nscale/Qwen/QwQ-32B": { - "input_cost_per_token": 1.8e-7, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { - "input_cost_per_token": 6e-8, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { - "input_cost_per_token": 1e-8, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 3e-8, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { - "input_cost_per_token": 1e-8, - "litellm_provider": "nscale", - "mode": "chat", - "output_cost_per_token": 3e-8, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "input_cost_per_token": 3.75e-7, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_flex": 1.25e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_flex": 1.25e-7, + "input_cost_per_token_priority": 4.5e-7, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.75e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.000002, + "output_cost_per_token_flex": 0.000001, + "output_cost_per_token_priority": 0.0000036, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { - "input_cost_per_token": 2.5e-8, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_flex": 1.25e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_flex": 1.25e-7, + "input_cost_per_token_priority": 4.5e-7, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-8, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.000002, + "output_cost_per_token_flex": 0.000001, + "output_cost_per_token_priority": 0.0000036, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "input_cost_per_token": 9e-8, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5-nano": { + "cache_read_input_token_cost": 5e-9, + "cache_read_input_token_cost_flex": 2.5e-9, + "input_cost_per_token": 5e-8, + "input_cost_per_token_flex": 2.5e-8, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 9e-8, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 4e-7, + "output_cost_per_token_flex": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { - "input_cost_per_token": 7e-8, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-9, + "cache_read_input_token_cost_flex": 2.5e-9, + "input_cost_per_token": 5e-8, + "input_cost_per_token_flex": 2.5e-8, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 7e-8, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 4e-7, + "output_cost_per_token_flex": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5-search-api": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { - "input_cost_per_token": 2e-7, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5-search-api-2025-10-14": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, - "nscale/meta-llama/Llama-3.1-8B-Instruct": { - "input_cost_per_token": 3e-8, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5.1": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-8, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, - "nscale/meta-llama/Llama-3.3-70B-Instruct": { - "input_cost_per_token": 2e-7, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5.1-2025-11-13": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, - "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 9e-8, - "litellm_provider": "nscale", + "gpt-5.1-chat-latest": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.9e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, - "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { - "input_cost_per_token": 6e-7, - "litellm_provider": "nscale", - "metadata": { - "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." - }, + "gpt-5.2": { + "cache_read_input_token_cost": 1.75e-7, + "cache_read_input_token_cost_priority": 3.5e-7, + "input_cost_per_token": 0.00000175, + "input_cost_per_token_priority": 0.0000035, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 0.000014, + "output_cost_per_token_priority": 0.000028, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true }, - "nebius/deepseek-ai/DeepSeek-R1": { + "gpt-5.2-2025-12-11": { + "cache_read_input_token_cost": 1.75e-7, + "cache_read_input_token_cost_priority": 3.5e-7, + "input_cost_per_token": 0.00000175, + "input_cost_per_token_priority": 0.0000035, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000014, + "output_cost_per_token_priority": 0.000028, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true + }, + "gpt-5.2-chat-latest": { + "cache_read_input_token_cost": 1.75e-7, + "cache_read_input_token_cost_priority": 3.5e-7, + "input_cost_per_token": 0.00000175, + "input_cost_per_token_priority": 0.0000035, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 8e-7, - "output_cost_per_token": 0.0000024, - "litellm_provider": "nebius", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 0.000014, + "output_cost_per_token_priority": 0.000028, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_web_search": true }, - "nebius/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 164000, - "max_input_tokens": 164000, - "max_output_tokens": 164000, - "input_cost_per_token": 8e-7, - "output_cost_per_token": 0.0000024, - "litellm_provider": "nebius", + "gpt-5.3-chat-latest": { + "cache_read_input_token_cost": 1.75e-7, + "cache_read_input_token_cost_priority": 3.5e-7, + "input_cost_per_token": 0.00000175, + "input_cost_per_token_priority": 0.0000035, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 0.000014, + "output_cost_per_token_priority": 0.000028, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_web_search": true }, - "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "gpt-5.4": { + "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_priority": 5e-7, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_priority": 0.000005, + "litellm_provider": "openai", + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-7, - "output_cost_per_token": 7.5e-7, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/deepseek-ai/DeepSeek-V3": { "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 0.0000015, - "litellm_provider": "nebius", - "mode": "chat", + "mode": "responses", + "output_cost_per_token": 0.000015, + "output_cost_per_token_priority": 0.0000225, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true }, - "nebius/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "gpt-5.4-2026-03-05": { + "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_priority": 5e-7, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_priority": 0.000005, + "litellm_provider": "openai", + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 0.0000015, - "litellm_provider": "nebius", - "mode": "chat", + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.000015, + "output_cost_per_token_priority": 0.0000225, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true }, - "nebius/google/gemma-3-27b-it": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "gpt-5.4-pro": { + "cache_read_input_token_cost": 0.000003, + "cache_read_input_token_cost_priority": 0.000006, + "input_cost_per_token": 0.00003, + "input_cost_per_token_priority": 0.00006, + "litellm_provider": "openai", + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "input_cost_per_token": 6e-8, - "output_cost_per_token": 2e-7, - "litellm_provider": "nebius", - "mode": "chat", + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00018, + "output_cost_per_token_priority": 0.00027, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, - "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, + "gpt-5.4-pro-2026-03-05": { + "cache_read_input_token_cost": 0.000003, + "cache_read_input_token_cost_priority": 0.000006, + "input_cost_per_token": 0.00003, + "input_cost_per_token_priority": 0.00006, + "litellm_provider": "openai", + "max_input_tokens": 1050000, "max_output_tokens": 128000, - "input_cost_per_token": 1.3e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/meta-llama/Llama-Guard-3-8B": { "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-8, - "output_cost_per_token": 6e-8, - "litellm_provider": "nebius", - "mode": "chat", - "source": "https://nebius.com/prices-ai-studio" + "mode": "responses", + "output_cost_per_token": 0.00018, + "output_cost_per_token_priority": 0.00027, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, - "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 128000, + "gpt-audio": { + "input_cost_per_audio_token": 0.000032, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-8, - "output_cost_per_token": 6e-8, - "litellm_provider": "nebius", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 128000, + "gpt-audio-1.5": { + "input_cost_per_audio_token": 0.000032, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.3e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "nebius", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 128000, + "gpt-audio-2025-08-28": { + "input_cost_per_audio_token": 0.000032, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000003, - "litellm_provider": "nebius", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "nebius/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 128000, + "gpt-audio-mini": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 4e-8, - "output_cost_per_token": 1.2e-7, - "litellm_provider": "nebius", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 128000, + "gpt-audio-mini-2025-10-06": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000003, - "litellm_provider": "nebius", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, + "gpt-audio-mini-2025-12-15": { + "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000018, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/Qwen/Qwen3-235B-A22B": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/Qwen/Qwen3-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/Qwen/Qwen3-30B-A3B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/Qwen/Qwen3-14B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 8e-8, - "output_cost_per_token": 2.4e-7, - "litellm_provider": "nebius", - "mode": "chat", - "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/Qwen/Qwen3-4B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 8e-8, - "output_cost_per_token": 2.4e-7, - "litellm_provider": "nebius", + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false }, - "nebius/Qwen/QwQ-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 4.5e-7, - "litellm_provider": "nebius", + "gpt-realtime": { + "cache_creation_input_audio_token_cost": 4e-7, + "cache_read_input_token_cost": 4e-7, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_reasoning": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.3e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "nebius", + "gpt-realtime-1.5": { + "cache_creation_input_audio_token_cost": 4e-7, + "cache_read_input_token_cost": 4e-7, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen2.5-32B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-8, - "output_cost_per_token": 2e-7, - "litellm_provider": "nebius", + "gpt-realtime-2025-08-28": { + "cache_creation_input_audio_token_cost": 4e-7, + "cache_read_input_token_cost": 4e-7, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen2.5-Coder-7B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-8, - "output_cost_per_token": 3e-8, - "litellm_provider": "nebius", + "gpt-realtime-mini": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_audio_token_cost": 3e-7, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "nebius", + "gpt-realtime-mini-2025-10-06": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 6e-8, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_image": 8e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "nebius/Qwen/Qwen2-VL-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "nebius", + "gpt-realtime-mini-2025-12-15": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 6e-8, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_image": 8e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, - "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" - }, - "nebius/Qwen/Qwen2-VL-7B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-8, - "output_cost_per_token": 6e-8, - "litellm_provider": "nebius", - "mode": "chat", - "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "nvidia.nemotron-nano-12b-v2": { - "input_cost_per_token": 2e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gradient_ai/alibaba-qwen3-32b": { + "litellm_provider": "gradient_ai", + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_system_messages": true, - "supports_vision": true + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "nvidia.nemotron-nano-9b-v2": { - "input_cost_per_token": 6e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gradient_ai/anthropic-claude-3-opus": { + "input_cost_per_token": 0.000015, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, "mode": "chat", - "output_cost_per_token": 2.3e-7, - "supports_system_messages": true + "output_cost_per_token": 0.000075, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "nvidia.nemotron-nano-3-30b": { - "input_cost_per_token": 6e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "gradient_ai/anthropic-claude-3.5-haiku": { + "input_cost_per_token": 8e-7, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, "mode": "chat", - "output_cost_per_token": 2.4e-7, - "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "output_cost_per_token": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "o1": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "gradient_ai/anthropic-claude-3.5-sonnet": { + "input_cost_per_token": 0.000003, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000015, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "o1-2024-12-17": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "gradient_ai/anthropic-claude-3.7-sonnet": { + "input_cost_per_token": 0.000003, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000015, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "o1-mini": { - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "gradient_ai/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 9.9e-7, + "litellm_provider": "gradient_ai", + "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 0.0000044, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_vision": true + "output_cost_per_token": 9.9e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "o1-mini-2024-09-12": { - "deprecation_date": "2025-10-27", - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000003, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "gradient_ai/llama3-8b-instruct": { + "input_cost_per_token": 2e-7, + "litellm_provider": "gradient_ai", + "max_tokens": 512, "mode": "chat", - "output_cost_per_token": 0.000012, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": true + "output_cost_per_token": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "o1-preview": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gradient_ai/llama3.3-70b-instruct": { + "input_cost_per_token": 6.5e-7, + "litellm_provider": "gradient_ai", + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": true + "output_cost_per_token": 6.5e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "o1-preview-2024-09-12": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "gradient_ai/mistral-nemo-instruct-2407": { + "input_cost_per_token": 3e-7, + "litellm_provider": "gradient_ai", + "max_tokens": 512, "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": true + "output_cost_per_token": 3e-7, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "o3": { - "cache_read_input_token_cost": 5e-7, - "cache_read_input_token_cost_flex": 2.5e-7, - "cache_read_input_token_cost_priority": 8.75e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_flex": 0.000001, - "input_cost_per_token_priority": 0.0000035, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "gradient_ai/openai-gpt-4o": { + "litellm_provider": "gradient_ai", + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000008, - "output_cost_per_token_flex": 0.000004, - "output_cost_per_token_priority": 0.000014, "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/chat/completions" ], "supported_modalities": [ - "text", - "image" + "text" ], - "supported_output_modalities": [ + "supports_tool_choice": false + }, + "gradient_ai/openai-gpt-4o-mini": { + "litellm_provider": "gradient_ai", + "max_tokens": 16384, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ "text" ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_tool_choice": false }, - "o3-2025-04-16": { - "cache_read_input_token_cost": 5e-7, + "gradient_ai/openai-o3": { "input_cost_per_token": 0.000002, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, + "litellm_provider": "gradient_ai", "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/chat/completions" ], "supported_modalities": [ - "text", - "image" + "text" ], - "supported_output_modalities": [ + "supports_tool_choice": false + }, + "gradient_ai/openai-o3-mini": { + "input_cost_per_token": 0.0000011, + "litellm_provider": "gradient_ai", + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ "text" ], + "supports_tool_choice": false + }, + "groq/gemma-7b-it": { + "input_cost_per_token": 5e-8, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-8, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true + }, + "groq/llama-3.1-8b-instant": { + "input_cost_per_token": 5e-8, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-8, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true + }, + "groq/llama-3.3-70b-versatile": { + "input_cost_per_token": 5.9e-7, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { + "input_cost_per_token": 2e-7, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_service_tier": true, "supports_vision": true }, - "o3-mini": { - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "groq/meta-llama/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 1.1e-7, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000044, + "output_cost_per_token": 3.4e-7, "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, - "o3-mini-2025-01-31": { - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "groq/meta-llama/llama-guard-4-12b": { + "input_cost_per_token": 2e-7, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-7 + }, + "groq/moonshotai/kimi-k2-instruct-0905": { + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003, + "cache_read_input_token_cost": 5e-7, + "litellm_provider": "groq", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000044, "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false + "supports_tool_choice": true }, - "o4-mini": { - "cache_read_input_token_cost": 2.75e-7, - "cache_read_input_token_cost_flex": 1.375e-7, - "cache_read_input_token_cost_priority": 5e-7, - "input_cost_per_token": 0.0000011, - "input_cost_per_token_flex": 5.5e-7, - "input_cost_per_token_priority": 0.000002, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "groq/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32766, + "max_tokens": 32766, "mode": "chat", - "output_cost_per_token": 0.0000044, - "output_cost_per_token_flex": 0.0000022, - "output_cost_per_token_priority": 0.000008, + "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_web_search": true }, - "o4-mini-2025-04-16": { - "cache_read_input_token_cost": 2.75e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "groq/openai/gpt-oss-20b": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.0000044, + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_service_tier": true, - "supports_vision": true + "supports_web_search": true }, - "oci/meta.llama-3.1-405b-instruct": { - "input_cost_per_token": 0.00001068, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "groq/openai/gpt-oss-safeguard-20b": { + "cache_read_input_token_cost": 3.7e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00001068, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true }, - "oci/meta.llama-3.2-90b-vision-instruct": { - "input_cost_per_token": 0.000002, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "groq/qwen/qwen3-32b": { + "input_cost_per_token": 2.9e-7, + "litellm_provider": "groq", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 5.9e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true }, - "oci/meta.llama-3.3-70b-instruct": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "heroku/claude-3-5-haiku": { + "litellm_provider": "heroku", + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7.2e-7, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "oci", - "max_input_tokens": 512000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "heroku/claude-3-5-sonnet-latest": { + "litellm_provider": "heroku", + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-7, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false - }, - "oci/meta.llama-4-scout-17b-16e-instruct": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "oci", - "max_input_tokens": 192000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "heroku/claude-3-7-sonnet": { + "litellm_provider": "heroku", + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-7, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/xai.grok-3": { - "input_cost_per_token": 0.000003, - "litellm_provider": "oci", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "heroku/claude-4-sonnet": { + "litellm_provider": "heroku", + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/xai.grok-3-fast": { - "input_cost_per_token": 0.000005, - "litellm_provider": "oci", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000025, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/xai.grok-3-mini": { - "input_cost_per_token": 3e-7, - "litellm_provider": "oci", + "hyperbolic/Qwen/QwQ-32B": { + "input_cost_per_token": 2e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 5e-7, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 2e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/xai.grok-3-mini-fast": { - "input_cost_per_token": 6e-7, - "litellm_provider": "oci", + "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000004, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/xai.grok-4": { - "input_cost_per_token": 0.000003, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/cohere.command-latest": { - "input_cost_per_token": 0.00000156, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "hyperbolic/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 0.000002, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000156, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_response_schema": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/cohere.command-a-03-2025": { - "input_cost_per_token": 0.00000156, - "litellm_provider": "oci", - "max_input_tokens": 256000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "hyperbolic/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 4e-7, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00000156, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "output_cost_per_token": 4e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "oci/cohere.command-plus-latest": { - "input_cost_per_token": 0.00000156, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000156, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "output_cost_per_token": 2.5e-7, "supports_function_calling": true, - "supports_response_schema": false + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/codegeex4": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", + "hyperbolic/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 2e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": false + "output_cost_per_token": 2e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/deepseek-coder-v2-instruct": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", + "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { + "input_cost_per_token": 4e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 4e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/deepseek-coder-v2-lite-instruct": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", + "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true - }, - "ollama/deepseek-v3.1:671b-cloud": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/gpt-oss:120b-cloud": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", + "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/gpt-oss:20b-cloud": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", + "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/internlm2_5-20b-chat": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", + "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "hyperbolic", "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/llama2": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "hyperbolic/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 0.000002, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "ollama/llama2:13b": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "jamba-1.5": { + "input_cost_per_token": 2e-7, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "ollama/llama2:70b": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "jamba-1.5-large": { + "input_cost_per_token": 0.000002, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 0.000008, + "supports_tool_choice": true }, - "ollama/llama2:7b": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "jamba-1.5-large@001": { + "input_cost_per_token": 0.000002, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 0.000008, + "supports_tool_choice": true }, - "ollama/llama3": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "jamba-1.5-mini": { + "input_cost_per_token": 2e-7, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "ollama/llama3.1": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "jamba-1.5-mini@001": { + "input_cost_per_token": 2e-7, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "ollama/llama3:70b": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "jamba-large-1.6": { + "input_cost_per_token": 0.000002, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 0.000008, + "supports_tool_choice": true }, - "ollama/llama3:8b": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "jamba-large-1.7": { + "input_cost_per_token": 0.000002, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 0.000008, + "supports_tool_choice": true }, - "ollama/mistral-7B-Instruct-v0.1": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "jamba-mini-1.6": { + "input_cost_per_token": 2e-7, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "ollama/mistral-7B-Instruct-v0.2": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "jamba-mini-1.7": { + "input_cost_per_token": 2e-7, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "ollama/mistral-large-instruct-2407": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, + "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "ollama/mixtral-8x22B-Instruct-v0.1": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "max_tokens": 65536, + "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.000004125, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "ollama/mixtral-8x7B-Instruct-v0.1": { + "kimi-k2-thinking-251104": { "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 32768, + "litellm_provider": "volcengine", + "max_input_tokens": 229376, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, - "supports_function_calling": true - }, - "ollama/qwen3-coder:480b-cloud": { - "input_cost_per_token": 0, - "litellm_provider": "ollama", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-llama3.3-70b": { + "input_cost_per_token": 2e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openai.gpt-oss-120b-1:0": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "lambda_ai/deepseek-r1-0528": { + "input_cost_per_token": 2e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "openai.gpt-oss-20b-1:0": { - "input_cost_per_token": 7e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "lambda_ai/deepseek-r1-671b": { + "input_cost_per_token": 8e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 8e-7, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "openai.gpt-oss-safeguard-120b": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lambda_ai/deepseek-v3-0324": { + "input_cost_per_token": 2e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, - "supports_system_messages": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openai.gpt-oss-safeguard-20b": { - "input_cost_per_token": 7e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lambda_ai/hermes3-405b": { + "input_cost_per_token": 8e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-7, - "supports_system_messages": true + "output_cost_per_token": 8e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-3-haiku": { - "input_cost_per_image": 0.0004, - "input_cost_per_token": 2.5e-7, - "litellm_provider": "openrouter", - "max_tokens": 200000, + "lambda_ai/hermes3-70b": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000125, + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-3.5-sonnet": { - "input_cost_per_token": 0.000003, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lambda_ai/hermes3-8b": { + "input_cost_per_token": 2.5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 4e-8, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-3.7-sonnet": { - "input_cost_per_image": 0.0048, - "input_cost_per_token": 0.000003, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "lambda_ai/lfm-40b": { + "input_cost_per_token": 1e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 2e-7, "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-opus-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "lambda_ai/lfm-7b": { + "input_cost_per_token": 2.5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 4e-8, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-opus-4.1": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 1e-7, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-sonnet-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "lambda_ai/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 16384, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 1e-7, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-sonnet-4.6": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "lambda_ai/llama3.1-405b-instruct-fp8": { + "input_cost_per_token": 8e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-7, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-opus-4.5": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "lambda_ai/llama3.1-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-opus-4.6": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "lambda_ai/llama3.1-8b-instruct": { + "input_cost_per_token": 2.5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 4e-8, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-sonnet-4.5": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "openrouter/anthropic/claude-haiku-4.5": { - "cache_creation_input_token_cost": 0.00000125, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "lambda_ai/llama3.2-11b-vision-instruct": { + "input_cost_per_token": 1.5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000005, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 2.5e-8, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_vision": true }, - "openrouter/bytedance/ui-tars-1.5-7b": { - "input_cost_per_token": 1e-7, - "litellm_provider": "openrouter", + "lambda_ai/llama3.2-3b-instruct": { + "input_cost_per_token": 1.5e-8, + "litellm_provider": "lambda_ai", "max_input_tokens": 131072, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", + "output_cost_per_token": 2.5e-8, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 1.4e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lambda_ai/llama3.3-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.8e-7, - "supports_prompt_caching": true, + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-chat-v3-0324": { - "input_cost_per_token": 1.4e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lambda_ai/qwen25-coder-32b-instruct": { + "input_cost_per_token": 5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.8e-7, - "supports_prompt_caching": true, + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-chat-v3.1": { - "input_cost_per_token": 2e-7, - "input_cost_per_token_cache_hit": 2e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "lambda_ai/qwen3-32b-fp8": { + "input_cost_per_token": 5e-8, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 8e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 1e-7, "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-v3.2": { - "input_cost_per_token": 2.8e-7, - "input_cost_per_token_cache_hit": 2.8e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "lemonade/Gemma-3-4b-it-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 8192, + "max_input_tokens": 128000, + "max_output_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 0, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-v3.2-exp": { - "input_cost_per_token": 2e-7, - "input_cost_per_token_cache_hit": 2e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "lemonade/Qwen3-4B-Instruct-2507-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 32768, + "max_input_tokens": 262144, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 0, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-r1": { - "input_cost_per_token": 5.5e-7, - "input_cost_per_token_cache_hit": 1.4e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 32768, + "max_input_tokens": 262144, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00000219, - "supports_assistant_prefill": true, + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "lemonade/gpt-oss-120b-mxfp-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 32768, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-r1-0528": { - "input_cost_per_token": 5e-7, - "input_cost_per_token_cache_hit": 1.4e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "max_tokens": 8192, + "lemonade/gpt-oss-20b-mxfp4-GGUF": { + "input_cost_per_token": 0, + "litellm_provider": "lemonade", + "max_tokens": 32768, + "max_input_tokens": 131072, + "max_output_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00000215, - "supports_assistant_prefill": true, + "output_cost_per_token": 0, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "openrouter", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "llamagate/codellama-7b": { + "max_tokens": 4096, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 1.2e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_audio_output": true, "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true }, - "openrouter/google/gemini-2.5-flash": { - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 3e-7, - "litellm_provider": "openrouter", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "llamagate/deepseek-coder-6.7b": { + "max_tokens": 4096, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 1.2e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 0.0000025, - "supports_audio_output": true, "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true }, - "openrouter/google/gemini-2.5-pro": { - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openrouter", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_pdf_size_mb": 30, - "max_tokens": 8192, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "llamagate/deepseek-r1-7b-qwen": { + "max_tokens": 16384, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 1.5e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_audio_output": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true }, - "openrouter/google/gemini-3-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "openrouter", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "llamagate/deepseek-r1-8b": { + "max_tokens": 16384, + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true + "supports_reasoning": true }, - "openrouter/google/gemini-3-flash-preview": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 5e-7, - "litellm_provider": "openrouter", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "llamagate/dolphin3-8b": { + "max_tokens": 8192, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 1.5e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_reasoning_token": 0.000003, - "output_cost_per_token": 0.000003, - "rpm": 2000, - "source": "https://ai.google.dev/pricing/gemini-3", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "supports_response_schema": true }, - "openrouter/google/gemini-3.1-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "llamagate/gemma3-4b": { + "max_tokens": 8192, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 3e-8, + "output_cost_per_token": 8e-8, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, "supports_vision": true }, - "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 0.000001875, - "litellm_provider": "openrouter", + "llamagate/llama-3.1-8b": { "max_tokens": 8192, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 3e-8, + "output_cost_per_token": 5e-8, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 0.000001875, - "supports_tool_choice": true - }, - "openrouter/mancer/weaver": { - "input_cost_per_token": 0.000005625, - "litellm_provider": "openrouter", - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 0.000005625, - "supports_tool_choice": true + "supports_function_calling": true, + "supports_response_schema": true }, - "openrouter/meta-llama/llama-3-70b-instruct": { - "input_cost_per_token": 5.9e-7, - "litellm_provider": "openrouter", + "llamagate/llama-3.2-3b": { "max_tokens": 8192, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 8e-8, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 7.9e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "supports_response_schema": true }, - "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 2.55e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, + "llamagate/llava-7b": { + "max_tokens": 2048, + "max_input_tokens": 4096, + "max_output_tokens": 2048, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 0.00000102, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_vision": true }, - "openrouter/mistralai/devstral-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "llamagate/mistral-7b-v0.3": { + "max_tokens": 8192, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1.5e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_vision": false + "supports_response_schema": true }, - "openrouter/mistralai/ministral-3b-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 1e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "llamagate/openthinker-7b": { + "max_tokens": 8192, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 1.5e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 1e-7, "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true, + "supports_reasoning": true }, - "openrouter/mistralai/ministral-8b-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "llamagate/qwen2.5-coder-7b": { + "max_tokens": 8192, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 1.2e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 1.5e-7, "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true }, - "openrouter/mistralai/ministral-14b-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 2e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "llamagate/qwen3-8b": { + "max_tokens": 8192, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 1.4e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 2e-7, "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true }, - "openrouter/mistralai/mistral-large-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "llamagate/qwen3-vl-8b": { + "max_tokens": 