[model-inventory] Model alias inventory update - 2026-07-16

[github-actions]

Summary

Model inventory analysis for 2026-07-16. All major live model families are covered by existing alias patterns. One new semantic alias (search) is proposed. models.json pricing data is current with models.dev baseline; make refresh-models-json would drop raptor-mini (historical entry, not in models.dev catalog). Playwright extraction of the GitHub Docs pricing table was skipped — Chrome sandbox is disabled in this agent environment, so billing multiplier cross-check via docs table could not be performed.

• Providers queried: Anthropic, Gemini (Google), OpenAI, Copilot (via api-proxy reflect)
• Total models found: 9 (Anthropic) + 50 (Gemini) + 219 (OpenAI) + 36 (Copilot reflect) = 314
• Proposed alias changes: 1 (new search alias)
• Pricing gaps found: 0 (no new copilot models missing from models.json)

Provider Model Counts

Provider	Models Available	Status
anthropic	9	✅ ok
gemini	50	✅ ok
openai	219	✅ ok
copilot (reflect)	36	✅ ok

Raw API Fields Discovered

Anthropic (/raw.json → .data[]):

• type, id, display_name, created_at
• max_input_tokens, max_tokens
• capabilities: batch, citations, code_execution, context_management, effort (low/medium/high/xhigh/max), image_input, pdf_input, structured_outputs, thinking (adaptive/enabled)
• No pricing fields in API; costs come from models.dev

OpenAI (/raw.json → .data[]):

• id, object, created (Unix timestamp), owned_by
• No context limits or pricing in the list endpoint; all models are owned_by: "system" or "openai-internal"

Gemini (/raw.json → .models[]):

• name, version, displayName, description
• inputTokenLimit, outputTokenLimit — useful for tier inference
• supportedGenerationMethods — generateContent, countTokens, batchGenerateContent, createCachedContent
• temperature, topP, topK, maxTemperature
• thinking: true flag on capable models (e.g. gemini-2.5-flash, gemini-3.5-flash)

Copilot reflect (/reflect → .endpoints[provider=copilot]):

• provider, base_url, port, configured, models_url, models (list of string IDs)
• No per-model billing multipliers returned by the reflect endpoint in this run (models list is flat string IDs, no billing objects)

models.json Pricing Analysis

Missing from models.json

No new Copilot models are missing. The reflect endpoint returned 36 models; after excluding deprecated IDs (gpt-4o-mini, gpt-4.1, gpt-4o, gpt-5.4-nano, legacy gpt-4*, gpt-3.5-turbo*, text-embedding-*, trajectory-compaction), all remaining reflect models are present in pkg/cli/data/models.json.

Model ID	Provider	Notes
(none)	—	All non-deprecated reflect models are covered

Historical entries not currently returned

The following entries in models.json are absent from live APIs. Retained as historical records:

github-copilot section:

• claude-fable-5 — not in Anthropic raw API or Copilot reflect; likely unreleased/preview
• claude-sonnet-4 — not in reflect (only claude-sonnet-4.5, claude-sonnet-4.6, claude-sonnet-5)
• gemini-3.1-pro-preview — not in Copilot reflect (only gemini-3-flash-preview and gemini-2.5-pro)
• gemini-3.5-flash — not in Copilot reflect (available directly via Google Gemini API)
• gpt-5.2, gpt-5.2-codex — not in Copilot reflect (available via OpenAI API)
• kimi-k2.7-code, raptor-mini — not in reflect or any live provider API

openai section (in models.json, absent from live OpenAI API):

• gpt-3.5-turbo, gpt-4, gpt-4-turbo, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
• gpt-4o, gpt-4o-2024-*, gpt-4o-mini
• gpt-5-chat-latest, gpt-5.1-chat-latest, gpt-5.2-chat-latest, gpt-5.3-chat-latest
• gpt-5.3-codex-spark, o1-mini, o1-preview
• text-embedding-3-large, text-embedding-3-small, text-embedding-ada-002

Inferred vs stored pricing discrepancies

No discrepancies detected. Copilot reflect does not return per-model billing multipliers in this run (models list is flat string IDs). The GitHub Docs pricing table extraction was skipped (Playwright/Chrome unavailable in sandbox). No pricing cross-check was possible beyond models.dev alignment.

Note: make refresh-models-json was run and produced changes (dropped raptor-mini, minor reordering), but those changes were reverted as they are a models.dev catalog sync, not a targeted fix. The refresh can be applied independently when the team decides to pull the latest models.dev snapshot.

Proposed Alias Updates

1. New search alias for GPT search API models

What: Add a search alias covering gpt-5-search-api and future search-optimized variants.

Why: OpenAI now exposes gpt-5-search-api (and gpt-5-search-api-2025-10-14 dated variant) in the live API. This is a distinct capability family (real-time web search augmented generation). No alias covers it today. Workflow authors who want to route to search-capable models have no ergonomic handle.