8192, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 5.5e-7, + "litellm_provider": "llamagate", "mode": "chat", - "output_cost_per_token": 0.0000015, "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, + "supports_response_schema": true, "supports_vision": true }, - "openrouter/mistralai/mistral-7b-instruct": { - "input_cost_per_token": 1.3e-7, - "litellm_provider": "openrouter", - "max_tokens": 8192, + "luminous-base-control": { + "input_cost_per_token": 0.0000375, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 1.3e-7, - "supports_tool_choice": true + "output_cost_per_token": 0.00004125 }, - "openrouter/mistralai/mistral-large": { - "input_cost_per_token": 0.000008, - "litellm_provider": "openrouter", - "max_tokens": 32000, + "luminous-extended-control": { + "input_cost_per_token": 0.00005625, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 0.000024, - "supports_tool_choice": true + "output_cost_per_token": 0.000061875 }, - "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 1e-7, - "litellm_provider": "openrouter", - "max_tokens": 32000, + "luminous-supreme-control": { + "input_cost_per_token": 0.00021875, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_tool_choice": true + "output_cost_per_token": 0.000240625 }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 1e-7, - "litellm_provider": "openrouter", - "max_tokens": 32000, + "medlm-large": { + "input_cost_per_character": 0.000005, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_character": 0.000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "openrouter/mistralai/mixtral-8x22b-instruct": { - "input_cost_per_token": 6.5e-7, - "litellm_provider": "openrouter", - "max_tokens": 65536, + "medlm-medium": { + "input_cost_per_character": 5e-7, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.5e-7, + "output_cost_per_character": 0.000001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "meta.llama2-13b-chat-v1": { + "input_cost_per_token": 7.5e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://openrouter.ai/moonshotai/kimi-k2.5", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "output_cost_per_token": 0.000001 }, - "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 0.0000015, - "litellm_provider": "openrouter", - "max_tokens": 4095, + "meta.llama2-70b-chat-v1": { + "input_cost_per_token": 0.00000195, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_tool_choice": true + "output_cost_per_token": 0.00000256 }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "input_cost_per_token": 0.000003, - "litellm_provider": "openrouter", - "max_tokens": 16383, + "meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 0.00000532, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000004, - "supports_tool_choice": true + "output_cost_per_token": 0.000016, + "supports_function_calling": true, + "supports_tool_choice": false }, - "openrouter/openai/gpt-4": { - "input_cost_per_token": 0.00003, - "litellm_provider": "openrouter", - "max_tokens": 8192, + "meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_tool_choice": true + "output_cost_per_token": 9.9e-7, + "supports_function_calling": true, + "supports_tool_choice": false }, - "openrouter/openai/gpt-4.1": { - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000002, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 0.000008, + "output_cost_per_token": 2.2e-7, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": false }, - "openrouter/openai/gpt-4.1-mini": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 4e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000016, + "output_cost_per_token": 3.5e-7, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "supports_tool_choice": false, "supports_vision": true }, - "openrouter/openai/gpt-4.1-nano": { - "cache_read_input_token_cost": 2.5e-8, + "meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 4e-7, + "output_cost_per_token": 1e-7, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": false }, - "openrouter/openai/gpt-4o": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "openrouter", + "meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 1.5e-7, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": false }, - "openrouter/openai/gpt-4o-2024-05-13": { - "input_cost_per_token": 0.000005, - "litellm_provider": "openrouter", + "meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 0.000002, + "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, + "supports_tool_choice": false, "supports_vision": true }, - "openrouter/openai/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openrouter", + "meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 7.2e-7, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000265, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000035 + }, + "meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7 + }, + "meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-7, + "input_cost_per_token_batches": 1.2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-7, + "output_cost_per_token_batches": 4.85e-7, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ - "text" + "text", + "code" ], - "supports_reasoning": true, - "supports_tool_choice": true + "supports_function_calling": true, + "supports_tool_choice": false }, - "openrouter/openai/gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-7, + "input_cost_per_token_batches": 8.5e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 6.6e-7, + "output_cost_per_token_batches": 3.3e-7, "supported_modalities": [ "text", "image" ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta_llama/Llama-3.3-70B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 4028, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text" + ], "supported_output_modalities": [ "text" ], - "supports_reasoning": true, + "supports_function_calling": true, "supports_tool_choice": true }, - "openrouter/openai/gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-7, - "input_cost_per_token": 0.00000175, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "meta_llama/Llama-3.3-8B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 4028, "mode": "chat", - "output_cost_per_token": 0.000014, + "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ - "text", - "image" + "text" ], "supported_output_modalities": [ "text" ], - "supports_reasoning": true, + "supports_function_calling": true, "supports_tool_choice": true }, - "openrouter/openai/gpt-5": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 1000000, + "max_output_tokens": 4028, + "max_tokens": 4028, "mode": "chat", - "output_cost_per_token": 0.00001, + "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" @@ -21661,18 +21436,16 @@ "supported_output_modalities": [ "text" ], - "supports_reasoning": true, + "supports_function_calling": true, "supports_tool_choice": true }, - "openrouter/openai/gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 2.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 10000000, + "max_output_tokens": 4028, + "max_tokens": 4028, "mode": "chat", - "output_cost_per_token": 0.000002, + "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" @@ -21680,10155 +21453,11266 @@ "supported_output_modalities": [ "text" ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "minimax.minimax-m2": { + "input_cost_per_token": 3e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "supports_system_messages": true + }, + "minimax.minimax-m2.1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 196000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "minimax/MiniMax-M2": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 3e-8, + "cache_creation_input_token_cost": 3.75e-7, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_system_messages": true, + "max_input_tokens": 200000, + "max_output_tokens": 8192 }, - "openrouter/openai/gpt-5-nano": { - "cache_read_input_token_cost": 5e-9, - "input_cost_per_token": 5e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "minimax/MiniMax-M2.1": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 3e-8, + "cache_creation_input_token_cost": 3.75e-7, + "litellm_provider": "minimax", "mode": "chat", - "output_cost_per_token": 4e-7, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 }, - "openrouter/openai/gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "minimax/MiniMax-M2.1-lightning": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000024, + "cache_read_input_token_cost": 3e-8, + "cache_creation_input_token_cost": 3.75e-7, + "litellm_provider": "minimax", "mode": "chat", - "output_cost_per_token": 0.00001, - "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], "supports_function_calling": true, + "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 }, - "openrouter/openai/gpt-5.2": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-7, - "input_cost_per_token": 0.00000175, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "minimax/MiniMax-M2.5": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 3e-8, + "cache_creation_input_token_cost": 3.75e-7, + "litellm_provider": "minimax", "mode": "chat", - "output_cost_per_token": 0.000014, "supports_function_calling": true, + "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 }, - "openrouter/openai/gpt-5.2-chat": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-7, - "input_cost_per_token": 0.00000175, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "minimax/MiniMax-M2.5-lightning": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000024, + "cache_read_input_token_cost": 3e-8, + "cache_creation_input_token_cost": 3.75e-7, + "litellm_provider": "minimax", "mode": "chat", - "output_cost_per_token": 0.000014, "supports_function_calling": true, - "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_vision": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 }, - "openrouter/openai/gpt-5.2-pro": { - "input_cost_per_image": 0, - "input_cost_per_token": 0.000021, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "mistral.devstral-2-123b": { + "input_cost_per_token": 4e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000168, + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "openrouter/openai/gpt-oss-120b": { - "input_cost_per_token": 1.8e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "mistral.magistral-small-2509": { + "input_cost_per_token": 5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8e-7, - "source": "https://openrouter.ai/openai/gpt-oss-120b", + "output_cost_per_token": 0.0000015, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "openrouter/openai/gpt-oss-20b": { - "input_cost_per_token": 2e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "mistral.ministral-3-14b-instruct": { + "input_cost_per_token": 2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_function_calling": true, + "supports_system_messages": true + }, + "mistral.ministral-3-3b-instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-7, - "source": "https://openrouter.ai/openai/gpt-oss-20b", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "openrouter/openai/o1": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "mistral.ministral-3-8b-instruct": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.00006, + "output_cost_per_token": 1.5e-7, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_system_messages": true }, - "openrouter/openai/o3-mini": { - "input_cost_per_token": 0.0000011, - "litellm_provider": "openrouter", + "mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_tool_choice": true + }, + "mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 0.000008, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true + }, + "mistral.mistral-large-2407-v1:0": { + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.0000044, + "output_cost_per_token": 0.000009, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false + "supports_tool_choice": true }, - "openrouter/openai/o3-mini-high": { - "input_cost_per_token": 0.0000011, - "litellm_provider": "openrouter", + "mistral.mistral-large-3-675b-instruct": { + "input_cost_per_token": 5e-7, + "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000044, + "output_cost_per_token": 0.0000015, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false + "supports_system_messages": true + }, + "mistral.mistral-small-2402-v1:0": { + "input_cost_per_token": 0.000001, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true }, - "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 1.8e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 33792, - "max_output_tokens": 33792, - "max_tokens": 33792, + "mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 1.8e-7, + "output_cost_per_token": 7e-7, "supports_tool_choice": true }, - "openrouter/qwen/qwen-vl-plus": { - "input_cost_per_token": 2.1e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, + "mistral.voxtral-mini-3b-2507": { + "input_cost_per_token": 4e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.3e-7, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 4e-8, + "supports_audio_input": true, + "supports_system_messages": true }, - "openrouter/qwen/qwen3-coder": { - "input_cost_per_token": 2.2e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262100, - "max_output_tokens": 262100, - "max_tokens": 262100, + "mistral.voxtral-small-24b-2507": { + "input_cost_per_token": 1e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9.5e-7, - "source": "https://openrouter.ai/qwen/qwen3-coder", - "supports_tool_choice": true, - "supports_function_calling": true + "output_cost_per_token": 3e-7, + "supports_audio_input": true, + "supports_system_messages": true }, - "openrouter/qwen/qwen3-coder-plus": { + "mistral/codestral-2405": { "input_cost_per_token": 0.000001, - "litellm_provider": "openrouter", - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://openrouter.ai/qwen/qwen3-coder-plus", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 7.1e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 1e-7, - "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", - "supports_function_calling": true, + "output_cost_per_token": 0.000003, + "supports_assistant_prefill": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "input_cost_per_token": 1.1e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "mistral/codestral-2508": { + "input_cost_per_token": 3e-7, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", + "output_cost_per_token": 9e-7, + "source": "https://mistral.ai/news/codestral-25-08", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/switchpoint/router": { - "input_cost_per_token": 8.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "mistral/codestral-latest": { + "input_cost_per_token": 0.000001, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.0000034, - "source": "https://openrouter.ai/switchpoint/router", + "output_cost_per_token": 0.000003, + "supports_assistant_prefill": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 0.000001875, - "litellm_provider": "openrouter", - "max_tokens": 6144, + "mistral/codestral-mamba-latest": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000001875, + "output_cost_per_token": 2.5e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, "supports_tool_choice": true }, - "openrouter/x-ai/grok-4": { - "input_cost_per_token": 0.000003, - "litellm_provider": "openrouter", + "mistral/devstral-2512": { + "input_cost_per_token": 4e-7, + "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://openrouter.ai/x-ai/grok-4", + "output_cost_per_token": 0.000002, + "source": "https://mistral.ai/news/devstral-2-vibe-cli", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "openrouter/z-ai/glm-4.6": { + "mistral/devstral-latest": { "input_cost_per_token": 4e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 202800, - "max_output_tokens": 131000, - "max_tokens": 131000, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.00000175, - "source": "https://openrouter.ai/z-ai/glm-4.6", + "output_cost_per_token": 0.000002, + "source": "https://mistral.ai/news/devstral-2-vibe-cli", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/z-ai/glm-4.6:exacto": { - "input_cost_per_token": 4.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 202800, - "max_output_tokens": 131000, - "max_tokens": 131000, + "mistral/devstral-medium-2507": { + "input_cost_per_token": 4e-7, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000019, - "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", + "output_cost_per_token": 0.000002, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/xiaomi/mimo-v2-flash": { - "input_cost_per_token": 9e-8, - "output_cost_per_token": 2.9e-7, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": false - }, - "openrouter/z-ai/glm-4.7": { + "mistral/devstral-medium-latest": { "input_cost_per_token": 4e-7, - "output_cost_per_token": 0.0000015, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 64000, - "max_tokens": 64000, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://mistral.ai/news/devstral-2-vibe-cli", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_assistant_prefill": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 7e-8, - "output_cost_per_token": 4e-7, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "mistral/devstral-small-2505": { + "input_cost_per_token": 1e-7, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_prompt_caching": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "openrouter/z-ai/glm-5": { - "input_cost_per_token": 8e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 202752, + "mistral/devstral-small-2507": { + "input_cost_per_token": 1e-7, + "litellm_provider": "mistral", + "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00000256, - "source": "https://openrouter.ai/z-ai/glm-5", + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 2.7e-7, - "output_cost_per_token": 0.0000012, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 204000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "mistral/devstral-small-latest": { + "input_cost_per_token": 1e-7, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_computer_use": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000011, - "cache_read_input_token_cost": 1.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 196608, - "max_output_tokens": 65536, - "max_tokens": 65536, + "mistral/labs-devstral-small-2512": { + "input_cost_per_token": 1e-7, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.5", + "output_cost_per_token": 3e-7, + "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "openrouter/openrouter/auto": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_tokens": 2000000, + "mistral/magistral-medium-1-2-2509": { + "input_cost_per_token": 0.000002, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true + "supports_tool_choice": true }, - "openrouter/openrouter/free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_tokens": 200000, + "mistral/magistral-medium-2506": { + "input_cost_per_token": 0.000002, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/openrouter/bodybuilder": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "chat" + "supports_tool_choice": true }, - "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { - "input_cost_per_token": 6.7e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, + "mistral/magistral-medium-2509": { + "input_cost_per_token": 0.000002, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", - "output_cost_per_token": 6.7e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", + "output_cost_per_token": 0.000005, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "ovhcloud/Llama-3.1-8B-Instruct": { - "input_cost_per_token": 1e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, + "mistral/magistral-medium-latest": { + "input_cost_per_token": 0.000002, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", - "output_cost_per_token": 1e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", + "output_cost_per_token": 0.000005, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "ovhcloud/Meta-Llama-3_1-70B-Instruct": { - "input_cost_per_token": 6.7e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 6.7e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct", - "supports_function_calling": false, - "supports_response_schema": false, - "supports_tool_choice": false - }, - "ovhcloud/Meta-Llama-3_3-70B-Instruct": { - "input_cost_per_token": 6.7e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, + "mistral/magistral-small-1-2-2509": { + "input_cost_per_token": 5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", - "output_cost_per_token": 6.7e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", + "output_cost_per_token": 0.0000015, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "ovhcloud/Mistral-7B-Instruct-v0.3": { - "input_cost_per_token": 1e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 127000, - "max_output_tokens": 127000, - "max_tokens": 127000, + "mistral/magistral-small-2506": { + "input_cost_per_token": 5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", - "output_cost_per_token": 1e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", + "output_cost_per_token": 0.0000015, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "ovhcloud/Mistral-Nemo-Instruct-2407": { - "input_cost_per_token": 1.3e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 118000, - "max_output_tokens": 118000, - "max_tokens": 118000, + "mistral/magistral-small-latest": { + "input_cost_per_token": 5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", - "output_cost_per_token": 1.3e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", + "output_cost_per_token": 0.0000015, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { - "input_cost_per_token": 9e-8, - "litellm_provider": "ovhcloud", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "mistral/ministral-3-14b-2512": { + "input_cost_per_token": 2e-7, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.8e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", + "output_cost_per_token": 2e-7, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 6.3e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 6.3e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false - }, - "ovhcloud/Qwen2.5-Coder-32B-Instruct": { - "input_cost_per_token": 8.7e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "mistral/ministral-3-3b-2512": { + "input_cost_per_token": 1e-7, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 8.7e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct", - "supports_function_calling": false, + "output_cost_per_token": 1e-7, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": false + "supports_tool_choice": true, + "supports_vision": true }, - "ovhcloud/Qwen2.5-VL-72B-Instruct": { - "input_cost_per_token": 9.1e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "mistral/ministral-3-8b-2512": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 9.1e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct", - "supports_function_calling": false, + "output_cost_per_token": 1.5e-7, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": false, + "supports_tool_choice": true, "supports_vision": true }, - "ovhcloud/Qwen3-32B": { - "input_cost_per_token": 8e-8, - "litellm_provider": "ovhcloud", + "mistral/mistral-large-2402": { + "input_cost_per_token": 0.000004, + "litellm_provider": "mistral", "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.3e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b", + "output_cost_per_token": 0.000012, + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "ovhcloud/gpt-oss-120b": { - "input_cost_per_token": 8e-8, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, + "mistral/mistral-large-2407": { + "input_cost_per_token": 0.000003, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b", - "supports_function_calling": false, - "supports_reasoning": true, + "output_cost_per_token": 0.000009, + "supports_assistant_prefill": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": false + "supports_tool_choice": true }, - "ovhcloud/gpt-oss-20b": { - "input_cost_per_token": 4e-8, - "litellm_provider": "ovhcloud", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, + "mistral/mistral-large-2411": { + "input_cost_per_token": 0.000002, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b", - "supports_function_calling": false, - "supports_reasoning": true, + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": false + "supports_tool_choice": true }, - "ovhcloud/llava-v1.6-mistral-7b-hf": { - "input_cost_per_token": 2.9e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "mistral/mistral-large-2512": { + "input_cost_per_token": 5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.9e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b", - "supports_function_calling": false, + "output_cost_per_token": 0.0000015, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": false, + "supports_tool_choice": true, "supports_vision": true }, - "ovhcloud/mamba-codestral-7B-v0.1": { - "input_cost_per_token": 1.9e-7, - "litellm_provider": "ovhcloud", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "mistral/mistral-large-3": { + "input_cost_per_token": 5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.9e-7, - "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1", - "supports_function_calling": false, + "output_cost_per_token": 0.0000015, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": false - }, - "palm/chat-bison": { - "input_cost_per_token": 1.25e-7, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + "supports_tool_choice": true, + "supports_vision": true }, - "palm/chat-bison-001": { - "input_cost_per_token": 1.25e-7, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "mistral/mistral-large-latest": { + "input_cost_per_token": 5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.25e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + "output_cost_per_token": 0.0000015, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "perplexity/codellama-34b-instruct": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "perplexity", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "mistral/mistral-medium": { + "input_cost_per_token": 0.0000027, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.0000014 + "output_cost_per_token": 0.0000081, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/codellama-70b-instruct": { - "input_cost_per_token": 7e-7, - "litellm_provider": "perplexity", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "mistral/mistral-medium-2312": { + "input_cost_per_token": 0.0000027, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.0000028 + "output_cost_per_token": 0.0000081, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/llama-2-70b-chat": { - "input_cost_per_token": 7e-7, - "litellm_provider": "perplexity", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "mistral/mistral-medium-2505": { + "input_cost_per_token": 4e-7, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.0000028 + "output_cost_per_token": 0.000002, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/llama-3.1-70b-instruct": { - "input_cost_per_token": 0.000001, - "litellm_provider": "perplexity", + "mistral/mistral-medium-3-1-2508": { + "input_cost_per_token": 4e-7, + "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000001 + "output_cost_per_token": 0.000002, + "source": "https://mistral.ai/news/mistral-medium-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "perplexity/llama-3.1-8b-instruct": { - "input_cost_per_token": 2e-7, - "litellm_provider": "perplexity", + "mistral/mistral-medium-latest": { + "input_cost_per_token": 4e-7, + "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-7 + "output_cost_per_token": 0.000002, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "perplexity/llama-3.1-sonar-huge-128k-online": { - "deprecation_date": "2025-02-22", - "input_cost_per_token": 0.000005, - "litellm_provider": "perplexity", - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "max_tokens": 127072, + "mistral/mistral-small": { + "input_cost_per_token": 1e-7, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.000005 - }, - "perplexity/llama-3.1-sonar-large-128k-chat": { - "deprecation_date": "2025-02-22", - "input_cost_per_token": 0.000001, - "litellm_provider": "perplexity", + "output_cost_per_token": 3e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-small-3-2-2506": { + "input_cost_per_token": 6e-8, + "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000001 - }, - "perplexity/llama-3.1-sonar-large-128k-online": { - "deprecation_date": "2025-02-22", - "input_cost_per_token": 0.000001, - "litellm_provider": "perplexity", - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "max_tokens": 127072, - "mode": "chat", - "output_cost_per_token": 0.000001 + "output_cost_per_token": 1.8e-7, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "perplexity/llama-3.1-sonar-small-128k-chat": { - "deprecation_date": "2025-02-22", - "input_cost_per_token": 2e-7, - "litellm_provider": "perplexity", + "mistral/mistral-small-latest": { + "input_cost_per_token": 6e-8, + "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-7 + "output_cost_per_token": 1.8e-7, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "perplexity/llama-3.1-sonar-small-128k-online": { - "deprecation_date": "2025-02-22", - "input_cost_per_token": 2e-7, - "litellm_provider": "perplexity", - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "max_tokens": 127072, + "mistral/mistral-tiny": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2e-7 + "output_cost_per_token": 2.5e-7, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/mistral-7b-instruct": { - "input_cost_per_token": 7e-8, - "litellm_provider": "perplexity", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "mistral/open-codestral-mamba": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 2.8e-7 + "output_cost_per_token": 2.5e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true }, - "perplexity/mixtral-8x7b-instruct": { - "input_cost_per_token": 7e-8, - "litellm_provider": "perplexity", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "mistral/open-mistral-7b": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.8e-7 + "output_cost_per_token": 2.5e-7, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/pplx-70b-chat": { - "input_cost_per_token": 7e-7, - "litellm_provider": "perplexity", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "mistral/open-mistral-nemo": { + "input_cost_per_token": 3e-7, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000028 + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/pplx-70b-online": { - "input_cost_per_request": 0.005, - "input_cost_per_token": 0, - "litellm_provider": "perplexity", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "mistral/open-mistral-nemo-2407": { + "input_cost_per_token": 3e-7, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000028 + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/pplx-7b-chat": { - "input_cost_per_token": 7e-8, - "litellm_provider": "perplexity", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "mistral/open-mixtral-8x22b": { + "input_cost_per_token": 0.000002, + "litellm_provider": "mistral", + "max_input_tokens": 65336, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.8e-7 + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/pplx-7b-online": { - "input_cost_per_request": 0.005, - "input_cost_per_token": 0, - "litellm_provider": "perplexity", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "mistral/open-mixtral-8x7b": { + "input_cost_per_token": 7e-7, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.8e-7 + "output_cost_per_token": 7e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "perplexity/sonar": { - "input_cost_per_token": 0.000001, - "litellm_provider": "perplexity", + "mistral/pixtral-12b-2409": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "mistral", "max_input_tokens": 128000, + "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000001, - "search_context_cost_per_query": { - "search_context_size_high": 0.012, - "search_context_size_low": 0.005, - "search_context_size_medium": 0.008 - }, - "supports_web_search": true + "output_cost_per_token": 1.5e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "perplexity/sonar-deep-research": { - "citation_cost_per_token": 0.000002, + "mistral/pixtral-large-2411": { "input_cost_per_token": 0.000002, - "litellm_provider": "perplexity", + "litellm_provider": "mistral", "max_input_tokens": 128000, + "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_reasoning_token": 0.000003, - "output_cost_per_token": 0.000008, - "search_context_cost_per_query": { - "search_context_size_high": 0.005, - "search_context_size_low": 0.005, - "search_context_size_medium": 0.005 - }, + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/pixtral-large-latest": { + "input_cost_per_token": 0.000002, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot.kimi-k2-thinking": { + "input_cost_per_token": 6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000025, "supports_reasoning": true, - "supports_web_search": true + "supports_system_messages": true }, - "perplexity/sonar-medium-chat": { + "moonshot/kimi-k2-0711-preview": { + "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, - "litellm_provider": "perplexity", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000018 + "output_cost_per_token": 0.0000025, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true }, - "perplexity/sonar-medium-online": { - "input_cost_per_request": 0.005, - "input_cost_per_token": 0, - "litellm_provider": "perplexity", - "max_input_tokens": 12000, - "max_output_tokens": 12000, - "max_tokens": 12000, + "moonshot/kimi-k2-0905-preview": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.0000018 + "output_cost_per_token": 0.0000025, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true }, - "perplexity/sonar-pro": { - "input_cost_per_token": 0.000003, - "litellm_provider": "perplexity", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "moonshot/kimi-k2-thinking": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.014, - "search_context_size_low": 0.006, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 0.0000025, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, "supports_web_search": true }, - "perplexity/sonar-reasoning": { - "input_cost_per_token": 0.000001, - "litellm_provider": "perplexity", - "max_input_tokens": 128000, - "max_tokens": 128000, + "moonshot/kimi-k2-thinking-turbo": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.00000115, + "litellm_provider": "moonshot", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.000005, - "search_context_cost_per_query": { - "search_context_size_high": 0.014, - "search_context_size_low": 0.005, - "search_context_size_medium": 0.008 - }, - "supports_reasoning": true, + "output_cost_per_token": 0.000008, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, "supports_web_search": true }, - "perplexity/sonar-reasoning-pro": { - "input_cost_per_token": 0.000002, - "litellm_provider": "perplexity", - "max_input_tokens": 128000, - "max_tokens": 128000, + "moonshot/kimi-k2-turbo-preview": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.00000115, + "litellm_provider": "moonshot", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000008, - "search_context_cost_per_query": { - "search_context_size_high": 0.014, - "search_context_size_low": 0.006, - "search_context_size_medium": 0.01 - }, - "supports_reasoning": true, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, "supports_web_search": true }, - "perplexity/sonar-small-chat": { - "input_cost_per_token": 7e-8, - "litellm_provider": "perplexity", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "moonshot/kimi-k2.5": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.8e-7 + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "perplexity/sonar-small-online": { - "input_cost_per_request": 0.005, - "input_cost_per_token": 0, - "litellm_provider": "perplexity", - "max_input_tokens": 12000, - "max_output_tokens": 12000, - "max_tokens": 12000, + "moonshot/kimi-latest": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.8e-7 + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "publicai/swiss-ai/apertus-8b-instruct": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "moonshot/kimi-latest-128k": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", - "supports_function_calling": false, - "supports_tool_choice": false + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "publicai/swiss-ai/apertus-70b-instruct": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "moonshot/kimi-latest-32k": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", - "supports_function_calling": false, - "supports_tool_choice": false + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", + "moonshot/kimi-latest-8k": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 2e-7, + "litellm_provider": "moonshot", "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, - "publicai/BSC-LT/salamandra-7b-instruct-tools-16k": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, + "moonshot/kimi-thinking-preview": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", + "output_cost_per_token": 0.0000025, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_vision": true + }, + "moonshot/moonshot-v1-128k": { + "input_cost_per_token": 0.000002, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true }, - "publicai/BSC-LT/ALIA-40b-instruct_Q8_0": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "moonshot/moonshot-v1-128k-0430": { + "input_cost_per_token": 0.000002, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true }, - "publicai/allenai/Olmo-3-7B-Instruct": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, + "moonshot/moonshot-v1-128k-vision-preview": { + "input_cost_per_token": 0.000002, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, - "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", + "moonshot/moonshot-v1-32k": { + "input_cost_per_token": 0.000001, + "litellm_provider": "moonshot", "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true }, - "publicai/allenai/Olmo-3-7B-Think": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", + "moonshot/moonshot-v1-32k-0430": { + "input_cost_per_token": 0.000001, + "litellm_provider": "moonshot", "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true + "supports_tool_choice": true }, - "publicai/allenai/Olmo-3-32B-Think": { - "input_cost_per_token": 0, - "litellm_provider": "publicai", + "moonshot/moonshot-v1-32k-vision-preview": { + "input_cost_per_token": 0.000001, + "litellm_provider": "moonshot", "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://platform.publicai.co/docs", + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, - "supports_reasoning": true + "supports_vision": true }, - "qwen.qwen3-coder-480b-a35b-v1:0": { - "input_cost_per_token": 2.2e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 262000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "moonshot/moonshot-v1-8k": { + "input_cost_per_token": 2e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000018, + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true }, - "qwen.qwen3-235b-a22b-2507-v1:0": { - "input_cost_per_token": 2.2e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "moonshot/moonshot-v1-8k-0430": { + "input_cost_per_token": 2e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8.8e-7, + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true }, - "qwen.qwen3-coder-30b-a3b-v1:0": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, + "moonshot/moonshot-v1-8k-vision-preview": { + "input_cost_per_token": 2e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-auto": { + "input_cost_per_token": 0.000002, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true }, - "qwen.qwen3-32b-v1:0": { - "input_cost_per_token": 1.5e-7, + "moonshotai.kimi-k2.5": { + "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_token": 0.000003, "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "qwen.qwen3-next-80b-a3b": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "morph/morph-v3-fast": { + "input_cost_per_token": 8e-7, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 0.0000012, - "supports_function_calling": true, - "supports_system_messages": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false }, - "qwen.qwen3-vl-235b-a22b": { - "input_cost_per_token": 5.3e-7, - "litellm_provider": "bedrock_converse", + "morph/morph-v3-large": { + "input_cost_per_token": 9e-7, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 0.0000019, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false + }, + "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { + "max_tokens": 128000, "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.00000266, "supports_function_calling": true, - "supports_system_messages": true, - "supports_vision": true + "source": "https://nebius.com/prices-ai-studio" }, - "qwen.qwen3-coder-next": { - "input_cost_per_token": 5e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/Qwen/QwQ-32B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 4.5e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.0000012, "supports_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-2-13b": { - "input_cost_per_token": 1e-7, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen2-VL-72B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 5e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-2-13b-chat": { - "input_cost_per_token": 1e-7, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen2-VL-7B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-8, + "output_cost_per_token": 6e-8, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 5e-7, - "supports_tool_choice": true + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-2-70b": { - "input_cost_per_token": 6.5e-7, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen2.5-32B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 2e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.00000275, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-2-70b-chat": { - "input_cost_per_token": 6.5e-7, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen2.5-72B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.00000275, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-2-7b": { - "input_cost_per_token": 5e-8, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen2.5-Coder-7B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-8, + "output_cost_per_token": 3e-8, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-2-7b-chat": { - "input_cost_per_token": 5e-8, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-3-70b": { - "input_cost_per_token": 6.5e-7, - "litellm_provider": "replicate", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/Qwen/Qwen3-14B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 2.4e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.00000275, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-3-70b-instruct": { - "input_cost_per_token": 6.5e-7, - "litellm_provider": "replicate", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "nebius/Qwen/Qwen3-235B-A22B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.00000275, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-3-8b": { - "input_cost_per_token": 5e-8, - "litellm_provider": "replicate", - "max_input_tokens": 8086, - "max_output_tokens": 8086, - "max_tokens": 8086, + "nebius/Qwen/Qwen3-30B-A3B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/meta/llama-3-8b-instruct": { - "input_cost_per_token": 5e-8, - "litellm_provider": "replicate", - "max_input_tokens": 8086, - "max_output_tokens": 8086, - "max_tokens": 8086, + "nebius/Qwen/Qwen3-32B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/mistralai/mistral-7b-instruct-v0.2": { - "input_cost_per_token": 5e-8, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/Qwen/Qwen3-4B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 2.4e-7, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/mistralai/mistral-7b-v0.1": { - "input_cost_per_token": 5e-8, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/deepseek-ai/DeepSeek-R1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 8e-7, + "output_cost_per_token": 0.0000024, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_tool_choice": true + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { - "input_cost_per_token": 3e-7, - "litellm_provider": "replicate", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "nebius/deepseek-ai/DeepSeek-R1-0528": { + "max_tokens": 164000, + "max_input_tokens": 164000, + "max_output_tokens": 164000, + "input_cost_per_token": 8e-7, + "output_cost_per_token": 0.0000024, + "litellm_provider": "nebius", "mode": "chat", - "output_cost_per_token": 0.000001, - "supports_tool_choice": true + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/openai/gpt-5": { - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.00001, - "litellm_provider": "replicate", + "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 7.5e-7, + "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true + "source": "https://nebius.com/prices-ai-studio" }, - "replicateopenai/gpt-oss-20b": { - "input_cost_per_token": 9e-8, - "output_cost_per_token": 3.6e-7, - "litellm_provider": "replicate", + "nebius/deepseek-ai/DeepSeek-V3": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.0000015, + "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "supports_system_messages": true + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/anthropic/claude-4.5-haiku": { - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000005, - "litellm_provider": "replicate", + "nebius/deepseek-ai/DeepSeek-V3-0324": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.0000015, + "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/ibm-granite/granite-3.3-8b-instruct": { - "input_cost_per_token": 3e-8, - "output_cost_per_token": 2.5e-7, - "litellm_provider": "replicate", + "nebius/google/gemma-3-27b-it": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 2e-7, + "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "supports_system_messages": true + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/openai/gpt-4o": { - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.00001, - "litellm_provider": "replicate", + "nebius/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_audio_input": true, - "supports_audio_output": true + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/openai/o4-mini": { + "nebius/meta-llama/Llama-Guard-3-8B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-8, + "output_cost_per_token": 6e-8, + "litellm_provider": "nebius", + "mode": "chat", + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000004, - "output_cost_per_reasoning_token": 0.000004, - "litellm_provider": "replicate", + "output_cost_per_token": 0.000003, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "nebius", "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/openai/o1-mini": { - "input_cost_per_token": 0.0000011, - "output_cost_per_token": 0.0000044, - "output_cost_per_reasoning_token": 0.0000044, - "litellm_provider": "replicate", + "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-8, + "output_cost_per_token": 6e-8, + "litellm_provider": "nebius", "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/openai/o1": { - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.00006, - "output_cost_per_reasoning_token": 0.00006, - "litellm_provider": "replicate", + "nebius/mistralai/Mistral-Nemo-Instruct-2407": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 1.2e-7, + "litellm_provider": "nebius", "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/openai/gpt-4o-mini": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "replicate", + "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000018, + "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/qwen/qwen3-235b-a22b-instruct-2507": { - "input_cost_per_token": 2.64e-7, - "output_cost_per_token": 0.00000106, - "litellm_provider": "replicate", + "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "supports_system_messages": true + "source": "https://nebius.com/prices-ai-studio" }, - "replicate/anthropic/claude-4-sonnet": { - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "litellm_provider": "replicate", + "novita/Sao10K/L3-8B-Stheno-v3.2": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 5e-8, + "output_cost_per_token": 5e-8, + "max_input_tokens": 8192, + "max_output_tokens": 32000, + "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true + "supports_system_messages": true }, - "replicate/deepseek-ai/deepseek-v3": { - "input_cost_per_token": 0.00000145, - "output_cost_per_token": 0.00000145, - "litellm_provider": "replicate", + "novita/baichuan/baichuan-m2-32b": { + "litellm_provider": "novita", "mode": "chat", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_function_calling": true, + "input_cost_per_token": 7e-8, + "output_cost_per_token": 7e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "supports_system_messages": true }, - "replicate/anthropic/claude-3.7-sonnet": { - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "litellm_provider": "replicate", + "novita/baidu/ernie-4.5-21B-a3b": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 7e-8, + "output_cost_per_token": 2.8e-7, + "max_input_tokens": 120000, + "max_output_tokens": 8000, + "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true + "supports_system_messages": true }, - "replicate/anthropic/claude-3.5-haiku": { - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000005, - "litellm_provider": "replicate", + "novita/baidu/ernie-4.5-21B-a3b-thinking": { + "litellm_provider": "novita", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, + "input_cost_per_token": 7e-8, + "output_cost_per_token": 2.8e-7, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true + "supports_reasoning": true }, - "replicate/anthropic/claude-3.5-sonnet": { - "input_cost_per_token": 0.00000375, - "output_cost_per_token": 0.00001875, - "litellm_provider": "replicate", + "novita/baidu/ernie-4.5-300b-a47b-paddle": { + "litellm_provider": "novita", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, + "input_cost_per_token": 2.8e-7, + "output_cost_per_token": 0.0000011, + "max_input_tokens": 123000, + "max_output_tokens": 12000, + "max_tokens": 12000, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true + "supports_system_messages": true, + "supports_response_schema": true }, - "replicate/google/gemini-3-pro": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000012, - "litellm_provider": "replicate", + "novita/baidu/ernie-4.5-vl-28b-a3b": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 5.6e-7, + "max_input_tokens": 30000, + "max_output_tokens": 8000, + "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true + "supports_reasoning": true }, - "replicate/anthropic/claude-4.5-sonnet": { - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "litellm_provider": "replicate", + "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 3.9e-7, + "output_cost_per_token": 3.9e-7, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, - "supports_tool_choice": true, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_reasoning": true }, - "replicate/openai/gpt-4.1": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000008, - "litellm_provider": "replicate", + "novita/baidu/ernie-4.5-vl-424b-a47b": { + "litellm_provider": "novita", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "input_cost_per_token": 4.2e-7, + "output_cost_per_token": 0.00000125, + "max_input_tokens": 123000, + "max_output_tokens": 16000, + "max_tokens": 16000, "supports_vision": true, "supports_system_messages": true, + "supports_reasoning": true + }, + "novita/deepseek/deepseek-ocr": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 3e-8, + "output_cost_per_token": 3e-8, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, "supports_response_schema": true }, - "replicate/openai/gpt-4.1-nano": { - "input_cost_per_token": 1e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "replicate", + "novita/deepseek/deepseek-prover-v2-671b": { + "litellm_provider": "novita", "mode": "chat", - "supports_function_calling": true, + "input_cost_per_token": 7e-7, + "output_cost_per_token": 0.0000025, + "max_input_tokens": 160000, + "max_output_tokens": 160000, + "max_tokens": 160000, "supports_system_messages": true }, - "replicate/openai/gpt-4.1-mini": { - "input_cost_per_token": 4e-7, - "output_cost_per_token": 0.0000016, - "litellm_provider": "replicate", + "novita/deepseek/deepseek-r1-0528": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 7e-7, + "output_cost_per_token": 0.0000025, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true, + "cache_read_input_token_cost": 3.5e-7, + "input_cost_per_token_cache_hit": 3.5e-7, + "supports_reasoning": true + }, + "novita/deepseek/deepseek-r1-0528-qwen3-8b": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 6e-8, + "output_cost_per_token": 9e-8, + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 32000, "supports_system_messages": true, + "supports_reasoning": true + }, + "novita/deepseek/deepseek-r1-distill-llama-70b": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 8e-7, + "output_cost_per_token": 8e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_tool_choice": true, - "supports_response_schema": true + "supports_system_messages": true, + "supports_response_schema": true, + "supports_reasoning": true }, - "replicate/openai/gpt-5-nano": { - "input_cost_per_token": 5e-8, - "output_cost_per_token": 4e-7, - "litellm_provider": "replicate", + "novita/deepseek/deepseek-r1-distill-qwen-14b": { + "litellm_provider": "novita", "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 1.5e-7, + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true, + "supports_reasoning": true }, - "replicate/openai/gpt-5-mini": { - "input_cost_per_token": 2.5e-7, - "output_cost_per_token": 0.000002, - "litellm_provider": "replicate", + "novita/deepseek/deepseek-r1-distill-qwen-32b": { + "litellm_provider": "novita", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 3e-7, + "max_input_tokens": 64000, + "max_output_tokens": 32000, + "max_tokens": 32000, "supports_tool_choice": true, - "supports_response_schema": true + "supports_system_messages": true, + "supports_response_schema": true, + "supports_reasoning": true }, - "replicate/google/gemini-2.5-flash": { - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "litellm_provider": "replicate", + "novita/deepseek/deepseek-r1-turbo": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 7e-7, + "output_cost_per_token": 0.0000025, + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_response_schema": true - }, - "replicate/openai/gpt-oss-120b": { - "input_cost_per_token": 1.8e-7, - "output_cost_per_token": 7.2e-7, - "litellm_provider": "replicate", - "mode": "chat", - "supports_function_calling": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_reasoning": true }, - "replicate/deepseek-ai/deepseek-v3.1": { - "input_cost_per_token": 6.72e-7, - "output_cost_per_token": 0.000002016, - "litellm_provider": "replicate", + "novita/deepseek/deepseek-v3-0324": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.00000112, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_function_calling": true, - "supports_reasoning": true, - "supports_system_messages": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true, + "cache_read_input_token_cost": 1.35e-7, + "input_cost_per_token_cache_hit": 1.35e-7 }, - "replicate/xai/grok-4": { - "input_cost_per_token": 0.0000072, - "output_cost_per_token": 0.000036, - "litellm_provider": "replicate", + "novita/deepseek/deepseek-v3-turbo": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.0000013, + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_system_messages": true }, - "replicate/deepseek-ai/deepseek-r1": { - "input_cost_per_token": 0.00000375, - "output_cost_per_token": 0.00001, - "output_cost_per_reasoning_token": 0.00001, - "litellm_provider": "replicate", - "mode": "chat", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_reasoning": true, - "supports_system_messages": true - }, - "sagemaker/meta-textgeneration-llama-2-13b-f": { - "input_cost_per_token": 0, - "litellm_provider": "sagemaker", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0 - }, - "sagemaker/meta-textgeneration-llama-2-70b-b-f": { - "input_cost_per_token": 0, - "litellm_provider": "sagemaker", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0 - }, - "sagemaker/meta-textgeneration-llama-2-7b-f": { - "input_cost_per_token": 0, - "litellm_provider": "sagemaker", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "novita/deepseek/deepseek-v3.1": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0 - }, - "sambanova/DeepSeek-R1": { - "input_cost_per_token": 0.000005, - "litellm_provider": "sambanova", - "max_input_tokens": 32768, + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.000001, + "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.000007, - "source": "https://cloud.sambanova.ai/plans/pricing" + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true, + "cache_read_input_token_cost": 1.35e-7, + "input_cost_per_token_cache_hit": 1.35e-7, + "supports_reasoning": true }, - "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "input_cost_per_token": 7e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "novita/deepseek/deepseek-v3.1-terminus": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.0000014, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-V3-0324": { - "input_cost_per_token": 0.000003, - "litellm_provider": "sambanova", - "max_input_tokens": 32768, + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.000001, + "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0000045, - "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true, + "cache_read_input_token_cost": 1.35e-7, + "input_cost_per_token_cache_hit": 1.35e-7, + "supports_reasoning": true }, - "sambanova/Llama-4-Maverick-17B-128E-Instruct": { - "input_cost_per_token": 6.3e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - }, + "novita/deepseek/deepseek-v3.2": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.0000018, - "source": "https://cloud.sambanova.ai/plans/pricing", + "input_cost_per_token": 2.69e-7, + "output_cost_per_token": 4e-7, + "max_input_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_system_messages": true, + "supports_response_schema": true, + "cache_read_input_token_cost": 1.345e-7, + "input_cost_per_token_cache_hit": 1.345e-7, + "supports_reasoning": true }, - "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 4e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - }, + "novita/deepseek/deepseek-v3.2-exp": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 7e-7, - "source": "https://cloud.sambanova.ai/plans/pricing", + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 4.1e-7, + "max_input_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "input_cost_per_token": 0.000005, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "novita/google/gemma-3-12b-it": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.00001, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "input_cost_per_token": 5e-8, + "output_cost_per_token": 1e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "input_cost_per_token": 1e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "novita/google/gemma-3-27b-it": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 1.19e-7, "output_cost_per_token": 2e-7, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.2-1B-Instruct": { - "input_cost_per_token": 4e-8, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, + "max_input_tokens": 98304, "max_output_tokens": 16384, "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8e-8, - "source": "https://cloud.sambanova.ai/plans/pricing" + "supports_vision": true, + "supports_system_messages": true }, - "sambanova/Meta-Llama-3.2-3B-Instruct": { - "input_cost_per_token": 8e-8, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "novita/gryphe/mythomax-l2-13b": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 1.6e-7, - "source": "https://cloud.sambanova.ai/plans/pricing" + "input_cost_per_token": 9e-8, + "output_cost_per_token": 9e-8, + "max_input_tokens": 4096, + "max_output_tokens": 3200, + "max_tokens": 3200, + "supports_system_messages": true }, - "sambanova/Meta-Llama-3.3-70B-Instruct": { - "input_cost_per_token": 6e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "novita/kwaipilot/kat-coder-pro": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, - "source": "https://cloud.sambanova.ai/plans/pricing", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-Guard-3-8B": { - "input_cost_per_token": 3e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://cloud.sambanova.ai/plans/pricing" + "cache_read_input_token_cost": 6e-8, + "input_cost_per_token_cache_hit": 6e-8 }, - "sambanova/QwQ-32B": { - "input_cost_per_token": 5e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "novita/meta-llama/llama-3-70b-instruct": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.000001, - "source": "https://cloud.sambanova.ai/plans/pricing" + "input_cost_per_token": 5.1e-7, + "output_cost_per_token": 7.4e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "sambanova/Qwen2-Audio-7B-Instruct": { - "input_cost_per_token": 5e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "novita/meta-llama/llama-3-8b-instruct": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.0001, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_audio_input": true - }, - "sambanova/Qwen3-32B": { - "input_cost_per_token": 4e-7, - "litellm_provider": "sambanova", + "input_cost_per_token": 4e-8, + "output_cost_per_token": 4e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, + "supports_system_messages": true + }, + "novita/meta-llama/llama-3.1-8b-instruct": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 8e-7, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "input_cost_per_token": 2e-8, + "output_cost_per_token": 5e-8, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "supports_system_messages": true }, - "sambanova/DeepSeek-V3.1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.0000045, - "litellm_provider": "sambanova", + "novita/meta-llama/llama-3.2-3b-instruct": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 3e-8, + "output_cost_per_token": 5e-8, + "max_input_tokens": 32768, + "max_output_tokens": 32000, + "max_tokens": 32000, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://cloud.sambanova.ai/plans/pricing" + "supports_system_messages": true }, - "sambanova/gpt-oss-120b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.0000045, - "litellm_provider": "sambanova", + "novita/meta-llama/llama-3.3-70b-instruct": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 1.35e-7, + "output_cost_per_token": 4e-7, + "max_input_tokens": 131072, + "max_output_tokens": 120000, + "max_tokens": 120000, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "snowflake/claude-3-5-sonnet": { - "litellm_provider": "snowflake", - "max_input_tokens": 18000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_computer_use": true + "supports_system_messages": true }, - "snowflake/deepseek-r1": { - "litellm_provider": "snowflake", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { + "litellm_provider": "novita", "mode": "chat", - "supports_reasoning": true - }, - "snowflake/gemma-7b": { - "litellm_provider": "snowflake", - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" - }, - "snowflake/jamba-1.5-large": { - "litellm_provider": "snowflake", - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" - }, - "snowflake/jamba-1.5-mini": { - "litellm_provider": "snowflake", - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" - }, - "snowflake/jamba-instruct": { - "litellm_provider": "snowflake", - "max_input_tokens": 256000, + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 8.5e-7, + "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat" + "supports_vision": true, + "supports_system_messages": true }, - "snowflake/llama2-70b-chat": { - "litellm_provider": "snowflake", - "max_input_tokens": 4096, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/meta-llama/llama-4-scout-17b-16e-instruct": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 1.8e-7, + "output_cost_per_token": 5.9e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "supports_vision": true, + "supports_system_messages": true }, - "snowflake/llama3-70b": { - "litellm_provider": "snowflake", - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/microsoft/wizardlm-2-8x22b": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 6.2e-7, + "output_cost_per_token": 6.2e-7, + "max_input_tokens": 65535, + "max_output_tokens": 8000, + "max_tokens": 8000, + "supports_system_messages": true }, - "snowflake/llama3-8b": { - "litellm_provider": "snowflake", - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/minimax/minimax-m2": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token_cache_hit": 3e-8, + "supports_reasoning": true }, - "snowflake/llama3.1-405b": { - "litellm_provider": "snowflake", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/minimax/minimax-m2.1": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token_cache_hit": 3e-8 }, - "snowflake/llama3.1-70b": { - "litellm_provider": "snowflake", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/minimaxai/minimax-m1-80k": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 5.5e-7, + "output_cost_per_token": 0.0000022, + "max_input_tokens": 1000000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_reasoning": true }, - "snowflake/llama3.1-8b": { - "litellm_provider": "snowflake", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/mistralai/mistral-nemo": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 4e-8, + "output_cost_per_token": 1.7e-7, + "max_input_tokens": 60288, + "max_output_tokens": 16000, + "max_tokens": 16000, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "snowflake/llama3.2-1b": { - "litellm_provider": "snowflake", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/moonshotai/kimi-k2-0905": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000025, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "snowflake/llama3.2-3b": { - "litellm_provider": "snowflake", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/moonshotai/kimi-k2-instruct": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 5.7e-7, + "output_cost_per_token": 0.0000023, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "snowflake/llama3.3-70b": { - "litellm_provider": "snowflake", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/moonshotai/kimi-k2-thinking": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000025, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true, + "supports_reasoning": true }, - "snowflake/mistral-7b": { - "litellm_provider": "snowflake", - "max_input_tokens": 32000, + "novita/nousresearch/hermes-2-pro-llama-3-8b": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 1.4e-7, + "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat" + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "snowflake/mistral-large": { - "litellm_provider": "snowflake", - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/openai/gpt-oss-120b": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 5e-8, + "output_cost_per_token": 2.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true, + "supports_reasoning": true }, - "snowflake/mistral-large2": { - "litellm_provider": "snowflake", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/openai/gpt-oss-20b": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 4e-8, + "output_cost_per_token": 1.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true, + "supports_reasoning": true }, - "snowflake/mixtral-8x7b": { - "litellm_provider": "snowflake", - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/paddlepaddle/paddleocr-vl": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 2e-8, + "output_cost_per_token": 2e-8, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "supports_vision": true, + "supports_system_messages": true }, - "snowflake/reka-core": { - "litellm_provider": "snowflake", + "novita/qwen/qwen-2.5-72b-instruct": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 4e-7, "max_input_tokens": 32000, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat" + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "snowflake/reka-flash": { - "litellm_provider": "snowflake", - "max_input_tokens": 100000, + "novita/qwen/qwen-mt-plus": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 7.5e-7, + "max_input_tokens": 16384, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat" + "supports_system_messages": true }, - "snowflake/snowflake-arctic": { - "litellm_provider": "snowflake", - "max_input_tokens": 4096, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/qwen/qwen2.5-7b-instruct": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 7e-8, + "output_cost_per_token": 7e-8, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "snowflake/snowflake-llama-3.1-405b": { - "litellm_provider": "snowflake", - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/qwen/qwen2.5-vl-72b-instruct": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 8e-7, + "output_cost_per_token": 8e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "supports_vision": true, + "supports_system_messages": true }, - "snowflake/snowflake-llama-3.3-70b": { - "litellm_provider": "snowflake", - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "novita/qwen/qwen3-235b-a22b-fp8": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 2e-7, + "output_cost_per_token": 8e-7, + "max_input_tokens": 40960, + "max_output_tokens": 20000, + "max_tokens": 20000, + "supports_system_messages": true, + "supports_reasoning": true }, - "together-ai-21.1b-41b": { - "input_cost_per_token": 8e-7, - "litellm_provider": "together_ai", + "novita/qwen/qwen3-235b-a22b-instruct-2507": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 8e-7 + "input_cost_per_token": 9e-8, + "output_cost_per_token": 5.8e-7, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together-ai-4.1b-8b": { - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", + "novita/qwen/qwen3-235b-a22b-thinking-2507": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 2e-7 + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_reasoning": true }, - "together-ai-41.1b-80b": { - "input_cost_per_token": 9e-7, - "litellm_provider": "together_ai", + "novita/qwen/qwen3-30b-a3b-fp8": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 9e-7 + "input_cost_per_token": 9e-8, + "output_cost_per_token": 4.5e-7, + "max_input_tokens": 40960, + "max_output_tokens": 20000, + "max_tokens": 20000, + "supports_system_messages": true, + "supports_reasoning": true }, - "together-ai-8.1b-21b": { - "input_cost_per_token": 3e-7, - "litellm_provider": "together_ai", - "max_tokens": 1000, + "novita/qwen/qwen3-32b-fp8": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 3e-7 + "input_cost_per_token": 1e-7, + "output_cost_per_token": 4.5e-7, + "max_input_tokens": 40960, + "max_output_tokens": 20000, + "max_tokens": 20000, + "supports_system_messages": true, + "supports_reasoning": true }, - "together-ai-81.1b-110b": { - "input_cost_per_token": 0.0000018, - "litellm_provider": "together_ai", + "novita/qwen/qwen3-4b-fp8": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.0000018 + "input_cost_per_token": 3e-8, + "output_cost_per_token": 3e-8, + "max_input_tokens": 128000, + "max_output_tokens": 20000, + "max_tokens": 20000, + "supports_system_messages": true, + "supports_reasoning": true }, - "together-ai-up-to-4b": { - "input_cost_per_token": 1e-7, - "litellm_provider": "together_ai", + "novita/qwen/qwen3-8b-fp8": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 1e-7 + "input_cost_per_token": 3.5e-8, + "output_cost_per_token": 1.38e-7, + "max_input_tokens": 128000, + "max_output_tokens": 20000, + "max_tokens": 20000, + "supports_system_messages": true, + "supports_reasoning": true }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "litellm_provider": "together_ai", + "novita/qwen/qwen3-coder-30b-a3b-instruct": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 7e-8, + "output_cost_per_token": 2.7e-7, + "max_input_tokens": 160000, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { - "litellm_provider": "together_ai", + "novita/qwen/qwen3-coder-480b-a35b-instruct": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000013, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 262000, + "novita/qwen/qwen3-max": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.000006, - "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", + "input_cost_per_token": 0.00000211, + "output_cost_per_token": 0.00000845, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "input_cost_per_token": 6.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, + "novita/qwen/qwen3-next-80b-a3b-instruct": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 0.0000015, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_tool_choice": false + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "input_cost_per_token": 0.000002, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, + "novita/qwen/qwen3-next-80b-a3b-thinking": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 0.0000015, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true }, - "together_ai/deepseek-ai/DeepSeek-R1": { - "input_cost_per_token": 0.000003, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "max_tokens": 20480, + "novita/qwen/qwen3-omni-30b-a3b-instruct": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.000007, + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 9.7e-7, + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_audio_input": true, + "supports_audio_output": true }, - "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "input_cost_per_token": 5.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "novita/qwen/qwen3-omni-30b-a3b-thinking": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.00000219, - "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 9.7e-7, + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_audio_input": true }, - "together_ai/deepseek-ai/DeepSeek-V3": { - "input_cost_per_token": 0.00000125, - "litellm_provider": "together_ai", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, + "novita/qwen/qwen3-vl-235b-a22b-instruct": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.00000125, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000015, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "input_cost_per_token": 6e-7, - "litellm_provider": "together_ai", - "max_tokens": 128000, + "novita/qwen/qwen3-vl-235b-a22b-thinking": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.0000017, - "source": "https://www.together.ai/models/deepseek-v3-1", + "input_cost_per_token": 9.8e-7, + "output_cost_per_token": 0.00000395, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "supports_vision": true, + "supports_system_messages": true, + "supports_reasoning": true + }, + "novita/qwen/qwen3-vl-30b-a3b-instruct": { + "litellm_provider": "novita", + "mode": "chat", + "input_cost_per_token": 2e-7, + "output_cost_per_token": 7e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "litellm_provider": "together_ai", + "novita/qwen/qwen3-vl-30b-a3b-thinking": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 2e-7, + "output_cost_per_token": 0.000001, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-7, - "litellm_provider": "together_ai", + "novita/qwen/qwen3-vl-8b-instruct": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 8.8e-7, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { - "input_cost_per_token": 0, - "litellm_provider": "together_ai", + "novita/sao10k/l3-70b-euryale-v2.1": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0, + "input_cost_per_token": 0.00000148, + "output_cost_per_token": 0.00000148, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_system_messages": true }, - "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 2.7e-7, - "litellm_provider": "together_ai", + "novita/sao10k/l3-8b-lunaris": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 8.5e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "input_cost_per_token": 5e-8, + "output_cost_per_token": 5e-8, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 1.8e-7, - "litellm_provider": "together_ai", + "novita/sao10k/l31-70b-euryale-v2.2": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 5.9e-7, + "input_cost_per_token": 0.00000148, + "output_cost_per_token": 0.00000148, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_system_messages": true }, - "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "input_cost_per_token": 0.0000035, - "litellm_provider": "together_ai", + "novita/skywork/r1v4-lite": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.0000035, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "input_cost_per_token": 2e-7, + "output_cost_per_token": 6e-7, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-7, - "litellm_provider": "together_ai", + "novita/xiaomimimo/mimo-v2-flash": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 8.8e-7, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "max_input_tokens": 262144, + "max_output_tokens": 32000, + "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token_cache_hit": 2e-8, + "supports_reasoning": true }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "input_cost_per_token": 1.8e-7, - "litellm_provider": "together_ai", + "novita/zai-org/autoglm-phone-9b-multilingual": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 1.8e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "input_cost_per_token": 3.5e-8, + "output_cost_per_token": 1.38e-7, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "supports_vision": true, + "supports_system_messages": true }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "litellm_provider": "together_ai", + "novita/zai-org/glm-4.5": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000022, + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_system_messages": true, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token_cache_hit": 1.1e-7, + "supports_reasoning": true }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "litellm_provider": "together_ai", + "novita/zai-org/glm-4.5-air": { + "litellm_provider": "novita", "mode": "chat", + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 8.