Syntax:

{
  "search": [
    "copilot/gpt-5*search*",
    "openai/gpt-5*search*",
    "openai/gpt-4o-search*"
  ]
}

2. No changes needed to existing aliases

All other new models observed in the live inventories are already covered:

New Live Model	Covered By
claude-sonnet-5 (Anthropic/Copilot)	sonnet → copilot/*sonnet*
claude-opus-4.7, claude-opus-4.8	opus → copilot/*opus*
gpt-5.5, gpt-5.6-luna/sol/terra	gpt-5.5, gpt-5.6 aliases
gpt-5-pro, gpt-5.4-pro, gpt-5.5-pro	gpt-5-pro → copilot/gpt-5*pro*
gemini-3.5-flash	gemini-3.5-flash alias
gemini-3.1-flash-lite	gemini-3.1-flash → copilot/gemini-3.1*flash*
gemini-3.1-flash-lite-image	vision → copilot/gemini-*image*
o3-pro, o3-deep-research, o4-mini-deep-research	reasoning / deep-research aliases
mai-code-1-flash-picker	mai-code alias
gpt-image-1.5, gpt-image-2	image-generation → openai/gpt-image*
antigravity-preview-05-2026	antigravity alias

Full Model Lists by Provider

Anthropic (9 models from API)

claude-haiku-4-5-20251001
claude-opus-4-1-20250805
claude-opus-4-5-20251101
claude-opus-4-6
claude-opus-4-7
claude-opus-4-8
claude-sonnet-4-5-20250929
claude-sonnet-4-6
claude-sonnet-5

Copilot reflect (36 models)

claude-haiku-4.5        claude-opus-4.5         claude-opus-4.6
claude-opus-4.7         claude-opus-4.8         claude-sonnet-4.5
claude-sonnet-4.6       claude-sonnet-5         gemini-2.5-pro
gemini-3-flash-preview  gpt-3.5-turbo           gpt-3.5-turbo-0613
gpt-4                   gpt-4-0613              gpt-4-o-preview
gpt-4.1                 gpt-4.1-2025-04-14      gpt-4o
gpt-4o-2024-05-13       gpt-4o-2024-08-06       gpt-4o-2024-11-20
gpt-4o-mini             gpt-4o-mini-2024-07-18  gpt-5-mini
gpt-5.3-codex           gpt-5.4                 gpt-5.4-mini
gpt-5.5                 gpt-5.6-luna            gpt-5.6-sol
gpt-5.6-terra           mai-code-1-flash-picker text-embedding-3-small
text-embedding-3-small-inference                text-embedding-ada-002
trajectory-compaction

Gemini (50 models — text-generation relevant subset)

antigravity-preview-05-2026     deep-research-max-preview-04-2026
deep-research-preview-04-2026   deep-research-pro-preview-12-2025
gemini-2.0-flash                gemini-2.0-flash-lite
gemini-2.5-flash                gemini-2.5-flash-image
gemini-2.5-flash-lite           gemini-2.5-pro
gemini-3-flash-preview          gemini-3-pro-image
gemini-3-pro-preview            gemini-3.1-flash-image
gemini-3.1-flash-lite           gemini-3.1-flash-lite-image
gemini-3.1-flash-lite-preview   gemini-3.1-pro-preview
gemini-3.1-pro-preview-customtools                gemini-3.5-flash
gemini-omni-flash-preview       gemma-4-26b-a4b-it
gemma-4-31b-it                  nano-banana-pro-preview

(Also: embedding, TTS, audio, imagen, veo, lyria, robotics, computer-use models)

OpenAI (219 models — notable GPT-5 and reasoning subset)

gpt-5              gpt-5-codex        gpt-5-mini         gpt-5-nano
gpt-5-pro          gpt-5-search-api   gpt-5.1            gpt-5.1-codex
gpt-5.1-codex-max  gpt-5.1-codex-mini gpt-5.2            gpt-5.2-codex
gpt-5.2-pro        gpt-5.3-codex      gpt-5.4            gpt-5.4-mini
gpt-5.4-nano       gpt-5.4-pro        gpt-5.5            gpt-5.5-pro
gpt-5.6-luna       gpt-5.6-sol        gpt-5.6-terra
o1     o1-pro     o3     o3-mini     o3-pro     o4-mini
o3-deep-research   o4-mini-deep-research
gpt-image-1        gpt-image-1-mini   gpt-image-1.5      gpt-image-2
chatgpt-image-latest

Notes

• Playwright unavailable: Chrome sandbox is disabled in the agent Docker environment (FATAL: chrome-sandbox not setuid). The GitHub Docs pricing table (models-and-pricing) could not be scraped. Billing multiplier validation against the docs table was skipped this run.
• Copilot reflect billing: The reflect endpoint returns models as a flat list of string IDs with no billing.multiplier fields. Per-model multiplier data is not available via this endpoint for cross-checking.
• raptor-mini: Present in models.json (github-copilot section) but absent from reflect, Anthropic API, and models.dev catalog. Treated as historical; retained until explicitly removed by a human.
• make refresh-models-json: Running this command would sync to the current models.dev catalog snapshot, which drops raptor-mini and reorders entries. This is safe to run but should be a deliberate action.

Generated by 📦 Daily Model Inventory Checker · 92.8 AIC · ⌖ 9.16 AIC · ⊞ 8.5K · ◷

• expires on Jul 22, 2026, 4:21 PM UTC-08:00

[github-actions]

This issue is being closed as outdated. A newer issue has been created: #46107

View newer issue

---

This action was performed automatically by the Daily Model Inventory Checker workflow.