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_reasoning": true }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 6e-7, - "litellm_provider": "together_ai", + "novita/zai-org/glm-4.5v": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 6e-7, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000018, + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token_cache_hit": 1.1e-7, + "supports_reasoning": true }, - "together_ai/moonshotai/Kimi-K2-Instruct": { - "input_cost_per_token": 0.000001, - "litellm_provider": "together_ai", + "novita/zai-org/glm-4.6": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://www.together.ai/models/kimi-k2-instruct", + "input_cost_per_token": 5.5e-7, + "output_cost_per_token": 0.0000022, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token_cache_hit": 1.1e-7, + "supports_reasoning": true }, - "together_ai/openai/gpt-oss-120b": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "novita/zai-org/glm-4.6v": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://www.together.ai/models/gpt-oss-120b", + "input_cost_per_token": 3e-7, + "output_cost_per_token": 9e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "cache_read_input_token_cost": 5.5e-8, + "input_cost_per_token_cache_hit": 5.5e-8, + "supports_reasoning": true }, - "together_ai/openai/gpt-oss-20b": { - "input_cost_per_token": 5e-8, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "novita/zai-org/glm-4.7": { + "litellm_provider": "novita", "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://www.together.ai/models/gpt-oss-20b", + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000022, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, "supports_response_schema": true, - "supports_tool_choice": true + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token_cache_hit": 1.1e-7, + "supports_reasoning": true + }, + "nscale/Qwen/QwQ-32B": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 6e-8, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/togethercomputer/CodeLlama-34b-Instruct": { - "litellm_provider": "together_ai", + "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { + "input_cost_per_token": 1e-8, + "litellm_provider": "nscale", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 3e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { + "input_cost_per_token": 1e-8, + "litellm_provider": "nscale", "mode": "chat", - "output_cost_per_token": 0.0000011, - "source": "https://www.together.ai/models/glm-4-5-air", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 3e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/zai-org/GLM-4.6": { - "input_cost_per_token": 6e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 3.75e-7, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 0.0000022, - "source": "https://www.together.ai/models/glm-4-6", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "output_cost_per_token": 3.75e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/zai-org/GLM-4.7": { - "input_cost_per_token": 4.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 2.5e-8, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://www.together.ai/models/glm-4-7", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "output_cost_per_token": 2.5e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/moonshotai/Kimi-K2.5": { - "input_cost_per_token": 5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "input_cost_per_token": 9e-8, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 0.0000028, - "source": "https://www.together.ai/models/kimi-k2-5", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_reasoning": true + "output_cost_per_token": 9e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/moonshotai/Kimi-K2-Instruct-0905": { - "input_cost_per_token": 0.000001, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 7e-8, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://www.together.ai/models/kimi-k2-0905", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 7e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { "input_cost_per_token": 1.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 1.5e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 2e-7, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "together_ai/Qwen/Qwen3.5-397B-A17B": { - "input_cost_per_token": 6e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, + "nscale/meta-llama/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-8, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 0.0000036, - "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 3e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "us.amazon.nova-lite-v1:0": { - "input_cost_per_token": 6e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "nscale/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-7, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, "mode": "chat", - "output_cost_per_token": 2.4e-7, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_vision": true + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "us.amazon.nova-micro-v1:0": { - "input_cost_per_token": 3.5e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 9e-8, + "litellm_provider": "nscale", "mode": "chat", - "output_cost_per_token": 1.4e-7, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true + "output_cost_per_token": 2.9e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, - "us.amazon.nova-premier-v1:0": { - "input_cost_per_token": 0.0000025, + "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { + "input_cost_per_token": 6e-7, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000125, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_response_schema": true, + "output_cost_per_token": 6e-7, + "supports_system_messages": true, "supports_vision": true }, - "us.amazon.nova-pro-v1:0": { - "input_cost_per_token": 8e-7, + "nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000032, + "output_cost_per_token": 2.4e-7, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_vision": true + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "us.anthropic.claude-3-5-haiku-20241022-v1:0": { - "cache_creation_input_token_cost": 0.000001, - "cache_read_input_token_cost": 8e-8, - "input_cost_per_token": 8e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, + "nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 6e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000004, - "supports_assistant_prefill": true, + "output_cost_per_token": 2.3e-7, + "supports_system_messages": true + }, + "o1": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00006, "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "us.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.000001375, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "bedrock_converse", + "o1-2024-12-17": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.0000055, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00006, "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_vision": true }, - "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "o1-mini": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, + "output_cost_per_token": 0.0000044, "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 + "supports_prompt_caching": true, + "supports_vision": true }, - "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, + "o1-mini-2024-09-12": { + "deprecation_date": "2025-10-27", + "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, + "output_cost_per_token": 0.000012, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, + "supports_reasoning": true, "supports_vision": true }, - "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock_converse", + "o1-preview": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-preview-2024-09-12": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o3": { + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_flex": 2.5e-7, + "cache_read_input_token_cost_priority": 8.75e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_flex": 0.000001, + "input_cost_per_token_priority": 0.0000035, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000008, + "output_cost_per_token_flex": 0.000004, + "output_cost_per_token_priority": 0.000014, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_service_tier": true, "supports_vision": true }, - "us.anthropic.claude-3-haiku-20240307-v1:0": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "bedrock", + "o3-2025-04-16": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.00000125, + "output_cost_per_token": 0.000008, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-8, - "cache_creation_input_token_cost": 3.125e-7 + "supports_service_tier": true, + "supports_vision": true }, - "us.anthropic.claude-3-opus-20240229-v1:0": { - "input_cost_per_token": 0.000015, - "litellm_provider": "bedrock", + "o3-deep-research": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_token": 0.00001, + "input_cost_per_token_batches": 0.000005, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000075, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00004, + "output_cost_per_token_batches": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 0.0000015, - "cache_creation_input_token_cost": 0.00001875 + "supports_vision": true }, - "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", + "o3-deep-research-2025-06-26": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_token": 0.00001, + "input_cost_per_token_batches": 0.000005, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000015, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00004, + "output_cost_per_token_batches": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 + "supports_vision": true }, - "us.anthropic.claude-opus-4-1-20250805-v1:0": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "bedrock_converse", + "o3-mini": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000044, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": false }, - "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 0.000004125, - "cache_read_input_token_cost": 3.3e-7, - "input_cost_per_token": 0.0000033, - "input_cost_per_token_above_200k_tokens": 0.0000066, - "output_cost_per_token_above_200k_tokens": 0.00002475, - "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, - "litellm_provider": "bedrock_converse", + "o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.0000165, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000044, "supports_function_calling": true, - "supports_pdf_input": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_vision": false }, - "au.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.000001375, - "cache_read_input_token_cost": 1.1e-7, + "o4-mini": { + "cache_read_input_token_cost": 2.75e-7, + "cache_read_input_token_cost_flex": 1.375e-7, + "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token": 0.0000011, - "litellm_provider": "bedrock_converse", + "input_cost_per_token_flex": 5.5e-7, + "input_cost_per_token_priority": 0.000002, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.0000055, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000044, + "output_cost_per_token_flex": 0.0000022, + "output_cost_per_token_priority": 0.000008, "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_service_tier": true, + "supports_vision": true }, - "us.anthropic.claude-opus-4-20250514-v1:0": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "bedrock_converse", + "o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000044, "supports_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_service_tier": true, + "supports_vision": true }, - "us.anthropic.claude-opus-4-5-20251101-v1:0": { - "cache_creation_input_token_cost": 0.000006875, - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000055, - "litellm_provider": "bedrock_converse", + "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.0000275, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, - "global.anthropic.claude-opus-4-5-20251101-v1:0": { - "cache_creation_input_token_cost": 0.00000625, + "o4-mini-deep-research-2025-06-26": { "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "bedrock_converse", + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "openai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "oci/cohere.command-a-03-2025": { + "input_cost_per_token": 0.00000156, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 0.000025, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00000156, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/cohere.command-latest": { + "input_cost_per_token": 0.00000156, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.00000156, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/cohere.command-plus-latest": { + "input_cost_per_token": 0.00000156, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.00000156, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-3.1-405b-instruct": { + "input_cost_per_token": 0.00001068, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.00001068, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-3.2-90b-vision-instruct": { + "input_cost_per_token": 0.000002, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-3.3-70b-instruct": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "oci", + "max_input_tokens": 512000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_response_schema": false }, - "eu.anthropic.claude-opus-4-5-20251101-v1:0": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "oci/meta.llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "oci", + "max_input_tokens": 192000, + "max_output_tokens": 4000, + "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 0.000025, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 7.2e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_response_schema": false }, - "us.anthropic.claude-sonnet-4-20250514-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, + "oci/xai.grok-3": { "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_response_schema": false }, - "us.deepseek.r1-v1:0": { - "input_cost_per_token": 0.00000135, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "oci/xai.grok-3-fast": { + "input_cost_per_token": 0.000005, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000054, - "supports_function_calling": false, - "supports_reasoning": true, - "supports_tool_choice": false + "output_cost_per_token": 0.000025, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false }, - "us.deepseek.v3.2": { - "input_cost_per_token": 6.2e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "oci/xai.grok-3-mini": { + "input_cost_per_token": 3e-7, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000185, + "output_cost_per_token": 5e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": false }, - "eu.deepseek.v3.2": { - "input_cost_per_token": 7.4e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "oci/xai.grok-3-mini-fast": { + "input_cost_per_token": 6e-7, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000222, + "output_cost_per_token": 0.000004, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": false }, - "us.meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 0.00000532, - "litellm_provider": "bedrock", + "oci/xai.grok-4": { + "input_cost_per_token": 0.000003, + "litellm_provider": "oci", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000016, + "output_cost_per_token": 0.000015, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_tool_choice": false + "supports_response_schema": false }, - "us.meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "ollama/codegeex4": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9.9e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0, + "supports_function_calling": false }, - "us.meta.llama3-1-8b-instruct-v1:0": { - "input_cost_per_token": 2.2e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "ollama/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.2e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0, + "supports_function_calling": true }, - "us.meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "ollama/deepseek-coder-v2-lite-instruct": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-7, - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true + "output_cost_per_token": 0, + "supports_function_calling": true }, - "us.meta.llama3-2-1b-instruct-v1:0": { - "input_cost_per_token": 1e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "ollama/deepseek-v3.1:671b-cloud": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 1e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0, + "supports_function_calling": true }, - "us.meta.llama3-2-3b-instruct-v1:0": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "ollama/gpt-oss:120b-cloud": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true + }, + "ollama/gpt-oss:20b-cloud": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true + }, + "ollama/internlm2_5-20b-chat": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true + }, + "ollama/llama2": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0 }, - "us.meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 0.000002, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "ollama/llama2:13b": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true + "output_cost_per_token": 0 }, - "us.meta.llama3-3-70b-instruct-v1:0": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "ollama/llama2:70b": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7.2e-7, - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0 }, - "us.meta.llama4-maverick-17b-instruct-v1:0": { - "input_cost_per_token": 2.4e-7, - "input_cost_per_token_batches": 1.2e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "ollama/llama2:7b": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 9.7e-7, - "output_cost_per_token_batches": 4.85e-7, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0 }, - "us.meta.llama4-scout-17b-instruct-v1:0": { - "input_cost_per_token": 1.7e-7, - "input_cost_per_token_batches": 8.5e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "ollama/llama3": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.6e-7, - "output_cost_per_token_batches": 3.3e-7, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0 }, - "us.mistral.pixtral-large-2502-v1:0": { - "input_cost_per_token": 0.000002, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "ollama/llama3.1": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_function_calling": true, - "supports_tool_choice": false + "output_cost_per_token": 0, + "supports_function_calling": true }, - "v0/v0-1.0-md": { - "input_cost_per_token": 0.000003, - "litellm_provider": "v0", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/llama3:70b": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0 }, - "v0/v0-1.5-lg": { - "input_cost_per_token": 0.000015, - "litellm_provider": "v0", - "max_input_tokens": 512000, - "max_output_tokens": 512000, - "max_tokens": 512000, + "ollama/llama3:8b": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0 }, - "v0/v0-1.5-md": { - "input_cost_per_token": 0.000003, - "litellm_provider": "v0", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "ollama/mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0, + "supports_function_calling": true }, - "vercel_ai_gateway/alibaba/qwen-3-14b": { - "input_cost_per_token": 8e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 40960, - "max_output_tokens": 16384, - "max_tokens": 16384, + "ollama/mistral-7B-Instruct-v0.2": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.4e-7 + "output_cost_per_token": 0, + "supports_function_calling": true }, - "vercel_ai_gateway/alibaba/qwen-3-235b": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 40960, - "max_output_tokens": 16384, - "max_tokens": 16384, + "ollama/mistral-large-instruct-2407": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-7 + "output_cost_per_token": 0, + "supports_function_calling": true }, - "vercel_ai_gateway/alibaba/qwen-3-30b": { - "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 40960, - "max_output_tokens": 16384, - "max_tokens": 16384, + "ollama/mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 3e-7 + "output_cost_per_token": 0, + "supports_function_calling": true }, - "vercel_ai_gateway/alibaba/qwen-3-32b": { - "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 40960, - "max_output_tokens": 16384, - "max_tokens": 16384, + "ollama/mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0, + "supports_function_calling": true }, - "vercel_ai_gateway/alibaba/qwen3-coder": { - "input_cost_per_token": 4e-7, - "litellm_provider": "vercel_ai_gateway", + "ollama/qwen3-coder:480b-cloud": { + "input_cost_per_token": 0, + "litellm_provider": "ollama", "max_input_tokens": 262144, - "max_output_tokens": 66536, - "max_tokens": 66536, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.0000016, + "output_cost_per_token": 0, + "supports_function_calling": true + }, + "openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vercel_ai_gateway/amazon/nova-lite": { - "input_cost_per_token": 6e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 300000, + "openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 7e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openai.gpt-oss-safeguard-120b": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.4e-7, - "supports_vision": true, - "supports_function_calling": true, - "supports_response_schema": true + "output_cost_per_token": 6e-7, + "supports_system_messages": true }, - "vercel_ai_gateway/amazon/nova-micro": { - "input_cost_per_token": 3.5e-8, - "litellm_provider": "vercel_ai_gateway", + "openai.gpt-oss-safeguard-20b": { + "input_cost_per_token": 7e-8, + "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.4e-7, + "output_cost_per_token": 2e-7, + "supports_system_messages": true + }, + "openai/container": { + "code_interpreter_cost_per_session": 0.03, + "litellm_provider": "openai", + "mode": "chat" + }, + "openrouter/anthropic/claude-3-haiku": { + "input_cost_per_image": 0.0004, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.00000125, "supports_function_calling": true, - "supports_response_schema": true + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/amazon/nova-pro": { - "input_cost_per_token": 8e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 300000, + "openrouter/anthropic/claude-3.5-sonnet": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000032, - "supports_vision": true, + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_response_schema": true + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "vercel_ai_gateway/amazon/titan-embed-text-v2": { - "input_cost_per_token": 2e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 0, - "max_output_tokens": 0, - "max_tokens": 0, + "openrouter/anthropic/claude-3.7-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "vercel_ai_gateway/anthropic/claude-3-haiku": { - "cache_creation_input_token_cost": 3e-7, - "cache_read_input_token_cost": 3e-8, - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vercel_ai_gateway", + "openrouter/anthropic/claude-haiku-4.5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 0.00000125, - "supports_vision": true, + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "vercel_ai_gateway/anthropic/claude-3-opus": { + "openrouter/anthropic/claude-opus-4": { + "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, - "litellm_provider": "vercel_ai_gateway", + "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-opus-4.1": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.00003, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "vercel_ai_gateway/anthropic/claude-3.5-haiku": { - "cache_creation_input_token_cost": 0.000001, - "cache_read_input_token_cost": 8e-8, - "input_cost_per_token": 8e-7, - "litellm_provider": "vercel_ai_gateway", + "openrouter/anthropic/claude-opus-4.5": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000004, + "output_cost_per_token": 0.000025, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-opus-4.6": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { + "openrouter/anthropic/claude-sonnet-4": { + "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-sonnet-4.5": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-sonnet-4.6": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/bytedance/ui-tars-1.5-7b": { + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", + "supports_tool_choice": true }, - "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/deepseek/deepseek-chat": { + "input_cost_per_token": 1.4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "output_cost_per_token": 2.8e-7, + "supports_prompt_caching": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/anthropic/claude-4-opus": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "openrouter/deepseek/deepseek-chat-v3-0324": { + "input_cost_per_token": 1.4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "output_cost_per_token": 2.8e-7, + "supports_prompt_caching": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/anthropic/claude-4-sonnet": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/deepseek/deepseek-chat-v3.1": { + "input_cost_per_token": 2e-7, + "input_cost_per_token_cache_hit": 2e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 8e-7, + "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true }, - "vercel_ai_gateway/anthropic/claude-3-5-sonnet": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, + "openrouter/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.00000219, "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, + "openrouter/deepseek/deepseek-r1-0528": { + "input_cost_per_token": 5e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.00000215, "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/anthropic/claude-3-7-sonnet": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/deepseek/deepseek-v3.2": { + "input_cost_per_token": 2.8e-7, + "input_cost_per_token_cache_hit": 2.8e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 4e-7, "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-v3.2-exp": { + "input_cost_per_token": 2e-7, + "input_cost_per_token_cache_hit": 2e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_tool_choice": true + }, + "openrouter/google/gemini-2.0-flash-001": { + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_audio_output": true, + "supports_function_calling": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "vercel_ai_gateway/anthropic/claude-haiku-4.5": { - "cache_creation_input_token_cost": 0.00000125, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/google/gemini-2.5-flash": { + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 3e-7, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000005, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000025, + "supports_audio_output": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "vercel_ai_gateway/anthropic/claude-opus-4": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "openrouter/google/gemini-2.5-pro": { + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00001, + "supports_audio_output": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "vercel_ai_gateway/anthropic/claude-opus-4.1": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "openrouter/google/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 5e-7, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_reasoning_token": 0.000003, + "output_cost_per_token": 0.000003, + "rpm": 2000, + "source": "https://ai.google.dev/pricing/gemini-3", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 }, - "vercel_ai_gateway/anthropic/claude-opus-4.5": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/google/gemini-3-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true }, - "vercel_ai_gateway/anthropic/claude-opus-4.6": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/google/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "vercel_ai_gateway/anthropic/claude-sonnet-4": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/gryphe/mythomax-l2-13b": { + "input_cost_per_token": 0.000001875, + "litellm_provider": "openrouter", + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000001875, + "supports_tool_choice": true + }, + "openrouter/mancer/weaver": { + "input_cost_per_token": 0.000005625, + "litellm_provider": "openrouter", + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000005625, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-70b-instruct": { + "input_cost_per_token": 5.9e-7, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_tool_choice": true + }, + "openrouter/minimax/minimax-m2": { + "input_cost_per_token": 2.55e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 0.00000102, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "vercel_ai_gateway/anthropic/claude-sonnet-4.5": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1000000, + "openrouter/minimax/minimax-m2.1": { + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.0000012, + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 204000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_computer_use": false }, - "vercel_ai_gateway/cohere/command-a": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 256000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "openrouter/minimax/minimax-m2.5": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000011, + "cache_read_input_token_cost": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/minimax/minimax-m2.5", "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_computer_use": false }, - "vercel_ai_gateway/cohere/command-r": { + "openrouter/mistralai/devstral-2512": { + "input_cost_per_image": 0, "input_cost_per_token": 1.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_tool_choice": true + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_vision": false }, - "vercel_ai_gateway/cohere/command-r-plus": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "openrouter/mistralai/ministral-14b-2512": { + "input_cost_per_image": 0, + "input_cost_per_token": 2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 2e-7, "supports_function_calling": true, - "supports_tool_choice": true - }, - "vercel_ai_gateway/cohere/embed-v4.0": { - "input_cost_per_token": 1.2e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 0, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "chat", - "output_cost_per_token": 0 - }, - "vercel_ai_gateway/deepseek/deepseek-r1": { - "input_cost_per_token": 5.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000219, - "supports_tool_choice": true + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { - "input_cost_per_token": 7.5e-7, - "litellm_provider": "vercel_ai_gateway", + "openrouter/mistralai/ministral-3b-2512": { + "input_cost_per_image": 0, + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 9.9e-7, + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/mistralai/ministral-8b-2512": { + "input_cost_per_image": 0, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-7, "supports_function_calling": true, + "supports_prompt_caching": false, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": true }, - "vercel_ai_gateway/deepseek/deepseek-v3": { - "input_cost_per_token": 9e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 8192, + "openrouter/mistralai/mistral-7b-instruct": { + "input_cost_per_token": 1.3e-7, + "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9e-7, + "output_cost_per_token": 1.3e-7, "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemini-2.0-flash": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/mistralai/mistral-large": { + "input_cost_per_token": 0.000008, + "litellm_provider": "openrouter", + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "output_cost_per_token": 0.000024, + "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 7.5e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/mistralai/mistral-large-2512": { + "input_cost_per_image": 0, + "input_cost_per_token": 5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_vision": true, + "output_cost_per_token": 0.0000015, "supports_function_calling": true, + "supports_prompt_caching": false, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": true }, - "vercel_ai_gateway/google/gemini-2.5-flash": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "openrouter/mistralai/mistral-small-3.1-24b-instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "output_cost_per_token": 3e-7, + "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemini-2.5-pro": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "openrouter/mistralai/mistral-small-3.2-24b-instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "output_cost_per_token": 3e-7, + "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemma-2-9b": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/mistralai/mixtral-8x22b-instruct": { + "input_cost_per_token": 6.5e-7, + "litellm_provider": "openrouter", + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2e-7, - "supports_vision": true, - "supports_function_calling": true, + "output_cost_per_token": 6.5e-7, "supports_tool_choice": true }, - "vercel_ai_gateway/inception/mercury-coder-small": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 32000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "openrouter/moonshotai/kimi-k2.5": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.000001 + "output_cost_per_token": 0.000003, + "source": "https://openrouter.ai/moonshotai/kimi-k2.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true }, - "vercel_ai_gateway/meta/llama-3-70b": { - "input_cost_per_token": 5.9e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/openai/gpt-3.5-turbo": { + "input_cost_per_token": 0.0000015, + "litellm_provider": "openrouter", + "max_tokens": 4095, "mode": "chat", - "output_cost_per_token": 7.9e-7, + "output_cost_per_token": 0.000002, "supports_tool_choice": true }, - "vercel_ai_gateway/meta/llama-3-8b": { - "input_cost_per_token": 5e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/openai/gpt-3.5-turbo-16k": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_tokens": 16383, "mode": "chat", - "output_cost_per_token": 8e-8, + "output_cost_per_token": 0.000004, "supports_tool_choice": true }, - "vercel_ai_gateway/meta/llama-3.1-70b": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 8192, + "openrouter/openai/gpt-4": { + "input_cost_per_token": 0.00003, + "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-7, + "output_cost_per_token": 0.00006, "supports_tool_choice": true }, - "vercel_ai_gateway/meta/llama-3.1-8b": { - "input_cost_per_token": 5e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "openrouter/openai/gpt-4.1": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 8e-8, + "output_cost_per_token": 0.000008, "supports_function_calling": true, - "supports_response_schema": true + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/meta/llama-3.2-11b": { - "input_cost_per_token": 1.6e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/openai/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.6e-7, - "supports_vision": true, + "output_cost_per_token": 0.0000016, "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/meta/llama-3.2-1b": { + "openrouter/openai/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1e-7 - }, - "vercel_ai_gateway/meta/llama-3.2-3b": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.5e-7, + "output_cost_per_token": 4e-7, "supports_function_calling": true, - "supports_response_schema": true + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/meta/llama-3.2-90b": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "vercel_ai_gateway", + "openrouter/openai/gpt-4o": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7.2e-7, - "supports_vision": true, + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/meta/llama-3.3-70b": { - "input_cost_per_token": 7.2e-7, - "litellm_provider": "vercel_ai_gateway", + "openrouter/openai/gpt-4o-2024-05-13": { + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7.2e-7, + "output_cost_per_token": 0.000015, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, "supports_tool_choice": true }, - "vercel_ai_gateway/meta/llama-4-maverick": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/openai/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_token": 0.00001, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, "supports_tool_choice": true }, - "vercel_ai_gateway/meta/llama-4-scout": { - "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "openrouter/openai/gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_vision": true, - "supports_function_calling": true, + "output_cost_per_token": 0.00001, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, "supports_tool_choice": true }, - "vercel_ai_gateway/mistral/codestral": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 256000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "openrouter/openai/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 9e-7, - "supports_function_calling": true, + "output_cost_per_token": 0.000002, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, "supports_tool_choice": true }, - "vercel_ai_gateway/mistral/codestral-embed": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 0, - "max_output_tokens": 0, - "max_tokens": 0, + "openrouter/openai/gpt-5-nano": { + "cache_read_input_token_cost": 5e-9, + "input_cost_per_token": 5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 4e-7, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/mistral/devstral-small": { - "input_cost_per_token": 7e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, + "openrouter/openai/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.8e-7, + "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": true }, - "vercel_ai_gateway/mistral/magistral-medium": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "openrouter/openai/gpt-5.2": { + "input_cost_per_image": 0, + "cache_read_input_token_cost": 1.75e-7, + "input_cost_per_token": 0.00000175, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000005, + "output_cost_per_token": 0.000014, "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true - }, - "vercel_ai_gateway/mistral/magistral-small": { - "input_cost_per_token": 5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true + "supports_vision": true }, - "vercel_ai_gateway/mistral/ministral-3b": { - "input_cost_per_token": 4e-8, - "litellm_provider": "vercel_ai_gateway", + "openrouter/openai/gpt-5.2-chat": { + "input_cost_per_image": 0, + "cache_read_input_token_cost": 1.75e-7, + "input_cost_per_token": 0.00000175, + "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 4e-8, + "output_cost_per_token": 0.000014, "supports_function_calling": true, - "supports_tool_choice": true + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/mistral/ministral-8b": { - "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "openrouter/openai/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.75e-7, + "input_cost_per_token": 0.00000175, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-7, - "supports_vision": true, - "supports_function_calling": true, + "output_cost_per_token": 0.000014, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, "supports_tool_choice": true }, - "vercel_ai_gateway/mistral/mistral-embed": { - "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 0, - "max_output_tokens": 0, - "max_tokens": 0, + "openrouter/openai/gpt-5.2-pro": { + "input_cost_per_image": 0, + "input_cost_per_token": 0.000021, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0 + "output_cost_per_token": 0.000168, + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/mistral/mistral-large": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 32000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "openrouter/openai/gpt-oss-120b": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000006, + "output_cost_per_token": 8e-7, + "source": "https://openrouter.ai/openai/gpt-oss-120b", "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vercel_ai_gateway/mistral/mistral-saba-24b": { - "input_cost_per_token": 7.9e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 32768, + "openrouter/openai/gpt-oss-20b": { + "input_cost_per_token": 2e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 7.9e-7 + "output_cost_per_token": 1e-7, + "source": "https://openrouter.ai/openai/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/mistral/mistral-small": { - "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 32000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "openrouter/openai/o1": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 3e-7, + "output_cost_per_token": 0.00006, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_response_schema": true - }, - "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { - "input_cost_per_token": 0.0000012, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 65536, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "supports_function_calling": true + "supports_vision": true }, - "vercel_ai_gateway/mistral/pixtral-12b": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vercel_ai_gateway", + "openrouter/openai/o3-mini": { + "input_cost_per_token": 0.0000011, + "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "supports_vision": true, + "output_cost_per_token": 0.0000044, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": false }, - "vercel_ai_gateway/mistral/pixtral-large": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", + "openrouter/openai/o3-mini-high": { + "input_cost_per_token": 0.0000011, + "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_vision": true, + "output_cost_per_token": 0.0000044, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_vision": false }, - "vercel_ai_gateway/moonshotai/kimi-k2": { - "input_cost_per_token": 5.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "openrouter/openrouter/auto": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", - "output_cost_per_token": 0.0000022, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true }, - "vercel_ai_gateway/morph/morph-v3-fast": { - "input_cost_per_token": 8e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.0000012 + "openrouter/openrouter/bodybuilder": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat" }, - "vercel_ai_gateway/morph/morph-v3-large": { - "input_cost_per_token": 9e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, + "openrouter/openrouter/free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 0.0000019 + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "vercel_ai_gateway/openai/gpt-3.5-turbo": { - "input_cost_per_token": 5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, + "openrouter/qwen/qwen-2.5-coder-32b-instruct": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 33792, + "max_output_tokens": 33792, + "max_tokens": 33792, "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, + "output_cost_per_token": 1.8e-7, "supports_tool_choice": true }, - "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { - "input_cost_per_token": 0.0000015, - "litellm_provider": "vercel_ai_gateway", + "openrouter/qwen/qwen-vl-plus": { + "input_cost_per_token": 2.1e-7, + "litellm_provider": "openrouter", "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 0.000002 + "output_cost_per_token": 6.3e-7, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/openai/gpt-4-turbo": { - "input_cost_per_token": 0.00001, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "openrouter/qwen/qwen3-235b-a22b-2507": { + "input_cost_per_token": 7.1e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_vision": true, + "output_cost_per_token": 1e-7, + "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true }, - "vercel_ai_gateway/openai/gpt-4.1": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { + "input_cost_per_token": 1.1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.000008, - "supports_vision": true, + "output_cost_per_token": 6e-7, + "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen3-coder": { + "input_cost_per_token": 2.2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262100, + "max_output_tokens": 262100, + "max_tokens": 262100, + "mode": "chat", + "output_cost_per_token": 9.5e-7, + "source": "https://openrouter.ai/qwen/qwen3-coder", "supports_tool_choice": true, - "supports_response_schema": true + "supports_function_calling": true }, - "vercel_ai_gateway/openai/gpt-4.1-mini": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 4e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "openrouter/qwen/qwen3-coder-plus": { + "input_cost_per_token": 0.000001, + "litellm_provider": "openrouter", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.0000016, - "supports_vision": true, + "output_cost_per_token": 0.000005, + "source": "https://openrouter.ai/qwen/qwen3-coder-plus", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/openai/gpt-4.1-nano": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 1e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "openrouter/switchpoint/router": { + "input_cost_per_token": 8.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000034, + "source": "https://openrouter.ai/switchpoint/router", + "supports_tool_choice": true + }, + "openrouter/undi95/remm-slerp-l2-13b": { + "input_cost_per_token": 0.000001875, + "litellm_provider": "openrouter", + "max_tokens": 6144, "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "output_cost_per_token": 0.000001875, + "supports_tool_choice": true }, - "vercel_ai_gateway/openai/gpt-4o": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "openrouter/x-ai/grok-4": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_vision": true, + "output_cost_per_token": 0.000015, + "source": "https://openrouter.ai/x-ai/grok-4", "supports_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_web_search": true }, - "vercel_ai_gateway/openai/gpt-4o-mini": { + "openrouter/xiaomi/mimo-v2-flash": { + "input_cost_per_token": 9e-8, + "output_cost_per_token": 2.9e-7, "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, + "cache_read_input_token_cost": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": false }, - "vercel_ai_gateway/openai/o1": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "openrouter/z-ai/glm-4.6": { + "input_cost_per_token": 4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 202800, + "max_output_tokens": 131000, + "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_vision": true, + "output_cost_per_token": 0.00000175, + "source": "https://openrouter.ai/z-ai/glm-4.6", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/openai/o3": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "openrouter/z-ai/glm-4.6:exacto": { + "input_cost_per_token": 4.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 202800, + "max_output_tokens": 131000, + "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 0.000008, - "supports_vision": true, + "output_cost_per_token": 0.0000019, + "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/openai/o3-mini": { + "openrouter/z-ai/glm-4.7": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.0000015, "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "cache_read_input_token_cost": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_assistant_prefill": true }, - "vercel_ai_gateway/openai/o4-mini": { + "openrouter/z-ai/glm-4.7-flash": { + "input_cost_per_token": 7e-8, + "output_cost_per_token": 4e-7, "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 2.75e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "vercel_ai_gateway", + "cache_read_input_token_cost": 0, + "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000044, - "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": false }, - "vercel_ai_gateway/perplexity/sonar": { - "input_cost_per_token": 0.000001, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 127000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "openrouter/z-ai/glm-5": { + "input_cost_per_token": 8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000001 + "output_cost_per_token": 0.00000256, + "source": "https://openrouter.ai/z-ai/glm-5", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/perplexity/sonar-pro": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 6.7e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 0.000015 + "output_cost_per_token": 6.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/perplexity/sonar-reasoning": { - "input_cost_per_token": 0.000001, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 127000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "ovhcloud/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 0.000005 + "output_cost_per_token": 1e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 127000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "ovhcloud/Meta-Llama-3_1-70B-Instruct": { + "input_cost_per_token": 6.7e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 0.000008 + "output_cost_per_token": 6.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct", + "supports_function_calling": false, + "supports_response_schema": false, + "supports_tool_choice": false }, - "vercel_ai_gateway/vercel/v0-1.0-md": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "ovhcloud/Meta-Llama-3_3-70B-Instruct": { + "input_cost_per_token": 6.7e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_vision": true, + "output_cost_per_token": 6.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vercel_ai_gateway/vercel/v0-1.5-md": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "ovhcloud/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 1e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 127000, + "max_output_tokens": 127000, + "max_tokens": 127000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_vision": true, + "output_cost_per_token": 1e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vercel_ai_gateway/xai/grok-2": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 4000, - "max_tokens": 4000, + "ovhcloud/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 1.3e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 118000, + "max_output_tokens": 118000, + "max_tokens": 118000, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 1.3e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vercel_ai_gateway/xai/grok-2-vision": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 9e-8, + "litellm_provider": "ovhcloud", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_vision": true, + "output_cost_per_token": 2.8e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", "supports_function_calling": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vercel_ai_gateway/xai/grok-3": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6.3e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 6.3e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false }, - "vercel_ai_gateway/xai/grok-3-fast": { - "input_cost_per_token": 0.000005, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "ovhcloud/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 8.7e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_function_calling": true + "output_cost_per_token": 8.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false }, - "vercel_ai_gateway/xai/grok-3-mini": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "ovhcloud/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 9.1e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 5e-7, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 9.1e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true }, - "vercel_ai_gateway/xai/grok-3-mini-fast": { - "input_cost_per_token": 6e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "ovhcloud/Qwen3-32B": { + "input_cost_per_token": 8e-8, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000004, + "output_cost_per_token": 2.3e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b", "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vercel_ai_gateway/xai/grok-4": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vercel_ai_gateway", + "ovhcloud/gpt-oss-120b": { + "input_cost_per_token": 8e-8, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/gpt-oss-20b": { + "input_cost_per_token": 4e-8, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/llava-v1.6-mistral-7b-hf": { + "input_cost_per_token": 2.9e-7, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.9e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "ovhcloud/mamba-codestral-7B-v0.1": { + "input_cost_per_token": 1.9e-7, + "litellm_provider": "ovhcloud", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 1.9e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false }, - "vercel_ai_gateway/zai/glm-4.5": { - "input_cost_per_token": 6e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "palm/chat-bison": { + "input_cost_per_token": 1.25e-7, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000022, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "vercel_ai_gateway/zai/glm-4.5-air": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 128000, - "max_output_tokens": 96000, - "max_tokens": 96000, + "palm/chat-bison-001": { + "input_cost_per_token": 1.25e-7, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000011, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "vercel_ai_gateway/zai/glm-4.6": { - "litellm_provider": "vercel_ai_gateway", - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 4.5e-7, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "perplexity/codellama-34b-instruct": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000018, - "source": "https://vercel.com/ai-gateway/models/glm-4.6", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000014 }, - "vertex_ai/claude-3-5-haiku": { - "input_cost_per_token": 0.000001, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "perplexity/codellama-70b-instruct": { + "input_cost_per_token": 7e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000005, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000028 }, - "vertex_ai/claude-3-5-haiku@20241022": { - "input_cost_per_token": 0.000001, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "perplexity/llama-2-70b-chat": { + "input_cost_per_token": 7e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000005, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000028 }, - "vertex_ai/claude-haiku-4-5@20251001": { - "cache_creation_input_token_cost": 0.00000125, - "cache_read_input_token_cost": 1e-7, + "perplexity/llama-3.1-70b-instruct": { "input_cost_per_token": 0.000001, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000001 + }, + "perplexity/llama-3.1-8b-instruct": { + "input_cost_per_token": 2e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_vision": true + "output_cost_per_token": 2e-7 }, - "vertex_ai/claude-3-5-sonnet": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "perplexity/llama-3.1-sonar-huge-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 0.000005, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000005 }, - "vertex_ai/claude-3-5-sonnet-v2": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "perplexity/llama-3.1-sonar-large-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 0.000001, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000001 }, - "vertex_ai/claude-3-5-sonnet-v2@20241022": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "perplexity/llama-3.1-sonar-large-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 0.000001, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000001 }, - "vertex_ai/claude-3-5-sonnet@20240620": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "perplexity/llama-3.1-sonar-small-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 2e-7 }, - "vertex_ai/claude-3-7-sonnet@20250219": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "deprecation_date": "2025-06-01", - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "perplexity/llama-3.1-sonar-small-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "output_cost_per_token": 2e-7 }, - "vertex_ai/claude-3-haiku": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, + "perplexity/mistral-7b-instruct": { + "input_cost_per_token": 7e-8, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00000125, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 2.8e-7 }, - "vertex_ai/claude-3-haiku@20240307": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, + "perplexity/mixtral-8x7b-instruct": { + "input_cost_per_token": 7e-8, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00000125, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 2.8e-7 }, - "vertex_ai/claude-3-opus": { - "input_cost_per_token": 0.000015, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, + "perplexity/pplx-70b-chat": { + "input_cost_per_token": 7e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.0000028 }, - "vertex_ai/claude-3-opus@20240229": { - "input_cost_per_token": 0.000015, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, + "perplexity/pplx-70b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.0000028 }, - "vertex_ai/claude-3-sonnet": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "perplexity/pplx-7b-chat": { + "input_cost_per_token": 7e-8, + "litellm_provider": "perplexity", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 2.8e-7 }, - "vertex_ai/claude-3-sonnet@20240229": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, + "perplexity/pplx-7b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 2.8e-7 }, - "vertex_ai/claude-opus-4": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "perplexity/sonar": { + "input_cost_per_token": 0.000001, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000075, + "output_cost_per_token": 0.000001, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.012, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 + }, + "supports_web_search": true + }, + "perplexity/sonar-deep-research": { + "citation_cost_per_token": 0.000002, + "input_cost_per_token": 0.000002, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_reasoning_token": 0.000003, + "output_cost_per_token": 0.000008, + "search_context_cost_per_query": { + "search_context_size_high": 0.005, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.005 }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_web_search": true }, - "vertex_ai/claude-opus-4-1": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "input_cost_per_token_batches": 0.0000075, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "perplexity/sonar-medium-chat": { + "input_cost_per_token": 6e-7, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000075, - "output_cost_per_token_batches": 0.0000375, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.0000018 }, - "vertex_ai/claude-opus-4-1@20250805": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "input_cost_per_token_batches": 0.0000075, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "perplexity/sonar-medium-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, "mode": "chat", - "output_cost_per_token": 0.000075, - "output_cost_per_token_batches": 0.0000375, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.0000018 }, - "vertex_ai/claude-opus-4-5": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "vertex_ai-anthropic_models", + "perplexity/sonar-pro": { + "input_cost_per_token": 0.000003, + "litellm_provider": "perplexity", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 0.000025, + "output_cost_per_token": 0.000015, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_web_search": true }, - "vertex_ai/claude-opus-4-5@20251101": { - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "perplexity/sonar-reasoning": { + "input_cost_per_token": 0.000001, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, + "output_cost_per_token": 0.000005, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 + "search_context_size_high": 0.014, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_native_streaming": true + "supports_web_search": true }, - "vertex_ai/claude-opus-4-6": { - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000125, - "cache_read_input_token_cost": 5e-7, - "cache_read_input_token_cost_above_200k_tokens": 0.000001, - "input_cost_per_token": 0.000005, - "input_cost_per_token_above_200k_tokens": 0.00001, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, + "perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 0.000002, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, - "output_cost_per_token_above_200k_tokens": 0.0000375, + "output_cost_per_token": 0.000008, "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_web_search": true }, - "vertex_ai/claude-opus-4-6@default": { - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000125, - "cache_read_input_token_cost": 5e-7, - "cache_read_input_token_cost_above_200k_tokens": 0.000001, - "input_cost_per_token": 0.000005, - "input_cost_per_token_above_200k_tokens": 0.00001, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "perplexity/sonar-small-chat": { + "input_cost_per_token": 7e-8, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000025, - "output_cost_per_token_above_200k_tokens": 0.0000375, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 2.8e-7 + }, + "perplexity/sonar-small-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 2.8e-7 + }, + "publicai/BSC-LT/ALIA-40b-instruct_Q8_0": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_tool_choice": true }, - "vertex_ai/claude-sonnet-4-5": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token_batches": 0.0000015, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "publicai/BSC-LT/salamandra-7b-instruct-tools-16k": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "publicai/allenai/Olmo-3-32B-Think": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_batches": 0.0000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true }, - "vertex_ai/claude-sonnet-4-6": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "publicai/allenai/Olmo-3-7B-Instruct": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - } + "supports_tool_choice": true }, - "vertex_ai/claude-sonnet-4-5@20250929": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token_batches": 0.0000015, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "publicai/allenai/Olmo-3-7B-Think": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_batches": 0.0000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_native_streaming": true + "supports_reasoning": true }, - "vertex_ai/claude-opus-4@20250514": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "publicai/swiss-ai/apertus-70b-instruct": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", + "supports_function_calling": false, + "supports_tool_choice": false + }, + "publicai/swiss-ai/apertus-8b-instruct": { + "input_cost_per_token": 0, + "litellm_provider": "publicai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://platform.publicai.co/docs", + "supports_function_calling": false, + "supports_tool_choice": false + }, + "qwen.qwen3-235b-a22b-2507-v1:0": { + "input_cost_per_token": 2.2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.8e-7, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_tool_choice": true }, - "vertex_ai/claude-sonnet-4": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "qwen.qwen3-32b-v1:0": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_tool_choice": true }, - "vertex_ai/claude-sonnet-4@20250514": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "qwen.qwen3-coder-30b-a3b-v1:0": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_tool_choice": true }, - "vertex_ai/mistralai/codestral-2@001": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "qwen.qwen3-coder-480b-a35b-v1:0": { + "input_cost_per_token": 2.2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 9e-7, + "output_cost_per_token": 0.0000018, "supports_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true }, - "vertex_ai/codestral-2": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-mistral_models", + "qwen.qwen3-coder-next": { + "input_cost_per_token": 5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9e-7, + "output_cost_per_token": 0.0000012, "supports_function_calling": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/codestral-2@001": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-mistral_models", + "qwen.qwen3-vl-235b-a22b": { + "input_cost_per_token": 5.3e-7, + "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9e-7, + "output_cost_per_token": 0.00000266, "supports_function_calling": true, - "supports_tool_choice": true + "supports_system_messages": true, + "supports_vision": true }, - "vertex_ai/mistralai/codestral-2": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "replicate/anthropic/claude-3.5-haiku": { + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000005, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 9e-7, "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true }, - "vertex_ai/codestral-2501": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "replicate/anthropic/claude-3.5-sonnet": { + "input_cost_per_token": 0.00000375, + "output_cost_per_token": 0.00001875, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true }, - "vertex_ai/codestral@2405": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "replicate/anthropic/claude-3.7-sonnet": { + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true }, - "vertex_ai/codestral@latest": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "replicate/anthropic/claude-4-sonnet": { + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true }, - "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { - "input_cost_per_token": 0.00000135, - "litellm_provider": "vertex_ai-deepseek_models", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, + "replicate/anthropic/claude-4.5-haiku": { + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000005, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.0000054, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supported_regions": [ - "us-west2" - ], - "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true }, - "vertex_ai/deepseek-ai/deepseek-v3.2-maas": { - "input_cost_per_token": 5.6e-7, - "input_cost_per_token_batches": 2.8e-7, - "litellm_provider": "vertex_ai-deepseek_models", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, + "replicate/anthropic/claude-4.5-sonnet": { + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.00000168, - "output_cost_per_token_batches": 8.4e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supported_regions": [ - "us-west2" - ], - "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true + }, + "replicate/deepseek-ai/deepseek-r1": { + "input_cost_per_token": 0.00000375, + "output_cost_per_token": 0.00001, + "output_cost_per_reasoning_token": 0.00001, + "litellm_provider": "replicate", + "mode": "chat", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_reasoning": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { - "input_cost_per_token": 0.00000135, - "litellm_provider": "vertex_ai-deepseek_models", - "max_input_tokens": 65336, + "replicate/deepseek-ai/deepseek-v3": { + "input_cost_per_token": 0.00000145, + "output_cost_per_token": 0.00000145, + "litellm_provider": "replicate", + "mode": "chat", + "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, + "supports_function_calling": true, + "supports_system_messages": true + }, + "replicate/deepseek-ai/deepseek-v3.1": { + "input_cost_per_token": 6.72e-7, + "output_cost_per_token": 0.000002016, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.0000054, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_assistant_prefill": true, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-8, - "cache_read_input_token_cost_per_audio_token": 5e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_pdf_size_mb": 30, - "max_tokens": 65536, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "replicate/google/gemini-2.5-flash": { + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_reasoning_token": 0.0000015, - "output_cost_per_token": 0.0000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_code_execution": true, - "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, + "supports_response_schema": true + }, + "replicate/google/gemini-3-pro": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000012, + "litellm_provider": "replicate", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "vertex_ai/jamba-1.5": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vertex_ai-ai21_models", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "replicate/ibm-granite/granite-3.3-8b-instruct": { + "input_cost_per_token": 3e-8, + "output_cost_per_token": 2.5e-7, + "litellm_provider": "replicate", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, + "replicate/meta/llama-2-13b": { + "input_cost_per_token": 1e-7, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-13b-chat": { + "input_cost_per_token": 1e-7, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 4e-7, + "output_cost_per_token": 5e-7, "supports_tool_choice": true }, - "vertex_ai/jamba-1.5-large": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vertex_ai-ai21_models", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "replicate/meta/llama-2-70b": { + "input_cost_per_token": 6.5e-7, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000008, + "output_cost_per_token": 0.00000275, "supports_tool_choice": true }, - "vertex_ai/jamba-1.5-large@001": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vertex_ai-ai21_models", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "replicate/meta/llama-2-70b-chat": { + "input_cost_per_token": 6.5e-7, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000008, + "output_cost_per_token": 0.00000275, "supports_tool_choice": true }, - "vertex_ai/jamba-1.5-mini": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vertex_ai-ai21_models", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "replicate/meta/llama-2-7b": { + "input_cost_per_token": 5e-8, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 4e-7, + "output_cost_per_token": 2.5e-7, "supports_tool_choice": true }, - "vertex_ai/jamba-1.5-mini@001": { - "input_cost_per_token": 2e-7, - "litellm_provider": "vertex_ai-ai21_models", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "replicate/meta/llama-2-7b-chat": { + "input_cost_per_token": 5e-8, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 4e-7, + "output_cost_per_token": 2.5e-7, "supports_tool_choice": true }, - "vertex_ai/meta/llama-3.1-405b-instruct-maas": { - "input_cost_per_token": 0.000005, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "replicate/meta/llama-3-70b": { + "input_cost_per_token": 6.5e-7, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000016, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.00000275, + "supports_tool_choice": true }, - "vertex_ai/meta/llama-3.1-70b-instruct-maas": { - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "replicate/meta/llama-3-70b-instruct": { + "input_cost_per_token": 6.5e-7, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.00000275, + "supports_tool_choice": true }, - "vertex_ai/meta/llama-3.1-8b-instruct-maas": { - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "metadata": { - "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." - }, + "replicate/meta/llama-3-8b": { + "input_cost_per_token": 5e-8, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true }, - "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "metadata": { - "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." - }, + "replicate/meta/llama-3-8b-instruct": { + "input_cost_per_token": 5e-8, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, "mode": "chat", - "output_cost_per_token": 0, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true }, - "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "replicate/mistralai/mistral-7b-instruct-v0.2": { + "input_cost_per_token": 5e-8, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00000115, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], - "supports_function_calling": true, + "output_cost_per_token": 2.5e-7, "supports_tool_choice": true }, - "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { - "input_cost_per_token": 3.5e-7, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "replicate/mistralai/mistral-7b-v0.1": { + "input_cost_per_token": 5e-8, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00000115, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], - "supports_function_calling": true, + "output_cost_per_token": 2.5e-7, "supports_tool_choice": true }, - "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 10000000, - "max_output_tokens": 10000000, - "max_tokens": 10000000, + "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], - "supports_function_calling": true, + "output_cost_per_token": 0.000001, "supports_tool_choice": true }, - "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 10000000, - "max_output_tokens": 10000000, - "max_tokens": 10000000, + "replicate/openai/gpt-4.1": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000008, + "litellm_provider": "replicate", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true + }, + "replicate/openai/gpt-4.1-mini": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.0000016, + "litellm_provider": "replicate", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true + }, + "replicate/openai/gpt-4.1-nano": { + "input_cost_per_token": 1e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 7e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/meta/llama3-405b-instruct-maas": { - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "replicate/openai/gpt-4o": { + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.00001, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_audio_input": true, + "supports_audio_output": true }, - "vertex_ai/meta/llama3-70b-instruct-maas": { - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "replicate/openai/gpt-4o-mini": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "vertex_ai/meta/llama3-8b-instruct-maas": { - "input_cost_per_token": 0, - "litellm_provider": "vertex_ai-llama_models", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "replicate/openai/gpt-5": { + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.00001, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "vertex_ai/minimaxai/minimax-m2-maas": { - "input_cost_per_token": 3e-7, - "litellm_provider": "vertex_ai-minimax_models", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, + "replicate/openai/gpt-5-mini": { + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 0.000002, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_function_calling": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_vision": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "vertex_ai/moonshotai/kimi-k2-thinking-maas": { - "input_cost_per_token": 6e-7, - "litellm_provider": "vertex_ai-moonshot_models", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "replicate/openai/gpt-5-nano": { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 4e-7, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_system_messages": true }, - "vertex_ai/zai-org/glm-4.7-maas": { - "input_cost_per_token": 6e-7, - "litellm_provider": "vertex_ai-zai_models", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "replicate/openai/gpt-oss-120b": { + "input_cost_per_token": 1.8e-7, + "output_cost_per_token": 7.2e-7, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.0000022, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_function_calling": true, + "supports_system_messages": true + }, + "replicate/openai/o1": { + "input_cost_per_token": 0.000015, + "output_cost_per_token": 0.00006, + "output_cost_per_reasoning_token": 0.00006, + "litellm_provider": "replicate", + "mode": "chat", "supports_reasoning": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/zai-org/glm-5-maas": { - "cache_read_input_token_cost": 1e-7, + "replicate/openai/o1-mini": { + "input_cost_per_token": 0.0000011, + "output_cost_per_token": 0.0000044, + "output_cost_per_reasoning_token": 0.0000044, + "litellm_provider": "replicate", + "mode": "chat", + "supports_reasoning": true, + "supports_system_messages": true + }, + "replicate/openai/o4-mini": { "input_cost_per_token": 0.000001, - "litellm_provider": "vertex_ai-zai_models", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "output_cost_per_token": 0.000004, + "output_cost_per_reasoning_token": 0.000004, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.0000032, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", - "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/mistral-medium-3": { - "input_cost_per_token": 4e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "replicate/qwen/qwen3-235b-a22b-instruct-2507": { + "input_cost_per_token": 2.64e-7, + "output_cost_per_token": 0.00000106, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/mistral-medium-3@001": { - "input_cost_per_token": 4e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "replicate/xai/grok-4": { + "input_cost_per_token": 0.0000072, + "output_cost_per_token": 0.000036, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/mistralai/mistral-medium-3": { - "input_cost_per_token": 4e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "replicateopenai/gpt-oss-20b": { + "input_cost_per_token": 9e-8, + "output_cost_per_token": 3.6e-7, + "litellm_provider": "replicate", "mode": "chat", - "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_tool_choice": true + "supports_system_messages": true }, - "vertex_ai/mistralai/mistral-medium-3@001": { - "input_cost_per_token": 4e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "sagemaker/meta-textgeneration-llama-2-13b-f": { + "input_cost_per_token": 0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, + "output_cost_per_token": 0 + }, + "sagemaker/meta-textgeneration-llama-2-70b-b-f": { + "input_cost_per_token": 0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0 + }, + "sagemaker/meta-textgeneration-llama-2-7b-f": { + "input_cost_per_token": 0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0 + }, + "sambanova/DeepSeek-R1": { + "input_cost_per_token": 0.000005, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000007, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 7e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000014, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-V3-0324": { + "input_cost_per_token": 0.000003, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000045, + "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true }, - "vertex_ai/mistral-large-2411": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "sambanova/DeepSeek-V3.1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.0000045, + "litellm_provider": "sambanova", "mode": "chat", - "output_cost_per_token": 0.000006, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing" }, - "vertex_ai/mistral-large@2407": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "sambanova/Llama-4-Maverick-17B-128E-Instruct": { + "input_cost_per_token": 6.3e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, "mode": "chat", - "output_cost_per_token": 0.000006, + "output_cost_per_token": 0.0000018, + "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "vertex_ai/mistral-large@2411-001": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "sambanova/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 4e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, "mode": "chat", - "output_cost_per_token": 0.000006, + "output_cost_per_token": 7e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vertex_ai/mistral-large@latest": { - "input_cost_per_token": 0.000002, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "sambanova/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 0.000005, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000006, + "output_cost_per_token": 0.00001, + "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vertex_ai/mistral-nemo@2407": { - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "sambanova/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000003, + "output_cost_per_token": 2e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vertex_ai/mistral-nemo@latest": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "sambanova/Meta-Llama-3.2-1B-Instruct": { + "input_cost_per_token": 4e-8, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 8e-8, + "source": "https://cloud.sambanova.ai/plans/pricing" }, - "vertex_ai/mistral-small-2503": { - "input_cost_per_token": 0.000001, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "sambanova/Meta-Llama-3.2-3B-Instruct": { + "input_cost_per_token": 8e-8, + "litellm_provider": "sambanova", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000003, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 1.6e-7, + "source": "https://cloud.sambanova.ai/plans/pricing" }, - "vertex_ai/mistral-small-2503@001": { - "input_cost_per_token": 0.000001, - "litellm_provider": "vertex_ai-mistral_models", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "sambanova/Meta-Llama-3.3-70B-Instruct": { + "input_cost_per_token": 6e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000003, + "output_cost_per_token": 0.0000012, + "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "vertex_ai/openai/gpt-oss-120b-maas": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vertex_ai-openai_models", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", - "supports_reasoning": true - }, - "vertex_ai/openai/gpt-oss-20b-maas": { - "input_cost_per_token": 7.5e-8, - "litellm_provider": "vertex_ai-openai_models", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "sambanova/Meta-Llama-Guard-3-8B": { + "input_cost_per_token": 3e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-7, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", - "supports_reasoning": true + "source": "https://cloud.sambanova.ai/plans/pricing" }, - "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "vertex_ai-qwen_models", - "max_input_tokens": 262144, + "sambanova/QwQ-32B": { + "input_cost_per_token": 5e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000001, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_regions": [ - "global" - ], - "supports_function_calling": true, - "supports_tool_choice": true + "source": "https://cloud.sambanova.ai/plans/pricing" }, - "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "input_cost_per_token": 0.000001, - "litellm_provider": "vertex_ai-qwen_models", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "sambanova/Qwen2-Audio-7B-Instruct": { + "input_cost_per_token": 5e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000004, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_regions": [ - "global" - ], + "output_cost_per_token": 0.0001, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_audio_input": true + }, + "sambanova/Qwen3-32B": { + "input_cost_per_token": 4e-7, + "litellm_provider": "sambanova", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true }, - "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vertex_ai-qwen_models", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "sambanova/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.0000045, + "litellm_provider": "sambanova", "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_regions": [ - "global" - ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing" }, - "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vertex_ai-qwen_models", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "sarvam/sarvam-m": { + "cache_creation_input_token_cost": 0, + "cache_creation_input_token_cost_above_1hr": 0, + "cache_read_input_token_cost": 0, + "input_cost_per_token": 0, + "litellm_provider": "sarvam", + "max_input_tokens": 8192, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "supports_reasoning": true + }, + "snowflake/claude-3-5-sonnet": { + "litellm_provider": "snowflake", + "max_input_tokens": 18000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "supports_computer_use": true + }, + "snowflake/deepseek-r1": { + "litellm_provider": "snowflake", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_regions": [ - "global" - ], - "supports_function_calling": true, - "supports_tool_choice": true + "supports_reasoning": true }, - "wandb/openai/gpt-oss-120b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.015, - "output_cost_per_token": 0.06, - "litellm_provider": "wandb", + "snowflake/gemma-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/openai/gpt-oss-20b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.005, - "output_cost_per_token": 0.02, - "litellm_provider": "wandb", + "snowflake/jamba-1.5-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/zai-org/GLM-4.5": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.2, - "litellm_provider": "wandb", + "snowflake/jamba-1.5-mini": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, - "litellm_provider": "wandb", + "snowflake/jamba-instruct": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 0.1, - "output_cost_per_token": 0.15, - "litellm_provider": "wandb", + "snowflake/llama2-70b-chat": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, - "litellm_provider": "wandb", + "snowflake/llama3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000025, - "litellm_provider": "wandb", + "snowflake/llama3-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/meta-llama/Llama-3.1-8B-Instruct": { - "max_tokens": 128000, + "snowflake/llama3.1-405b": { + "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.022, - "output_cost_per_token": 0.022, - "litellm_provider": "wandb", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/deepseek-ai/DeepSeek-V3.1": { - "max_tokens": 128000, + "snowflake/llama3.1-70b": { + "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.165, - "litellm_provider": "wandb", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 0.135, - "output_cost_per_token": 0.54, - "litellm_provider": "wandb", + "snowflake/llama3.1-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 0.114, - "output_cost_per_token": 0.275, - "litellm_provider": "wandb", + "snowflake/llama3.2-1b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, + "snowflake/llama3.2-3b": { + "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.071, - "output_cost_per_token": 0.071, - "litellm_provider": "wandb", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 64000, - "max_input_tokens": 64000, - "max_output_tokens": 64000, - "input_cost_per_token": 0.017, - "output_cost_per_token": 0.066, - "litellm_provider": "wandb", + "snowflake/llama3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "wandb/microsoft/Phi-4-mini-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.008, - "output_cost_per_token": 0.035, - "litellm_provider": "wandb", + "snowflake/mistral-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat" }, - "watsonx/ibm/granite-3-8b-instruct": { - "input_cost_per_token": 2e-7, - "litellm_provider": "watsonx", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "chat", - "output_cost_per_token": 2e-7, - "supports_audio_input": false, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false + "snowflake/mistral-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat" }, - "watsonx/mistralai/mistral-large": { - "input_cost_per_token": 0.000003, - "litellm_provider": "watsonx", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_audio_input": false, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false + "snowflake/mistral-large2": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat" }, - "watsonx/bigscience/mt0-xxl-13b": { + "snowflake/mixtral-8x7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, "max_tokens": 8192, - "max_input_tokens": 8192, + "mode": "chat" + }, + "snowflake/reka-core": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 0.0005, - "output_cost_per_token": 0.002, - "litellm_provider": "watsonx", - "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "max_tokens": 8192, + "mode": "chat" }, - "watsonx/core42/jais-13b-chat": { + "snowflake/reka-flash": { + "litellm_provider": "snowflake", + "max_input_tokens": 100000, + "max_output_tokens": 8192, "max_tokens": 8192, - "max_input_tokens": 8192, + "mode": "chat" + }, + "snowflake/snowflake-arctic": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, "max_output_tokens": 8192, - "input_cost_per_token": 0.0005, - "output_cost_per_token": 0.002, - "litellm_provider": "watsonx", - "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "max_tokens": 8192, + "mode": "chat" }, - "watsonx/google/flan-t5-xl-3b": { + "snowflake/snowflake-llama-3.1-405b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, "max_tokens": 8192, - "max_input_tokens": 8192, + "mode": "chat" + }, + "snowflake/snowflake-llama-3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, "max_output_tokens": 8192, - "input_cost_per_token": 6e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "watsonx", + "max_tokens": 8192, + "mode": "chat" + }, + "together-ai-21.1b-41b": { + "input_cost_per_token": 8e-7, + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 8e-7 }, - "watsonx/ibm/granite-13b-chat-v2": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "watsonx", + "together-ai-4.1b-8b": { + "input_cost_per_token": 2e-7, + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 2e-7 }, - "watsonx/ibm/granite-13b-instruct-v2": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "watsonx", + "together-ai-41.1b-80b": { + "input_cost_per_token": 9e-7, + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 9e-7 }, - "watsonx/ibm/granite-3-3-8b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "watsonx", + "together-ai-8.1b-21b": { + "input_cost_per_token": 3e-7, + "litellm_provider": "together_ai", + "max_tokens": 1000, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false + "output_cost_per_token": 3e-7 }, - "watsonx/ibm/granite-4-h-small": { - "max_tokens": 20480, - "max_input_tokens": 20480, - "max_output_tokens": 20480, - "input_cost_per_token": 6e-8, - "output_cost_per_token": 2.5e-7, - "litellm_provider": "watsonx", + "together-ai-81.1b-110b": { + "input_cost_per_token": 0.0000018, + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false + "output_cost_per_token": 0.0000018 }, - "watsonx/ibm/granite-guardian-3-2-2b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, + "together-ai-up-to-4b": { "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "watsonx", + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 1e-7 }, - "watsonx/ibm/granite-guardian-3-3-8b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/ibm/granite-ttm-1024-96-r2": { - "max_tokens": 512, - "max_input_tokens": 512, - "max_output_tokens": 512, - "input_cost_per_token": 3.8e-7, - "output_cost_per_token": 3.8e-7, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/ibm/granite-ttm-1536-96-r2": { - "max_tokens": 512, - "max_input_tokens": 512, - "max_output_tokens": 512, - "input_cost_per_token": 3.8e-7, - "output_cost_per_token": 3.8e-7, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "input_cost_per_token": 2e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 262000, "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 0.000006, + "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/ibm/granite-ttm-512-96-r2": { - "max_tokens": 512, - "max_input_tokens": 512, - "max_output_tokens": 512, - "input_cost_per_token": 3.8e-7, - "output_cost_per_token": 3.8e-7, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 6.5e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 0.000003, + "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/ibm/granite-vision-3-2-2b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "input_cost_per_token": 2e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 40000, "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_vision": true + "supports_tool_choice": false }, - "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-7, - "output_cost_per_token": 3.5e-7, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "input_cost_per_token": 0.000002, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/meta-llama/llama-3-2-1b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/meta-llama/llama-3-2-3b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, + "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 1.5e-7, - "litellm_provider": "watsonx", + "litellm_provider": "together_ai", + "max_input_tokens": 262144, "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000002, - "litellm_provider": "watsonx", + "together_ai/Qwen/Qwen3.5-397B-A17B": { + "input_cost_per_token": 6e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, "mode": "chat", + "output_cost_per_token": 0.0000036, + "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 128000, + "together_ai/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 0.000003, + "litellm_provider": "together_ai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 7.1e-7, - "output_cost_per_token": 7.1e-7, - "litellm_provider": "watsonx", + "max_output_tokens": 20480, + "max_tokens": 20480, "mode": "chat", + "output_cost_per_token": 0.000007, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 128000, + "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { + "input_cost_per_token": 5.5e-7, + "litellm_provider": "together_ai", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-7, - "output_cost_per_token": 0.0000014, - "litellm_provider": "watsonx", "mode": "chat", + "output_cost_per_token": 0.00000219, + "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/meta-llama/llama-guard-3-11b-vision": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-7, - "output_cost_per_token": 3.5e-7, - "litellm_provider": "watsonx", + "together_ai/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 0.00000125, + "litellm_provider": "together_ai", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": true + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/mistralai/mistral-medium-2505": { + "together_ai/deepseek-ai/DeepSeek-V3.1": { + "input_cost_per_token": 6e-7, + "litellm_provider": "together_ai", "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.00001, - "litellm_provider": "watsonx", "mode": "chat", + "output_cost_per_token": 0.0000017, + "source": "https://www.together.ai/models/deepseek-v3-1", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_reasoning": true, + "supports_tool_choice": true }, - "watsonx/mistralai/mistral-small-2503": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, - "litellm_provider": "watsonx", + "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { + "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, - "litellm_provider": "watsonx", + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-7, + "litellm_provider": "together_ai", "mode": "chat", + "output_cost_per_token": 8.8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/mistralai/pixtral-12b-2409": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-7, - "output_cost_per_token": 3.5e-7, - "litellm_provider": "watsonx", + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { + "input_cost_per_token": 0, + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": true + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/openai/gpt-oss-120b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "watsonx", + "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 2.7e-7, + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 8.5e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "watsonx/sdaia/allam-1-13b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0000018, - "output_cost_per_token": 0.0000018, - "litellm_provider": "watsonx", + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false + "output_cost_per_token": 5.9e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-2": { - "input_cost_per_token": 0.000002, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { + "input_cost_per_token": 0.0000035, + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.0000035, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-2-1212": { - "input_cost_per_token": 0.000002, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-7, + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 8.8e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-2-latest": { - "input_cost_per_token": 0.000002, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 1.8e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-2-vision": { - "input_cost_per_image": 0.000002, - "input_cost_per_token": 0.000002, - "litellm_provider": "xai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-2-vision-1212": { - "deprecation_date": "2026-02-28", - "input_cost_per_image": 0.000002, - "input_cost_per_token": 0.000002, - "litellm_provider": "xai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, - "xai/grok-2-vision-latest": { - "input_cost_per_image": 0.000002, - "input_cost_per_token": 0.000002, - "litellm_provider": "xai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, + "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6e-7, + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 6e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-3": { - "cache_read_input_token_cost": 7.5e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 0.000001, + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 0.000003, + "source": "https://www.together.ai/models/kimi-k2-instruct", "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-beta": { - "cache_read_input_token_cost": 7.5e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/moonshotai/Kimi-K2-Instruct-0905": { + "input_cost_per_token": 0.000001, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 0.000003, + "source": "https://www.together.ai/models/kimi-k2-0905", "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, - "xai/grok-3-fast-beta": { - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.000005, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/moonshotai/Kimi-K2.5": { + "input_cost_per_token": 5e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000025, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 0.0000028, + "source": "https://www.together.ai/models/kimi-k2-5", "supports_function_calling": true, - "supports_response_schema": false, "supports_tool_choice": true, - "supports_web_search": true + "supports_vision": true, + "supports_reasoning": true }, - "xai/grok-3-fast-latest": { - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.000005, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 6e-7, + "source": "https://www.together.ai/models/gpt-oss-120b", "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-3-latest": { - "cache_read_input_token_cost": 7.5e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/openai/gpt-oss-20b": { + "input_cost_per_token": 5e-8, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 2e-7, + "source": "https://www.together.ai/models/gpt-oss-20b", "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-3-mini": { - "cache_read_input_token_cost": 7.5e-8, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 3e-7, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/togethercomputer/CodeLlama-34b-Instruct": { + "litellm_provider": "together_ai", "mode": "chat", - "output_cost_per_token": 5e-7, - "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, - "xai/grok-3-mini-beta": { - "cache_read_input_token_cost": 7.5e-8, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 3e-7, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5e-7, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 0.0000011, + "source": "https://www.together.ai/models/glm-4-5-air", "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-3-mini-fast": { - "cache_read_input_token_cost": 1.5e-7, + "together_ai/zai-org/GLM-4.6": { "input_cost_per_token": 6e-7, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "litellm_provider": "together_ai", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 0.000004, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 0.0000022, + "source": "https://www.together.ai/models/glm-4-6", "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_tool_choice": true }, - "xai/grok-3-mini-fast-beta": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "together_ai/zai-org/GLM-4.7": { + "input_cost_per_token": 4.5e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 0.000004, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 0.000002, + "source": "https://www.together.ai/models/glm-4-7", "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_tool_choice": true }, - "xai/grok-3-mini-fast-latest": { - "cache_read_input_token_cost": 1.5e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 0.0000075, + "litellm_provider": "bedrock", "mode": "chat", - "output_cost_per_token": 0.000004, - "source": "https://x.ai/api#pricing", + "supports_video_input": true + }, + "us.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 8.25e-8, + "input_cost_per_token": 3.3e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.00000275, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true }, - "xai/grok-3-mini-latest": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 3e-7, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "us.amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 0.0000021875, + "input_cost_per_image_token": 0.0000021875, + "input_cost_per_audio_token": 0.0000021875, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 5e-7, - "source": "https://x.ai/api#pricing", + "output_cost_per_token": 0.0000175, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true }, - "xai/grok-4": { - "input_cost_per_token": 0.000003, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "us.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 2.4e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true }, - "xai/grok-4-fast-reasoning": { - "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, - "mode": "chat", - "input_cost_per_token": 2e-7, - "input_cost_per_token_above_128k_tokens": 4e-7, - "output_cost_per_token": 5e-7, - "output_cost_per_token_above_128k_tokens": 0.000001, - "cache_read_input_token_cost": 5e-8, - "source": "https://docs.x.ai/docs/models", + "us.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_response_schema": true }, - "xai/grok-4-fast-non-reasoning": { - "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "cache_read_input_token_cost": 5e-8, - "max_tokens": 2000000, + "us.amazon.nova-premier-v1:0": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "input_cost_per_token": 2e-7, - "input_cost_per_token_above_128k_tokens": 4e-7, - "output_cost_per_token": 5e-7, - "output_cost_per_token_above_128k_tokens": 0.000001, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 0.0000125, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_response_schema": true, + "supports_vision": true }, - "xai/grok-4-0709": { - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_128k_tokens": 0.000006, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "us.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_128k_tokens": 0.00003, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 0.0000032, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true }, - "xai/grok-4-latest": { - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_128k_tokens": 0.000006, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 8e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_128k_tokens": 0.00003, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 0.000004, + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "xai/grok-4-1-fast": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_token": 2e-7, - "input_cost_per_token_above_128k_tokens": 4e-7, - "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 5e-7, - "output_cost_per_token_above_128k_tokens": 0.000001, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, + "output_cost_per_token": 0.000015, "supports_function_calling": true, - "supports_reasoning": true, + "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "cache_read_input_token_cost": 3e-7, + "cache_creation_input_token_cost": 0.00000375 }, - "xai/grok-4-1-fast-reasoning": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_token": 2e-7, - "input_cost_per_token_above_128k_tokens": 4e-7, - "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 5e-7, - "output_cost_per_token_above_128k_tokens": 0.000001, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_reasoning": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "xai/grok-4-1-fast-reasoning-latest": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_token": 2e-7, - "input_cost_per_token_above_128k_tokens": 4e-7, - "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 5e-7, - "output_cost_per_token_above_128k_tokens": 0.000001, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true }, - "xai/grok-4-1-fast-non-reasoning": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_token": 2e-7, - "input_cost_per_token_above_128k_tokens": 4e-7, - "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "us.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 5e-7, - "output_cost_per_token_above_128k_tokens": 0.000001, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, + "output_cost_per_token": 0.00000125, "supports_function_calling": true, + "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "cache_read_input_token_cost": 2.5e-8, + "cache_creation_input_token_cost": 3.125e-7 }, - "xai/grok-4-1-fast-non-reasoning-latest": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_token": 2e-7, - "input_cost_per_token_above_128k_tokens": 4e-7, - "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "us.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 0.000015, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 5e-7, - "output_cost_per_token_above_128k_tokens": 0.000001, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, + "output_cost_per_token": 0.000075, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "cache_read_input_token_cost": 0.0000015, + "cache_creation_input_token_cost": 0.00001875 }, - "xai/grok-beta": { - "input_cost_per_token": 0.000005, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "us.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true - }, - "xai/grok-code-fast": { - "cache_read_input_token_cost": 2e-8, - "input_cost_per_token": 2e-7, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "cache_read_input_token_cost": 3e-7, + "cache_creation_input_token_cost": 0.00000375 }, - "xai/grok-code-fast-1": { - "cache_read_input_token_cost": 2e-8, - "input_cost_per_token": 2e-7, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://docs.x.ai/docs/models", + "us.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "xai/grok-code-fast-1-0825": { - "cache_read_input_token_cost": 2e-8, - "input_cost_per_token": 2e-7, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "us.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "xai/grok-vision-beta": { - "input_cost_per_image": 0.000005, - "input_cost_per_token": 0.000005, - "litellm_provider": "xai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "us.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "tool_use_system_prompt_tokens": 159 }, - "zai.glm-4.7": { - "input_cost_per_token": 6e-7, + "us.anthropic.claude-opus-4-5-20251101-v1:0": { + "cache_creation_input_token_cost": 0.000006875, + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000022, + "output_cost_per_token": 0.0000275, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "zai/glm-5": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.0000032, - "litellm_provider": "zai", - "max_input_tokens": 200000, + "us.anthropic.claude-opus-4-6-v1": { + "cache_creation_input_token_cost": 0.000006875, + "cache_creation_input_token_cost_above_200k_tokens": 0.00001375, + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.0000011, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_above_200k_tokens": 0.000011, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 0.0000275, + "output_cost_per_token_above_200k_tokens": 0.00004125, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "zai/glm-5-code": { - "cache_creation_input_token_cost": 0, + "us.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.000005, - "litellm_provider": "zai", - "max_input_tokens": 200000, - "max_output_tokens": 128000, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "zai/glm-4.7": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000022, - "litellm_provider": "zai", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.000004125, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, - "max_output_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "zai/glm-4.6": { - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000022, - "litellm_provider": "zai", + "us.anthropic.claude-sonnet-4-6": { + "cache_creation_input_token_cost": 0.000004125, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost": 3.3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, - "max_output_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 0.0000165, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "zai/glm-4.5": { - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000022, - "litellm_provider": "zai", + "us.deepseek.r1-v1:0": { + "input_cost_per_token": 0.00000135, + "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "supports_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": false + }, + "us.deepseek.v3.2": { + "input_cost_per_token": 6.2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, "mode": "chat", + "output_cost_per_token": 0.00000185, "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_reasoning": true, + "supports_tool_choice": true }, - "zai/glm-4.5v": { - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000018, - "litellm_provider": "zai", + "us.meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 0.00000532, + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 0.000016, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_tool_choice": false }, - "zai/glm-4.5-x": { - "input_cost_per_token": 0.0000022, - "output_cost_per_token": 0.0000089, - "litellm_provider": "zai", + "us.meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-7, + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 32000, + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", + "output_cost_per_token": 9.9e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_tool_choice": false }, - "zai/glm-4.5-air": { - "input_cost_per_token": 2e-7, - "output_cost_per_token": 0.0000011, - "litellm_provider": "zai", + "us.meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-7, + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 32000, + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", + "output_cost_per_token": 2.2e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_tool_choice": false }, - "zai/glm-4.5-airx": { - "input_cost_per_token": 0.0000011, - "output_cost_per_token": 0.0000045, - "litellm_provider": "zai", + "us.meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 3.5e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_tool_choice": false, + "supports_vision": true }, - "zai/glm-4-32b-0414-128k": { + "us.meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "zai", + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 1e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" + "supports_tool_choice": false }, - "zai/glm-4.5-flash": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "zai", + "us.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 1.5e-7, "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://docs.z.ai/guides/overview/pricing" - }, - "openai/container": { - "code_interpreter_cost_per_session": 0.03, - "litellm_provider": "openai", - "mode": "chat" + "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 4.5e-7, - "output_cost_per_token": 0.0000018, - "litellm_provider": "fireworks_ai", + "us.meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 0.000002, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_reasoning": true + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "us.meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-13b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-34b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-70b": { "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "supports_function_calling": true, + "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "us.meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-7, + "input_cost_per_token_batches": 1.2e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-7b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 9.7e-7, + "output_cost_per_token_batches": 4.85e-7, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "us.meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-7, + "input_cost_per_token_batches": 8.5e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "output_cost_per_token_batches": 3.3e-7, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "us.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 0.000002, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": false }, - "fireworks_ai/accounts/fireworks/models/codegemma-2b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "us.twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 0.0000075, + "litellm_provider": "bedrock", + "mode": "chat", + "supports_video_input": true }, - "fireworks_ai/accounts/fireworks/models/codegemma-7b": { - "max_tokens": 8192, - "max_input_tokens": 8192, + "us.writer.palmyra-x4-v1:0": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_pdf_input": true }, - "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "us.writer.palmyra-x5-v1:0": { + "input_cost_per_token": 6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_pdf_input": true }, - "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "v0/v0-1.0-md": { + "input_cost_per_token": 0.000003, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "v0/v0-1.5-lg": { + "input_cost_per_token": 0.000015, + "litellm_provider": "v0", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "v0/v0-1.5-md": { + "input_cost_per_token": 0.000003, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { - "max_tokens": 16384, - "max_input_tokens": 16384, + "vercel_ai_gateway/alibaba/qwen-3-14b": { + "input_cost_per_token": 8e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, "max_output_tokens": 16384, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 2.4e-7 }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, + "vercel_ai_gateway/alibaba/qwen-3-235b": { "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7 }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/alibaba/qwen-3-30b": { + "input_cost_per_token": 1e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-7 }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/alibaba/qwen-3-32b": { + "input_cost_per_token": 1e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/alibaba/qwen3-coder": { + "input_cost_per_token": 4e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 262144, + "max_output_tokens": 66536, + "max_tokens": 66536, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/amazon/nova-lite": { + "input_cost_per_token": 6e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/amazon/nova-micro": { + "input_cost_per_token": 3.5e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.4e-7, + "supports_function_calling": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/amazon/nova-pro": { + "input_cost_per_token": 8e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000032, + "supports_vision": true, + "supports_function_calling": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/amazon/titan-embed-text-v2": { + "input_cost_per_token": 2e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0 }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3-5-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3-7-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3-haiku": { + "cache_creation_input_token_cost": 3e-7, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3-opus": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3.5-haiku": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 8e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-4-opus": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-4-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-haiku-4.5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-opus-4": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-opus-4.1": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-opus-4.5": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/fare-20b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-opus-4.6": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/firefunction-v1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-sonnet-4": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/firellava-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/anthropic/claude-sonnet-4.5": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/cohere/command-a": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/flux-1-dev": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "vercel_ai_gateway/cohere/command-r": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-9, - "output_cost_per_token": 1e-9, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "vercel_ai_gateway/cohere/command-r-plus": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/gemma-7b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/cohere/embed-v4.0": { + "input_cost_per_token": 1.2e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0 }, - "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, + "vercel_ai_gateway/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/glm-4p5v": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", "mode": "chat", - "supports_reasoning": true - }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "output_cost_per_token": 0.00000219, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { - "max_tokens": 131072, + "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/internvl3-38b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/internvl3-78b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/internvl3-8b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/kat-coder": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 9.9e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, + "vercel_ai_gateway/deepseek/deepseek-v3": { "input_cost_per_token": 9e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { - "max_tokens": 8192, - "max_input_tokens": 8192, + "vercel_ai_gateway/google/gemini-2.0-flash": { + "deprecation_date": "2026-06-01", + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/google/gemini-2.0-flash-lite": { + "deprecation_date": "2026-06-01", + "input_cost_per_token": 7.5e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/google/gemini-2.5-flash": { + "input_cost_per_token": 3e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/google/gemini-2.5-pro": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, + "vercel_ai_gateway/google/gemma-2-9b": { "input_cost_per_token": 2e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/inception/mercury-coder-small": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000001 }, - "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { - "max_tokens": 8192, + "vercel_ai_gateway/meta/llama-3-70b": { + "input_cost_per_token": 5.9e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { - "max_tokens": 8192, + "vercel_ai_gateway/meta/llama-3-8b": { + "input_cost_per_token": 5e-8, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-8, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { + "vercel_ai_gateway/meta/llama-3.1-70b": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, "max_tokens": 8192, - "max_input_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "supports_tool_choice": true + }, + "vercel_ai_gateway/meta/llama-3.1-8b": { + "input_cost_per_token": 5e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-8, + "supports_function_calling": true, + "supports_response_schema": true + }, + "vercel_ai_gateway/meta/llama-3.2-11b": { + "input_cost_per_token": 1.6e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.6e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, + "vercel_ai_gateway/meta/llama-3.2-1b": { "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-7 }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/meta/llama-3.2-3b": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "supports_function_calling": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/meta/llama-3.2-90b": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/meta/llama-3.3-70b": { + "input_cost_per_token": 7.2e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { - "max_tokens": 131072, + "vercel_ai_gateway/meta/llama-4-maverick": { + "input_cost_per_token": 2e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, + "vercel_ai_gateway/meta/llama-4-scout": { "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { - "max_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, + "vercel_ai_gateway/mistral/codestral": { + "input_cost_per_token": 3e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vercel_ai_gateway/mistral/codestral-embed": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0 }, - "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/mistral/devstral-small": { + "input_cost_per_token": 7e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/minimax-m2": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/mistral/magistral-medium": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/mistral/magistral-small": { + "input_cost_per_token": 5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true }, - "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, + "vercel_ai_gateway/mistral/ministral-3b": { + "input_cost_per_token": 4e-8, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-8, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vercel_ai_gateway/mistral/ministral-8b": { "input_cost_per_token": 1e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/mistral-7b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/mistral/mistral-embed": { + "input_cost_per_token": 1e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0 }, - "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/mistral/mistral-large": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { - "max_tokens": 32768, + "vercel_ai_gateway/mistral/mistral-saba-24b": { + "input_cost_per_token": 7.9e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 7.9e-7 }, - "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/mistral/mistral-small": { + "input_cost_per_token": 1e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, + "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { "input_cost_per_token": 0.0000012, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_function_calling": true }, - "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { - "max_tokens": 128000, + "vercel_ai_gateway/mistral/pixtral-12b": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { - "max_tokens": 128000, + "vercel_ai_gateway/mistral/pixtral-large": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.0000012, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/moonshotai/kimi-k2": { + "input_cost_per_token": 5.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000022, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { - "max_tokens": 32768, + "vercel_ai_gateway/morph/morph-v3-fast": { + "input_cost_per_token": 8e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000012 }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { - "max_tokens": 32768, + "vercel_ai_gateway/morph/morph-v3-large": { + "input_cost_per_token": 9e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000019 }, - "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "vercel_ai_gateway/openai/gpt-3.5-turbo": { + "input_cost_per_token": 5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { + "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 0.0000015, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 4096, "max_tokens": 4096, - "max_input_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000002 + }, + "vercel_ai_gateway/openai/gpt-4-turbo": { + "input_cost_per_token": 0.00001, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { - "max_tokens": 32768, - "max_input_tokens": 32768, + "vercel_ai_gateway/openai/gpt-4.1": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { + "vercel_ai_gateway/openai/gpt-4.1-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, "max_tokens": 32768, - "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true + }, + "vercel_ai_gateway/openai/gpt-4.1-nano": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, "max_output_tokens": 32768, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/openai/gpt-4o": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/openai/gpt-4o-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/openai/o1": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/openai/o3": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true + }, + "vercel_ai_gateway/openai/o3-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true + }, + "vercel_ai_gateway/openai/o4-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true + }, + "vercel_ai_gateway/perplexity/sonar": { + "input_cost_per_token": 0.000001, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000001 + }, + "vercel_ai_gateway/perplexity/sonar-pro": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000015 }, - "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/perplexity/sonar-reasoning": { + "input_cost_per_token": 0.000001, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000005 }, - "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000008 }, - "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/vercel/v0-1.0-md": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { - "max_tokens": 32768, - "max_input_tokens": 32768, + "vercel_ai_gateway/vercel/v0-1.5-md": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/openorca-7b": { - "max_tokens": 32768, + "vercel_ai_gateway/xai/grok-2": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vercel_ai_gateway/xai/grok-2-vision": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/phi-2-3b": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { - "max_tokens": 131072, + "vercel_ai_gateway/xai/grok-3": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { - "max_tokens": 32064, - "max_input_tokens": 32064, - "max_output_tokens": 32064, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/xai/grok-3-fast": { + "input_cost_per_token": 0.000005, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000025, + "supports_function_calling": true }, - "fireworks_ai/accounts/fireworks/models/pythia-12b": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/xai/grok-3-mini": { + "input_cost_per_token": 3e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-7, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vercel_ai_gateway/xai/grok-4": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { - "max_tokens": 131072, + "vercel_ai_gateway/zai/glm-4.5": { + "input_cost_per_token": 6e-7, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000022, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vercel_ai_gateway/zai/glm-4.5-air": { "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 0.0000011, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vercel_ai_gateway/zai/glm-4.6": { + "litellm_provider": "vercel_ai_gateway", + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 4.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.0000018, + "source": "https://vercel.com/ai-gateway/models/glm-4.6", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-5-haiku": { + "input_cost_per_token": 0.000001, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-5-haiku@20241022": { + "input_cost_per_token": 0.000001, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-5-sonnet": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-5-sonnet-v2": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-5-sonnet-v2@20241022": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-5-sonnet@20240620": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-7-sonnet@20250219": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-haiku": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-haiku@20240307": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-opus": { + "input_cost_per_token": 0.000015, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-opus@20240229": { + "input_cost_per_token": 0.000015, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-sonnet": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-3-sonnet@20240229": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-haiku-4-5@20251001": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4-1": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "output_cost_per_token_batches": 0.0000375, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4-1@20250805": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "output_cost_per_token_batches": 0.0000375, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4-5": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4-5@20251101": { + "cache_creation_input_token_cost": 0.00000625, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "supports_native_streaming": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4-6": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000125, + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.000001, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_200k_tokens": 0.00001, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "output_cost_per_token_above_200k_tokens": 0.0000375, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4-6@default": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000125, + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.000001, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_200k_tokens": 0.00001, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "output_cost_per_token_above_200k_tokens": 0.0000375, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-opus-4@20250514": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-sonnet-4": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token_batches": 0.0000015, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-sonnet-4-5@20250929": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token_batches": 0.0000015, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_streaming": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-sonnet-4-6": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + } }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-sonnet-4-6@default": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + } }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/claude-sonnet-4@20250514": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { - "max_tokens": 128000, + "vertex_ai/codestral-2": { + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 9e-7, + "max_tokens": 128000, + "mode": "chat", "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, + "vertex_ai/codestral-2501": { "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { - "max_tokens": 128000, + "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-14b": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.2e-7, - "output_cost_per_token": 8.8e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 2.2e-7, - "output_cost_per_token": 8.8e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 2.2e-7, - "output_cost_per_token": 8.8e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 5e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-32b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_reasoning": true - }, - "fireworks_ai/accounts/fireworks/models/qwen3-4b": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-8b": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", "mode": "chat", - "supports_reasoning": true - }, - "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" - }, - "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 2.2e-7, - "output_cost_per_token": 8.8e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 2.2e-7, - "output_cost_per_token": 8.8e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/codestral-2@001": { + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1.5e-7, + "vertex_ai/codestral@2405": { + "input_cost_per_token": 2e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", "output_cost_per_token": 6e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1.5e-7, + "vertex_ai/codestral@latest": { + "input_cost_per_token": 2e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", "output_cost_per_token": 6e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { + "input_cost_per_token": 0.00000135, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { + "input_cost_per_token": 0.00000135, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_regions": [ + "us-west2" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/qwq-32b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/deepseek-ai/deepseek-v3.2-maas": { + "input_cost_per_token": 5.6e-7, + "input_cost_per_token_batches": 2.8e-7, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00000168, + "output_cost_per_token_batches": 8.4e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_regions": [ + "us-west2" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "vertex_ai/gemini-2.5-flash-image": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "max_pdf_size_mb": 30, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 0.00003, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": false, + "tpm": 8000000 + }, + "vertex_ai/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 5e-7, + "input_cost_per_audio_token": 0.000001, + "litellm_provider": "vertex_ai", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 9e-7, + "input_cost_per_audio_token_priority": 0.0000018, + "output_cost_per_token_priority": 0.0000054, + "cache_read_input_token_cost_priority": 9e-8, + "supports_service_tier": true + }, + "vertex_ai/gemini-3-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "fireworks_ai/accounts/fireworks/models/rolm-ocr": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_per_audio_token": 5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000015, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true }, - "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "output_cost_per_image": 0.00012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_url_context": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "fireworks_ai/accounts/fireworks/models/stablecode-3b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/gemini-3.1-pro-preview-customtools": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "vertex_ai", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "output_cost_per_image": 0.00012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_url_context": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 0.0000036, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "output_cost_per_token_priority": 0.0000216, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "cache_read_input_token_cost_priority": 3.6e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "supports_service_tier": true }, - "fireworks_ai/accounts/fireworks/models/starcoder-16b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, + "vertex_ai/jamba-1.5": { "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/starcoder-7b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/jamba-1.5-large": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/jamba-1.5-large@001": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/jamba-1.5-mini": { + "input_cost_per_token": 2e-7, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, + "vertex_ai/jamba-1.5-mini@001": { "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/meta/llama-3.1-405b-instruct-maas": { + "input_cost_per_token": 0.000005, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000016, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/yi-34b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/meta/llama-3.1-70b-instruct-maas": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/meta/llama-3.1-8b-instruct-maas": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "metadata": { + "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." + }, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-7, - "output_cost_per_token": 9e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "metadata": { + "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." + }, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "fireworks_ai/accounts/fireworks/models/yi-6b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.00000115, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "fireworks_ai", - "mode": "chat" + "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { + "input_cost_per_token": 3.5e-7, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.00000115, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true }, - "novita/deepseek/deepseek-v3.2": { - "litellm_provider": "novita", + "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, "mode": "chat", - "input_cost_per_token": 2.69e-7, - "output_cost_per_token": 4e-7, - "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, + "output_cost_per_token": 7e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 1.345e-7, - "input_cost_per_token_cache_hit": 1.345e-7, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/minimax/minimax-m2.1": { - "litellm_provider": "novita", + "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, "mode": "chat", - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, + "output_cost_per_token": 7e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 3e-8, - "input_cost_per_token_cache_hit": 3e-8 + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-405b-instruct-maas": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-70b-instruct-maas": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-8b-instruct-maas": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/minimaxai/minimax-m2-maas": { + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-minimax_models", + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "max_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_function_calling": true, + "supports_tool_choice": true }, - "novita/zai-org/glm-4.7": { - "litellm_provider": "novita", + "vertex_ai/mistral-large-2411": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000022, - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, + "output_cost_per_token": 0.000006, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token_cache_hit": 1.1e-7, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/xiaomimimo/mimo-v2-flash": { - "litellm_provider": "novita", + "vertex_ai/mistral-large@2407": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, - "max_input_tokens": 262144, - "max_output_tokens": 32000, - "max_tokens": 32000, + "output_cost_per_token": 0.000006, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 2e-8, - "input_cost_per_token_cache_hit": 2e-8, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/zai-org/autoglm-phone-9b-multilingual": { - "litellm_provider": "novita", + "vertex_ai/mistral-large@2411-001": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 3.5e-8, - "output_cost_per_token": 1.38e-7, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "max_tokens": 65536, - "supports_vision": true, - "supports_system_messages": true + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": true }, - "novita/moonshotai/kimi-k2-thinking": { - "litellm_provider": "novita", + "vertex_ai/mistral-large@latest": { + "input_cost_per_token": 0.000002, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000025, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "output_cost_per_token": 0.000006, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/minimax/minimax-m2": { - "litellm_provider": "novita", + "vertex_ai/mistral-medium-3": { + "input_cost_per_token": 4e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "cache_read_input_token_cost": 3e-8, - "input_cost_per_token_cache_hit": 3e-8, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/paddlepaddle/paddleocr-vl": { - "litellm_provider": "novita", + "vertex_ai/mistral-medium-3@001": { + "input_cost_per_token": 4e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 2e-8, - "output_cost_per_token": 2e-8, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "supports_vision": true, - "supports_system_messages": true + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": true }, - "novita/deepseek/deepseek-v3.2-exp": { - "litellm_provider": "novita", + "vertex_ai/mistral-nemo@2407": { + "input_cost_per_token": 0.000003, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "input_cost_per_token": 2.7e-7, - "output_cost_per_token": 4.1e-7, - "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, + "output_cost_per_token": 0.000003, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/qwen/qwen3-vl-235b-a22b-thinking": { - "litellm_provider": "novita", + "vertex_ai/mistral-nemo@latest": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "input_cost_per_token": 9.8e-7, - "output_cost_per_token": 0.00000395, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "supports_vision": true, - "supports_system_messages": true, - "supports_reasoning": true + "output_cost_per_token": 1.5e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, - "novita/zai-org/glm-4.6v": { - "litellm_provider": "novita", + "vertex_ai/mistral-small-2503": { + "input_cost_per_token": 0.000001, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "input_cost_per_token": 3e-7, - "output_cost_per_token": 9e-7, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "output_cost_per_token": 0.000003, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 5.5e-8, - "input_cost_per_token_cache_hit": 5.5e-8, - "supports_reasoning": true + "supports_vision": true }, - "novita/zai-org/glm-4.6": { - "litellm_provider": "novita", + "vertex_ai/mistral-small-2503@001": { + "input_cost_per_token": 0.000001, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 5.5e-7, - "output_cost_per_token": 0.0000022, - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, + "output_cost_per_token": 0.000003, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token_cache_hit": 1.1e-7, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/kwaipilot/kat-coder-pro": { - "litellm_provider": "novita", + "vertex_ai/mistralai/codestral-2": { + "input_cost_per_token": 3e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "max_input_tokens": 256000, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-7, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 6e-8, - "input_cost_per_token_cache_hit": 6e-8 + "supports_tool_choice": true }, - "novita/qwen/qwen3-next-80b-a3b-instruct": { - "litellm_provider": "novita", + "vertex_ai/mistralai/mistral-medium-3": { + "input_cost_per_token": 4e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 0.0000015, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_tool_choice": true }, - "novita/qwen/qwen3-next-80b-a3b-thinking": { - "litellm_provider": "novita", + "vertex_ai/mistralai/mistral-medium-3@001": { + "input_cost_per_token": 4e-7, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 0.0000015, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "output_cost_per_token": 0.000002, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/deepseek/deepseek-ocr": { - "litellm_provider": "novita", + "vertex_ai/moonshotai/kimi-k2-thinking-maas": { + "input_cost_per_token": 6e-7, + "litellm_provider": "vertex_ai-moonshot_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "input_cost_per_token": 3e-8, - "output_cost_per_token": 3e-8, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "output_cost_per_token": 0.0000025, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_web_search": true }, - "novita/deepseek/deepseek-v3.1-terminus": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 2.7e-7, - "output_cost_per_token": 0.000001, + "vertex_ai/openai/gpt-oss-120b-maas": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 1.35e-7, - "input_cost_per_token_cache_hit": 1.35e-7, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true }, - "novita/qwen/qwen3-vl-235b-a22b-instruct": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000015, + "vertex_ai/openai/gpt-oss-20b-maas": { + "input_cost_per_token": 7.5e-8, + "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "novita/qwen/qwen3-max": { - "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 0.00000211, - "output_cost_per_token": 0.00000845, - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "output_cost_per_token": 3e-7, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true }, - "novita/skywork/r1v4-lite": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 2e-7, - "output_cost_per_token": 6e-7, + "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "novita/deepseek/deepseek-v3.1": { - "litellm_provider": "novita", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, - "max_input_tokens": 131072, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": [ + "global" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { + "input_cost_per_token": 0.000001, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": [ + "global" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 1.35e-7, - "input_cost_per_token_cache_hit": 1.35e-7, - "supports_reasoning": true + "supports_tool_choice": true }, - "novita/moonshotai/kimi-k2-0905": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000025, + "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": [ + "global" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_tool_choice": true }, - "novita/qwen/qwen3-coder-480b-a35b-instruct": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000013, + "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": [ + "global" + ], "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_tool_choice": true }, - "novita/qwen/qwen3-coder-30b-a3b-instruct": { - "litellm_provider": "novita", + "vertex_ai/zai-org/glm-4.7-maas": { + "input_cost_per_token": 6e-7, + "litellm_provider": "vertex_ai-zai_models", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "input_cost_per_token": 7e-8, - "output_cost_per_token": 2.7e-7, - "max_input_tokens": 160000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "output_cost_per_token": 0.0000022, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_tool_choice": true }, - "novita/openai/gpt-oss-120b": { - "litellm_provider": "novita", + "vertex_ai/zai-org/glm-5-maas": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "vertex_ai-zai_models", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "input_cost_per_token": 5e-8, - "output_cost_per_token": 2.5e-7, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "output_cost_per_token": 0.0000032, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.01, + "litellm_provider": "wandb", + "mode": "chat" + }, + "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.01, + "litellm_provider": "wandb", + "mode": "chat" + }, + "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 0.1, + "output_cost_per_token": 0.15, + "litellm_provider": "wandb", + "mode": "chat" + }, + "wandb/deepseek-ai/DeepSeek-R1-0528": { + "max_tokens": 161000, + "max_input_tokens": 161000, + "max_output_tokens": 161000, + "input_cost_per_token": 0.135, + "output_cost_per_token": 0.54, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/moonshotai/kimi-k2-instruct": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 5.7e-7, - "output_cost_per_token": 0.0000023, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "wandb/deepseek-ai/DeepSeek-V3-0324": { + "max_tokens": 161000, + "max_input_tokens": 161000, + "max_output_tokens": 161000, + "input_cost_per_token": 0.114, + "output_cost_per_token": 0.275, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/deepseek/deepseek-v3-0324": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 2.7e-7, - "output_cost_per_token": 0.00000112, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 1.35e-7, - "input_cost_per_token_cache_hit": 1.35e-7 + "wandb/deepseek-ai/DeepSeek-V3.1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.055, + "output_cost_per_token": 0.165, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/zai-org/glm-4.5": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000022, - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token_cache_hit": 1.1e-7, - "supports_reasoning": true + "wandb/meta-llama/Llama-3.1-8B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.022, + "output_cost_per_token": 0.022, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/qwen/qwen3-235b-a22b-thinking-2507": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.000003, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_reasoning": true + "wandb/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.071, + "output_cost_per_token": 0.071, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/meta-llama/llama-3.1-8b-instruct": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 2e-8, - "output_cost_per_token": 5e-8, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "supports_system_messages": true + "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "max_tokens": 64000, + "max_input_tokens": 64000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.017, + "output_cost_per_token": 0.066, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/google/gemma-3-12b-it": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 5e-8, - "output_cost_per_token": 1e-7, - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true + "wandb/microsoft/Phi-4-mini-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.008, + "output_cost_per_token": 0.035, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/zai-org/glm-4.5v": { - "litellm_provider": "novita", - "mode": "chat", + "wandb/moonshotai/Kimi-K2-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000018, - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "max_tokens": 16384, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token_cache_hit": 1.1e-7, - "supports_reasoning": true + "output_cost_per_token": 0.0000025, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/openai/gpt-oss-20b": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 4e-8, - "output_cost_per_token": 1.5e-7, + "wandb/openai/gpt-oss-120b": { + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "max_output_tokens": 131072, + "input_cost_per_token": 0.015, + "output_cost_per_token": 0.06, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/qwen/qwen3-235b-a22b-instruct-2507": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 9e-8, - "output_cost_per_token": 5.8e-7, + "wandb/openai/gpt-oss-20b": { + "max_tokens": 131072, "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "max_output_tokens": 131072, + "input_cost_per_token": 0.005, + "output_cost_per_token": 0.02, + "litellm_provider": "wandb", + "mode": "chat" }, - "novita/deepseek/deepseek-r1-distill-qwen-14b": { - "litellm_provider": "novita", + "wandb/zai-org/GLM-4.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.055, + "output_cost_per_token": 0.2, + "litellm_provider": "wandb", + "mode": "chat" + }, + "watsonx/bigscience/mt0-xxl-13b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0005, + "output_cost_per_token": 0.002, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 1.5e-7, - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/meta-llama/llama-3.3-70b-instruct": { - "litellm_provider": "novita", + "watsonx/core42/jais-13b-chat": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0005, + "output_cost_per_token": 0.002, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 1.35e-7, - "output_cost_per_token": 4e-7, - "max_input_tokens": 131072, - "max_output_tokens": 120000, - "max_tokens": 120000, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/qwen/qwen-2.5-72b-instruct": { - "litellm_provider": "novita", + "watsonx/google/flan-t5-xl-3b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 3.8e-7, - "output_cost_per_token": 4e-7, - "max_input_tokens": 32000, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false + }, + "watsonx/ibm/granite-13b-chat-v2": { + "max_tokens": 8192, + "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "input_cost_per_token": 6e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/mistralai/mistral-nemo": { - "litellm_provider": "novita", + "watsonx/ibm/granite-13b-instruct-v2": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 4e-8, - "output_cost_per_token": 1.7e-7, - "max_input_tokens": 60288, - "max_output_tokens": 16000, - "max_tokens": 16000, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/minimaxai/minimax-m1-80k": { - "litellm_provider": "novita", + "watsonx/ibm/granite-3-3-8b-instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 5.5e-7, - "output_cost_per_token": 0.0000022, - "max_input_tokens": 1000000, - "max_output_tokens": 40000, - "max_tokens": 40000, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_reasoning": true + "supports_vision": false }, - "novita/deepseek/deepseek-r1-0528": { - "litellm_provider": "novita", + "watsonx/ibm/granite-3-8b-instruct": { + "input_cost_per_token": 2e-7, + "litellm_provider": "watsonx", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "chat", - "input_cost_per_token": 7e-7, - "output_cost_per_token": 0.0000025, - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, + "output_cost_per_token": 2e-7, + "supports_audio_input": false, + "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, "supports_response_schema": true, - "cache_read_input_token_cost": 3.5e-7, - "input_cost_per_token_cache_hit": 3.5e-7, - "supports_reasoning": true - }, - "novita/deepseek/deepseek-r1-distill-qwen-32b": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 3e-7, - "output_cost_per_token": 3e-7, - "max_input_tokens": 64000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "supports_tool_choice": true, "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_tool_choice": true, + "supports_vision": false }, - "novita/meta-llama/llama-3-8b-instruct": { - "litellm_provider": "novita", + "watsonx/ibm/granite-4-h-small": { + "max_tokens": 20480, + "max_input_tokens": 20480, + "max_output_tokens": 20480, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 2.5e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 4e-8, - "output_cost_per_token": 4e-8, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false + }, + "watsonx/ibm/granite-guardian-3-2-2b": { + "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_system_messages": true - }, - "novita/microsoft/wizardlm-2-8x22b": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 6.2e-7, - "output_cost_per_token": 6.2e-7, - "max_input_tokens": 65535, - "max_output_tokens": 8000, - "max_tokens": 8000, - "supports_system_messages": true - }, - "novita/deepseek/deepseek-r1-0528-qwen3-8b": { - "litellm_provider": "novita", + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 6e-8, - "output_cost_per_token": 9e-8, - "max_input_tokens": 128000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "supports_system_messages": true, - "supports_reasoning": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/deepseek/deepseek-r1-distill-llama-70b": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 8e-7, - "output_cost_per_token": 8e-7, + "watsonx/ibm/granite-guardian-3-3-8b": { + "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true - }, - "novita/meta-llama/llama-3-70b-instruct": { - "litellm_provider": "novita", + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 5.1e-7, - "output_cost_per_token": 7.4e-7, - "max_input_tokens": 8192, - "max_output_tokens": 8000, - "max_tokens": 8000, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/qwen/qwen3-235b-a22b-fp8": { - "litellm_provider": "novita", + "watsonx/ibm/granite-ttm-1024-96-r2": { + "max_tokens": 512, + "max_input_tokens": 512, + "max_output_tokens": 512, + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 3.8e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 2e-7, - "output_cost_per_token": 8e-7, - "max_input_tokens": 40960, - "max_output_tokens": 20000, - "max_tokens": 20000, - "supports_system_messages": true, - "supports_reasoning": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "litellm_provider": "novita", + "watsonx/ibm/granite-ttm-1536-96-r2": { + "max_tokens": 512, + "max_input_tokens": 512, + "max_output_tokens": 512, + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 3.8e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 2.7e-7, - "output_cost_per_token": 8.5e-7, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_vision": true, - "supports_system_messages": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/meta-llama/llama-4-scout-17b-16e-instruct": { - "litellm_provider": "novita", + "watsonx/ibm/granite-ttm-512-96-r2": { + "max_tokens": 512, + "max_input_tokens": 512, + "max_output_tokens": 512, + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 3.8e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 1.8e-7, - "output_cost_per_token": 5.9e-7, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "supports_vision": true, - "supports_system_messages": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false }, - "novita/nousresearch/hermes-2-pro-llama-3-8b": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 1.4e-7, - "output_cost_per_token": 1.4e-7, + "watsonx/ibm/granite-vision-3-2-2b": { + "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "novita/qwen/qwen2.5-vl-72b-instruct": { - "litellm_provider": "novita", + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 8e-7, - "output_cost_per_token": 8e-7, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "supports_vision": true, - "supports_system_messages": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": true }, - "novita/sao10k/l3-70b-euryale-v2.1": { - "litellm_provider": "novita", + "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 3.5e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 0.00000148, - "output_cost_per_token": 0.00000148, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true - }, - "novita/baidu/ernie-4.5-21B-a3b-thinking": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 7e-8, - "output_cost_per_token": 2.8e-7, - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "supports_system_messages": true, - "supports_reasoning": true + "supports_vision": true }, - "novita/sao10k/l3-8b-lunaris": { - "litellm_provider": "novita", + "watsonx/meta-llama/llama-3-2-1b-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 5e-8, - "output_cost_per_token": 5e-8, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false }, - "novita/baichuan/baichuan-m2-32b": { - "litellm_provider": "novita", + "watsonx/meta-llama/llama-3-2-3b-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 1.5e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 7e-8, - "output_cost_per_token": 7e-8, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "supports_system_messages": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false }, - "novita/baidu/ernie-4.5-vl-424b-a47b": { - "litellm_provider": "novita", + "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000002, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 4.2e-7, - "output_cost_per_token": 0.00000125, - "max_input_tokens": 123000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "supports_vision": true, - "supports_system_messages": true, - "supports_reasoning": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true }, - "novita/baidu/ernie-4.5-300b-a47b-paddle": { - "litellm_provider": "novita", + "watsonx/meta-llama/llama-3-3-70b-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 7.1e-7, + "output_cost_per_token": 7.1e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 2.8e-7, - "output_cost_per_token": 0.0000011, - "max_input_tokens": 123000, - "max_output_tokens": 12000, - "max_tokens": 12000, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false }, - "novita/deepseek/deepseek-prover-v2-671b": { - "litellm_provider": "novita", + "watsonx/meta-llama/llama-4-maverick-17b": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 0.0000014, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 7e-7, - "output_cost_per_token": 0.0000025, - "max_input_tokens": 160000, - "max_output_tokens": 160000, - "max_tokens": 160000, - "supports_system_messages": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false }, - "novita/qwen/qwen3-32b-fp8": { - "litellm_provider": "novita", + "watsonx/meta-llama/llama-guard-3-11b-vision": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 3.5e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 1e-7, - "output_cost_per_token": 4.5e-7, - "max_input_tokens": 40960, - "max_output_tokens": 20000, - "max_tokens": 20000, - "supports_system_messages": true, - "supports_reasoning": true + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": true }, - "novita/qwen/qwen3-30b-a3b-fp8": { - "litellm_provider": "novita", + "watsonx/mistralai/mistral-large": { + "input_cost_per_token": 0.000003, + "litellm_provider": "watsonx", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "input_cost_per_token": 9e-8, - "output_cost_per_token": 4.5e-7, - "max_input_tokens": 40960, - "max_output_tokens": 20000, - "max_tokens": 20000, + "output_cost_per_token": 0.00001, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_tool_choice": true, + "supports_vision": false }, - "novita/google/gemma-3-27b-it": { - "litellm_provider": "novita", + "watsonx/mistralai/mistral-medium-2505": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.00001, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 1.19e-7, - "output_cost_per_token": 2e-7, - "max_input_tokens": 98304, - "max_output_tokens": 16384, - "max_tokens": 16384, - "supports_vision": true, - "supports_system_messages": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false }, - "novita/deepseek/deepseek-v3-turbo": { - "litellm_provider": "novita", + "watsonx/mistralai/mistral-small-2503": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 4e-7, - "output_cost_per_token": 0.0000013, - "max_input_tokens": 64000, - "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true + "supports_vision": false }, - "novita/deepseek/deepseek-r1-turbo": { - "litellm_provider": "novita", + "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 7e-7, - "output_cost_per_token": 0.0000025, - "max_input_tokens": 64000, - "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true, - "supports_reasoning": true + "supports_vision": false }, - "novita/Sao10K/L3-8B-Stheno-v3.2": { - "litellm_provider": "novita", + "watsonx/mistralai/pixtral-12b-2409": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 3.5e-7, + "litellm_provider": "watsonx", "mode": "chat", - "input_cost_per_token": 5e-8, - "output_cost_per_token": 5e-8, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": true + }, + "watsonx/openai/gpt-oss-120b": { + "max_tokens": 8192, "max_input_tokens": 8192, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 8192, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false + }, + "watsonx/sdaia/allam-1-13b-instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0000018, + "output_cost_per_token": 0.0000018, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false + }, + "writer.palmyra-x4-v1:0": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_system_messages": true + "supports_pdf_input": true }, - "novita/gryphe/mythomax-l2-13b": { - "litellm_provider": "novita", + "writer.palmyra-x5-v1:0": { + "input_cost_per_token": 6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "input_cost_per_token": 9e-8, - "output_cost_per_token": 9e-8, - "max_input_tokens": 4096, - "max_output_tokens": 3200, - "max_tokens": 3200, - "supports_system_messages": true + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_pdf_input": true }, - "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 3.9e-7, - "output_cost_per_token": 3.9e-7, + "xai/grok-2": { + "input_cost_per_token": 0.000002, + "litellm_provider": "xai", "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_web_search": true }, - "novita/qwen/qwen3-vl-8b-instruct": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 8e-8, - "output_cost_per_token": 5e-7, + "xai/grok-2-1212": { + "input_cost_per_token": 0.000002, + "litellm_provider": "xai", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_web_search": true }, - "novita/zai-org/glm-4.5-air": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 1.3e-7, - "output_cost_per_token": 8.5e-7, + "xai/grok-2-latest": { + "input_cost_per_token": 0.000002, + "litellm_provider": "xai", "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_system_messages": true, - "supports_reasoning": true + "supports_web_search": true }, - "novita/qwen/qwen3-vl-30b-a3b-instruct": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 2e-7, - "output_cost_per_token": 7e-7, - "max_input_tokens": 131072, + "xai/grok-2-vision": { + "input_cost_per_image": 0.000002, + "input_cost_per_token": 0.000002, + "litellm_provider": "xai", + "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_web_search": true }, - "novita/qwen/qwen3-vl-30b-a3b-thinking": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 2e-7, - "output_cost_per_token": 0.000001, - "max_input_tokens": 131072, + "xai/grok-2-vision-1212": { + "deprecation_date": "2026-02-28", + "input_cost_per_image": 0.000002, + "input_cost_per_token": 0.000002, + "litellm_provider": "xai", + "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true - }, - "novita/qwen/qwen3-omni-30b-a3b-thinking": { - "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 2.5e-7, - "output_cost_per_token": 9.7e-7, - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "max_tokens": 16384, + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_audio_input": true + "supports_web_search": true }, - "novita/qwen/qwen3-omni-30b-a3b-instruct": { - "litellm_provider": "novita", + "xai/grok-2-vision-latest": { + "input_cost_per_image": 0.000002, + "input_cost_per_token": 0.000002, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "input_cost_per_token": 2.5e-7, - "output_cost_per_token": 9.7e-7, - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "max_tokens": 16384, + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_audio_input": true, - "supports_audio_output": true - }, - "novita/qwen/qwen-mt-plus": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 2.5e-7, - "output_cost_per_token": 7.5e-7, - "max_input_tokens": 16384, - "max_output_tokens": 8192, - "max_tokens": 8192, - "supports_system_messages": true + "supports_web_search": true }, - "novita/baidu/ernie-4.5-vl-28b-a3b": { - "litellm_provider": "novita", + "xai/grok-3": { + "cache_read_input_token_cost": 7.5e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "input_cost_per_token": 1.4e-7, - "output_cost_per_token": 5.6e-7, - "max_input_tokens": 30000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "output_cost_per_token": 0.000015, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_reasoning": true + "supports_web_search": true }, - "novita/baidu/ernie-4.5-21B-a3b": { - "litellm_provider": "novita", + "xai/grok-3-beta": { + "cache_read_input_token_cost": 7.5e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "input_cost_per_token": 7e-8, - "output_cost_per_token": 2.8e-7, - "max_input_tokens": 120000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "output_cost_per_token": 0.000015, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_system_messages": true - }, - "novita/qwen/qwen3-8b-fp8": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 3.5e-8, - "output_cost_per_token": 1.38e-7, - "max_input_tokens": 128000, - "max_output_tokens": 20000, - "max_tokens": 20000, - "supports_system_messages": true, - "supports_reasoning": true - }, - "novita/qwen/qwen3-4b-fp8": { - "litellm_provider": "novita", - "mode": "chat", - "input_cost_per_token": 3e-8, - "output_cost_per_token": 3e-8, - "max_input_tokens": 128000, - "max_output_tokens": 20000, - "max_tokens": 20000, - "supports_system_messages": true, - "supports_reasoning": true + "supports_web_search": true }, - "novita/qwen/qwen2.5-7b-instruct": { - "litellm_provider": "novita", + "xai/grok-3-fast-beta": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.000005, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "input_cost_per_token": 7e-8, - "output_cost_per_token": 7e-8, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "output_cost_per_token": 0.000025, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_system_messages": true, - "supports_response_schema": true + "supports_web_search": true }, - "novita/meta-llama/llama-3.2-3b-instruct": { - "litellm_provider": "novita", + "xai/grok-3-fast-latest": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.000005, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "input_cost_per_token": 3e-8, - "output_cost_per_token": 5e-8, - "max_input_tokens": 32768, - "max_output_tokens": 32000, - "max_tokens": 32000, + "output_cost_per_token": 0.000025, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_system_messages": true + "supports_web_search": true }, - "novita/sao10k/l31-70b-euryale-v2.2": { - "litellm_provider": "novita", + "xai/grok-3-latest": { + "cache_read_input_token_cost": 7.5e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "input_cost_per_token": 0.00000148, - "output_cost_per_token": 0.00000148, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "output_cost_per_token": 0.000015, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_system_messages": true + "supports_web_search": true }, - "llamagate/llama-3.1-8b": { - "max_tokens": 8192, + "xai/grok-3-mini": { + "cache_read_input_token_cost": 7.5e-8, + "deprecation_date": "2026-02-28", + "input_cost_per_token": 3e-7, + "litellm_provider": "xai", "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-8, - "output_cost_per_token": 5e-8, - "litellm_provider": "llamagate", + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/llama-3.2-3b": { - "max_tokens": 8192, + "xai/grok-3-mini-beta": { + "cache_read_input_token_cost": 7.5e-8, + "deprecation_date": "2026-02-28", + "input_cost_per_token": 3e-7, + "litellm_provider": "xai", "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-8, - "output_cost_per_token": 8e-8, - "litellm_provider": "llamagate", + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/mistral-7b-v0.3": { - "max_tokens": 8192, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1.5e-7, - "litellm_provider": "llamagate", + "xai/grok-3-mini-fast": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/qwen3-8b": { - "max_tokens": 8192, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-8, - "output_cost_per_token": 1.4e-7, - "litellm_provider": "llamagate", + "xai/grok-3-mini-fast-beta": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/dolphin3-8b": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-8, - "output_cost_per_token": 1.5e-7, - "litellm_provider": "llamagate", + "xai/grok-3-mini-fast-latest": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/deepseek-r1-8b": { - "max_tokens": 16384, - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "llamagate", + "xai/grok-3-mini-latest": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 3e-7, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://x.ai/api#pricing", "supports_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/deepseek-r1-7b-qwen": { - "max_tokens": 16384, - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "input_cost_per_token": 8e-8, - "output_cost_per_token": 1.5e-7, - "litellm_provider": "llamagate", + "xai/grok-4": { + "input_cost_per_token": 0.000003, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/openthinker-7b": { - "max_tokens": 8192, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-8, - "output_cost_per_token": 1.5e-7, - "litellm_provider": "llamagate", + "xai/grok-4-0709": { + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_128k_tokens": 0.000006, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_128k_tokens": 0.00003, + "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true + "supports_tool_choice": true, + "supports_web_search": true }, - "llamagate/qwen2.5-coder-7b": { - "max_tokens": 8192, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 6e-8, - "output_cost_per_token": 1.2e-7, - "litellm_provider": "llamagate", + "xai/grok-4-1-fast": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "litellm_provider": "xai", + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", + "supports_audio_input": true, "supports_function_calling": true, - "supports_response_schema": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "llamagate/deepseek-coder-6.7b": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-8, - "output_cost_per_token": 1.2e-7, - "litellm_provider": "llamagate", + "xai/grok-4-1-fast-non-reasoning": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "litellm_provider": "xai", + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", + "supports_audio_input": true, "supports_function_calling": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "llamagate/codellama-7b": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-8, - "output_cost_per_token": 1.2e-7, - "litellm_provider": "llamagate", + "xai/grok-4-1-fast-non-reasoning-latest": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "litellm_provider": "xai", + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", + "supports_audio_input": true, "supports_function_calling": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "llamagate/qwen3-vl-8b": { - "max_tokens": 8192, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 5.5e-7, - "litellm_provider": "llamagate", + "xai/grok-4-1-fast-reasoning": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "litellm_provider": "xai", + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", + "supports_audio_input": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "llamagate/llava-7b": { - "max_tokens": 2048, - "max_input_tokens": 4096, - "max_output_tokens": 2048, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 2e-7, - "litellm_provider": "llamagate", + "xai/grok-4-1-fast-reasoning-latest": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "litellm_provider": "xai", + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "llamagate/gemma3-4b": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-8, - "output_cost_per_token": 8e-8, - "litellm_provider": "llamagate", + "xai/grok-4-fast-non-reasoning": { + "litellm_provider": "xai", + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "cache_read_input_token_cost": 5e-8, + "max_tokens": 2000000, "mode": "chat", + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_web_search": true }, - "sarvam/sarvam-m": { - "cache_creation_input_token_cost": 0, - "cache_creation_input_token_cost_above_1hr": 0, - "cache_read_input_token_cost": 0, - "input_cost_per_token": 0, - "litellm_provider": "sarvam", - "max_input_tokens": 8192, - "max_output_tokens": 32000, - "max_tokens": 32000, + "xai/grok-4-fast-reasoning": { + "litellm_provider": "xai", + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", - "output_cost_per_token": 0, - "supports_reasoning": true + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "cache_read_input_token_cost": 5e-8, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true }, - "gpt-5-search-api": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "xai/grok-4-latest": { + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_128k_tokens": 0.000006, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_128k_tokens": 0.00003, + "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, "supports_web_search": true }, - "gpt-5-search-api-2025-10-14": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "xai/grok-beta": { + "input_cost_per_token": 0.000005, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000015, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, - "gpt-realtime-mini-2025-10-06": { - "cache_creation_input_audio_token_cost": 3e-7, - "cache_read_input_audio_token_cost": 3e-7, - "cache_read_input_token_cost": 6e-8, - "input_cost_per_audio_token": 0.00001, - "input_cost_per_image": 8e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "xai/grok-code-fast": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, + "output_cost_per_token": 0.0000015, + "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, + "supports_reasoning": true, "supports_tool_choice": true }, - "gpt-realtime-mini-2025-12-15": { - "cache_creation_input_audio_token_cost": 3e-7, - "cache_read_input_audio_token_cost": 3e-7, - "cache_read_input_token_cost": 6e-8, - "input_cost_per_audio_token": 0.00001, - "input_cost_per_image": 8e-7, - "input_cost_per_token": 6e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "xai/grok-code-fast-1": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, + "output_cost_per_token": 0.0000015, + "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, + "supports_reasoning": true, "supports_tool_choice": true }, - "gemini/gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, + "xai/grok-code-fast-1-0825": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-vision-beta": { + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000005, + "litellm_provider": "xai", + "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_pdf_size_mb": 50, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-7, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, + "output_cost_per_token": 0.000015, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000 + "supports_web_search": true }, - "gemini-2.5-flash-native-audio-latest": { - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "zai.glm-4.7": { + "input_cost_per_token": 6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true + "output_cost_per_token": 0.0000022, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "gemini-2.5-flash-native-audio-preview-09-2025": { - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "zai.glm-4.7-flash": { + "input_cost_per_token": 7e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true + "output_cost_per_token": 4e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "gemini-2.5-flash-native-audio-preview-12-2025": { - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "zai/glm-4-32b-0414-128k": { + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "litellm_provider": "zai", + "max_input_tokens": 128000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini/gemini-2.5-flash-native-audio-latest": { - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "zai/glm-4.5": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000022, + "litellm_provider": "zai", + "max_input_tokens": 128000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "tpm": 250000, - "rpm": 10 + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini/gemini-2.5-flash-native-audio-preview-09-2025": { - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "zai/glm-4.5-air": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 0.0000011, + "litellm_provider": "zai", + "max_input_tokens": 128000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "tpm": 250000, - "rpm": 10 + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "zai/glm-4.5-airx": { + "input_cost_per_token": 0.0000011, + "output_cost_per_token": 0.0000045, + "litellm_provider": "zai", + "max_input_tokens": 128000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "tpm": 250000, - "rpm": 10 + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini-flash-latest": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "zai/glm-4.5-flash": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "zai", + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" + }, + "zai/glm-4.5-x": { + "input_cost_per_token": 0.0000022, + "output_cost_per_token": 0.0000089, + "litellm_provider": "zai", + "max_input_tokens": 128000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 8000000 + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "zai/glm-4.5v": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000018, + "litellm_provider": "zai", + "max_input_tokens": 128000, + "max_output_tokens": 32000, "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, - "tpm": 250000 + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "zai/glm-4.6": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000022, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini/gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "zai/glm-4.7": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000022, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "source": "https://docs.z.ai/guides/overview/pricing" }, - "gemini-exp-1206": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_images_per_prompt": 3000, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_pdf_size_mb": 30, - "max_tokens": 65535, - "max_video_length": 1, - "max_videos_per_prompt": 10, + "zai/glm-5": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.0000032, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 8000000 + "source": "https://docs.z.ai/guides/overview/pricing" }, - "vertex_ai/claude-sonnet-4-6@default": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "zai/glm-5-code": { + "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "litellm_provider": "vertex_ai-anthropic_models", + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.000005, + "litellm_provider": "zai", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - } + "source": "https://docs.z.ai/guides/overview/pricing" } } \ No newline at end of file diff --git a/cecli/scrape.py b/cecli/scrape.py index 2e16c90707f..0722e11768d 100755 --- a/cecli/scrape.py +++ b/cecli/scrape.py @@ -51,7 +51,7 @@ async def install_playwright(io): if has_playwright and has_chromium: return True - pip_cmd = utils.get_pip_install(["cecli[playwright]"]) + pip_cmd = utils.get_pip_install(["cecli-dev[playwright]"]) chromium_cmd = "-m playwright install --with-deps chromium" chromium_cmd = [sys.executable] + chromium_cmd.split() diff --git a/cecli/tools/command.py b/cecli/tools/command.py index 7b8826ce031..8ef37d3367d 100644 --- a/cecli/tools/command.py +++ b/cecli/tools/command.py @@ -1,4 +1,7 @@ # Import necessary functions +import os +import platform + from cecli.helpers.background_commands import BackgroundCommandManager from cecli.run_cmd import run_cmd_subprocess from cecli.tools.utils.base_tool import BaseTool @@ -121,6 +124,8 @@ async def _execute_with_timeout(cls, coder, command_string, timeout): coder.io.tool_output(f"⚙️ Executing shell command with {timeout}s timeout: {command_string}") + shell = os.environ.get("SHELL", "/bin/sh") + # Create output buffer buffer = CircularBuffer(max_size=4096) @@ -128,6 +133,7 @@ async def _execute_with_timeout(cls, coder, command_string, timeout): process = subprocess.Popen( command_string, shell=True, + executable=shell if platform.system() != "Windows" else None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.DEVNULL, diff --git a/cecli/tools/context_manager.py b/cecli/tools/context_manager.py index 5eb85beff82..ac34c096c37 100644 --- a/cecli/tools/context_manager.py +++ b/cecli/tools/context_manager.py @@ -86,6 +86,11 @@ def execute(cls, coder, remove=None, editable=None, view=None, create=None, **kw for f in editable_files: messages.append(cls._editable(coder, f)) + if coder.tui and coder.tui(): + coder.tui().refresh() + + coder.context_blocks_cache = {} + return "\n".join(messages) @staticmethod @@ -95,12 +100,15 @@ def _remove(coder, file_path): abs_path = coder.abs_root_path(file_path) rel_path = coder.get_rel_fname(abs_path) removed = False + if abs_path in coder.abs_fnames: coder.abs_fnames.remove(abs_path) removed = True - elif abs_path in coder.abs_read_only_fnames: + + if abs_path in coder.abs_read_only_fnames: coder.abs_read_only_fnames.remove(abs_path) removed = True + if not removed: coder.io.tool_output(f"⚠️ File '{file_path}' not in context") return f"File not in context: {file_path}" diff --git a/cecli/tools/grep.py b/cecli/tools/grep.py index 557dc250a96..b04f1b8090e 100644 --- a/cecli/tools/grep.py +++ b/cecli/tools/grep.py @@ -108,7 +108,7 @@ def execute( for search_op in searches: pattern = search_op.get("pattern") file_pattern = search_op.get("file_pattern", "*") - directory = search_op.get("directory", ".") + directory = search_op.get("directory", search_op.get("path", ".")) use_regex = search_op.get("use_regex", False) case_insensitive = search_op.get("case_insensitive", False) context_before = search_op.get("context_before", 5) @@ -116,9 +116,6 @@ def execute( try: search_dir_path = Path(repo.root) / directory - if not search_dir_path.is_dir(): - all_results.append(f"Error: Directory not found: {directory}") - continue # Build the command arguments based on the available tool cmd_args = [tool_path] @@ -205,7 +202,27 @@ def execute( all_results.append(f"Error executing search for '{pattern}': {str(e)}") final_message = "\n\n".join(all_results) + if coder.tui and coder.tui(): - coder.io.tool_output(final_message) + # For the UI, show a summary to avoid cluttering the terminal + ui_summaries = [] + for search_op, result in zip(searches, all_results): + pattern = search_op.get("pattern") + if "No matches found" in result: + ui_summaries.append(f"No matches found for '{pattern}'.") + elif "Error" in result: + ui_summaries.append(f"Error searching for '{pattern}'.") + else: + # Count lines in the output to give a sense of scale + # The result string contains the matches in a code block + match_count = ( + result.count("\n") - 2 + ) # Subtracting for the markdown block markers + if match_count < 0: + match_count = 0 + ui_summaries.append(f"✅ Matches found for '{pattern}'.") + + ui_message = "\n\n".join(ui_summaries) + coder.io.tool_output(ui_message) return final_message diff --git a/cecli/tui/app.py b/cecli/tui/app.py index 7423cc41205..5522946cde0 100644 --- a/cecli/tui/app.py +++ b/cecli/tui/app.py @@ -3,8 +3,12 @@ import concurrent.futures import json import queue +from functools import lru_cache from pathlib import Path +import textual.strip +from rich.color import ColorSystem +from rich.style import Style from textual import events from textual.app import App, ComposeResult @@ -75,6 +79,9 @@ def __init__(self, coder_worker, output_queue, input_queue, args): }, ) + if other.get("use_terminal_background", False): + patch_textual_strip_render_with_cache() + self.bind( self._encode_keys(self.get_keys_for("newline")), "noop", @@ -218,6 +225,7 @@ def _get_config(self): # Default settings for the "other" section default_other = { "render_markdown": False, + "use_terminal_background": False, } # Merge default other settings with user-provided settings @@ -1171,3 +1179,39 @@ def on_completion_bar_dismissed(self, message: CompletionBar.Dismissed): input_area.completion_active = False input_area.focus() + + +def patch_textual_strip_render_with_cache(): + # 1. Define the logic + def modified_render_ansi(cls, style: Style, color_system: ColorSystem) -> str: + """Modified ANSI generator that ignores background colors.""" + sgr: list[str] + # Handle Attributes + if attributes := style._attributes & style._set_attributes: + _style_map = textual.strip.SGR_STYLES + sgr = [ + _style_map[bit_offset] + for bit_offset in range(attributes.bit_length()) + if attributes & (1 << bit_offset) + ] + else: + sgr = [] + + # Handle Foreground Color + if (color := style._color) is not None: + sgr.extend(color.downgrade(color_system).get_ansi_codes()) + + # BACKGROUND OVERRIDE: Skip the bgcolor block entirely + + ansi = style._ansi = ";".join(sgr) + return ansi + + # 2. Re-apply the EXACT cache settings from the original source + cached_version = lru_cache(maxsize=16384)(modified_render_ansi) + + # 3. Convert to classmethod and inject + textual.strip.Strip.render_ansi = classmethod(cached_version) + + +# Execute the patch +# patch_textual_strip_render_with_cache() diff --git a/cecli/tui/widgets/input_area.py b/cecli/tui/widgets/input_area.py index 30fdfc5cd8b..4d59e66246d 100644 --- a/cecli/tui/widgets/input_area.py +++ b/cecli/tui/widgets/input_area.py @@ -296,19 +296,23 @@ def on_key(self, event) -> None: self.post_message(self.CompletionDismiss()) elif event.key == "up": # If on first line, navigate history - # Or use Ctrl+Up? Let's use Up if on first line for convenience, similar to typical shell - # BUT this is a text editor. - # Let's try: if cursor is at (0,0) or just row 0. - if self.cursor_location[0] == 0: - event.stop() - event.prevent_default() - self._history_prev() + current_row, current_col = self.cursor_location + if current_row == 0: + if current_col // self.size.width == 0: + event.stop() + event.prevent_default() + self._history_prev() elif event.key == "down": # If on last line, navigate history - if self.cursor_location[0] == self.document.line_count - 1: - event.stop() - event.prevent_default() - self._history_next() + current_row, current_col = self.cursor_location + if current_row == self.document.line_count - 1: + if self.get_cursor_down_location()[1] == sum( + len(s) for s in self.wrapped_document.lines[self.document.line_count - 1] + ): + event.stop() + event.prevent_default() + self._history_next() + self.cursor_location = (0, 0) elif self.app.is_key_for("input_start", event.key): # Move cursor to start of first line event.stop() diff --git a/cecli/website/docs/config/tui.md b/cecli/website/docs/config/tui.md index 3962766fd40..f56604f4cb6 100644 --- a/cecli/website/docs/config/tui.md +++ b/cecli/website/docs/config/tui.md @@ -50,6 +50,7 @@ tui-config: other: dark: true input-cursor-text-style: "underline" + use_terminal_background: false key_bindings: newline: "shift+enter" submit: "enter" diff --git a/scripts/filter-chat-mode.js b/scripts/filter-chat-mode.js index 919765235ff..a929b6f0c12 100644 --- a/scripts/filter-chat-mode.js +++ b/scripts/filter-chat-mode.js @@ -17,17 +17,42 @@ const fs = require('fs'); const path = require('path'); +/** + * Sort object keys alphabetically (top-level only) + * @param {object} obj - The object to sort + * @returns {object} - New object with sorted keys + */ +function sortObjectKeysTopLevel(obj) { + if (!obj || typeof obj !== 'object' || Array.isArray(obj)) { + return obj; + } + + const sortedObj = {}; + Object.keys(obj).sort().forEach(key => { + sortedObj[key] = obj[key]; + }); + return sortedObj; +} + function filterChatMode(data) { if (Array.isArray(data)) { - // If input is an array, filter objects with mode: "chat" + // If input is an array, filter objects with mode: "chat" or with /v1/chat/completions in supported_endpoints return data.filter(item => - item && typeof item === 'object' && item.mode === 'chat' + item && typeof item === 'object' && + (item.mode === 'chat' || + (item.supported_endpoints && + Array.isArray(item.supported_endpoints) && + item.supported_endpoints.includes('/v1/chat/completions'))) ); } else if (data && typeof data === 'object') { - // If input is an object, filter properties with mode: "chat" + // If input is an object, filter properties with mode: "chat" or with /v1/chat/completions in supported_endpoints const result = {}; for (const [key, value] of Object.entries(data)) { - if (value && typeof value === 'object' && value.mode === 'chat') { + if (value && typeof value === 'object' && + (value.mode === 'chat' || + (value.supported_endpoints && + Array.isArray(value.supported_endpoints) && + value.supported_endpoints.includes('/v1/chat/completions')))) { result[key] = value; } } @@ -80,7 +105,12 @@ function main() { try { const filteredData = filterChatMode(inputData); - const outputJson = JSON.stringify(filteredData, null, 2); + // Sort top-level keys alphabetically if result is an object + const sortedData = typeof filteredData === 'object' && !Array.isArray(filteredData) + ? sortObjectKeysTopLevel(filteredData) + : filteredData; + + const outputJson = JSON.stringify(sortedData, null, 2); if (outputPath) { fs.writeFileSync(outputPath, outputJson, 'utf8'); diff --git a/tests/basic/test_hashline.py b/tests/basic/test_hashline.py index 0adbdf1ad1a..871d058048b 100644 --- a/tests/basic/test_hashline.py +++ b/tests/basic/test_hashline.py @@ -8,7 +8,6 @@ extract_hashline_range, find_hashline_by_exact_match, find_hashline_by_fragment, - find_hashline_range, get_hashline_content_diff, get_hashline_diff, hashline, @@ -24,10 +23,11 @@ def test_int_to_2digit_52_basic(): assert int_to_2digit_52(0) == "aa" assert int_to_2digit_52(1) == "ab" assert int_to_2digit_52(25) == "az" - assert int_to_2digit_52(26) == "aA" - assert int_to_2digit_52(51) == "aZ" + # Note: We now lower case all output, so values >= 26 are lowercase too + assert int_to_2digit_52(26) == "aa" # Was "aA", now lowercase + assert int_to_2digit_52(51) == "az" # Was "aZ", now lowercase assert int_to_2digit_52(52) == "ba" - assert int_to_2digit_52(2703) == "ZZ" # 52^2 - 1 + assert int_to_2digit_52(2703) == "zz" # Was "ZZ", now lowercase def test_int_to_2digit_52_wraparound(): @@ -289,81 +289,6 @@ def test_find_hashline_by_fragment(): assert index is None -def test_find_hashline_range(): - """Test find_hashline_range function.""" - # Create hashed content - original = "Line 1\nLine 2\nLine 3\nLine 4\nLine 5" - hashed = hashline(original) - hashed_lines = hashed.splitlines(keepends=True) - - # Get hash fragments for testing - # Format is |line_numhash|content, so split by "|" gives ["", "line_numhash", "content"] - # The hash fragment is part of the second element - line1_hash = hashed_lines[0].split("|")[1] - line3_hash = hashed_lines[2].split("|")[1] - line5_hash = hashed_lines[4].split("|")[1] - - # Test exact match - # Extract just the hash fragments (last 2 characters) - hash_fragment1 = line1_hash[-2:] # This gives "vm" - hash_fragment3 = line3_hash[-2:] # This gives "Cx" - start_idx, end_idx = find_hashline_range( - hashed_lines, - f"|1{hash_fragment1}|", - f"|3{hash_fragment3}|", - allow_exact_match=True, - ) - assert start_idx == 0 - assert end_idx == 2 - - # Test fragment match (no exact match) - # Extract just the hash fragments (last 2 characters) - hash_fragment1 = line1_hash[-2:] # This gives "vm" - hash_fragment3 = line3_hash[-2:] # This gives "Cx" - start_idx, end_idx = find_hashline_range( - hashed_lines, - f"|99{hash_fragment1}|", # Wrong line number - f"|101{hash_fragment3}|", # Wrong line number - allow_exact_match=True, - ) - assert start_idx == 0 # Should find by fragment - assert end_idx == 2 # Should calculate distance - - # Test with allow_exact_match=False - # Use parse_hashline to extract hash fragments from the hashline strings - # line1_hash is "1vm" (line number + hash fragment), we need to parse it - hash_fragment1, line_num_str1, line_num1 = parse_hashline(f"|{line1_hash}|") - hash_fragment5, line_num_str5, line_num5 = parse_hashline(f"|{line5_hash}|") - start_idx, end_idx = find_hashline_range( - hashed_lines, - f"|1{hash_fragment1}|", - f"|5{hash_fragment5}|", - allow_exact_match=False, - ) - assert start_idx == 0 - assert end_idx == 4 - - # Test error cases - with pytest.raises(HashlineError, match="Start line hash fragment 'zz' not found in file"): - find_hashline_range(hashed_lines, "|1zz|", "|3zz|") - # Test with allow_exact_match=False - # Extract just the hash fragments (last 2 characters) - hash_fragment1 = line1_hash[-2:] # This gives "vm" - hash_fragment5 = line5_hash[-2:] # This gives "BG" - start_idx, end_idx = find_hashline_range( - hashed_lines, - f"|1{hash_fragment1}|", - f"|5{hash_fragment5}|", - allow_exact_match=False, - ) - assert start_idx == 0 - assert end_idx == 4 - - # Test error cases - with pytest.raises(HashlineError, match="Start line hash fragment 'zz' not found in file"): - find_hashline_range(hashed_lines, "|1zz|", "|3zz|") - - def test_apply_hashline_operation_insert(): """Test apply_hashline_operation with insert operation.""" original = "Line 1\nLine 2\nLine 3"