Skip to content

feat(providers): add DeepInfra preset #747

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
olddonkey wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

feat(providers): add DeepInfra preset #747

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs-site/src/content/docs/getting-started/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ ocx init

`ocx init` walks you through:

1. **Pick a provider** — choose one of the 50 built-in registry presets or `custom` to type a base
1. **Pick a provider** — choose one of the 61 built-in registry presets or `custom` to type a base
URL and adapter.
2. **API key** — paste a key, or reference an environment variable like `${ANTHROPIC_API_KEY}`.
3. **Default model** — for key, local, and custom providers, accept the preset or enter a model id.
Expand Down
8 changes: 7 additions & 1 deletion docs-site/src/content/docs/guides/providers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@ selectors, then retry. Signing in from a machine with no existing `kiro-cli` ses

## 3. API-key catalog

opencodex ships 53 built-in presets: 42 key-based, seven OAuth, three local, and the default
opencodex ships 61 built-in presets: 50 key-based, seven OAuth, three local, and the default
ChatGPT-forward preset. The dashboard's **Add provider** picker opens a key provider's dashboard,
validates the key, and stores it. Notable entries:

Expand All @@ -207,6 +207,7 @@ validates the key, and stores it. Notable entries:
| MiniMax · MiniMax (CN) | `https://api.minimax.io/v1` · `https://api.minimaxi.com/v1` |
| DeepSeek | `https://api.deepseek.com` |
| Cerebras | `https://api.cerebras.ai/v1` |
| DeepInfra | `https://api.deepinfra.com/v1/openai` |
Comment thread
coderabbitai[bot] marked this conversation as resolved.
| Together | `https://api.together.xyz/v1` |
| Fireworks | `https://api.fireworks.ai/inference/v1` |
| Moonshot (Kimi API) · Kimi (coding) | `https://api.moonshot.ai/v1` · `https://api.kimi.com/coding/v1` |
Expand All @@ -226,6 +227,11 @@ validates the key, and stores it. Notable entries:
Most use the `openai-chat` adapter with a bearer key; a few that expose only an Anthropic-compatible
endpoint (e.g. **Xiaomi MiMo**) use the `anthropic` adapter (`x-api-key`).

**DeepInfra discovery.** The key-based `deepinfra` OpenAI Chat Completions provider uses the
`openai-chat` adapter with a Bearer API key. Its registry-owned model-list URL keeps only rows tagged
`chat`, preserves slash-containing native model ids, and caps live discovery at 512 KiB and 512 raw
rows. Create keys in [DeepInfra's dashboard](https://deepinfra.com/dash/api_keys).

> **Tencent Cloud Coding Plan usage restriction:** Tencent documents this subscription for
> interactive coding tools only. General API automation, custom application backends, and
> non-interactive batch use are prohibited and may cause the plan key to be suspended.
Expand Down
2 changes: 1 addition & 1 deletion docs-site/src/content/docs/ja/getting-started/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ ocx init

`ocx init` は次の手順を案内します:

1. **プロバイダー選択** — 組み込みレジストリのプリセット 50 個から一つを選ぶか、`custom` を選んで
1. **プロバイダー選択** — 組み込みレジストリのプリセット 61 個から一つを選ぶか、`custom` を選んで
base URL とアダプターを直接入力します。
2. **API キー** — キーを貼り付けるか、`${ANTHROPIC_API_KEY}` のような環境変数を参照します。
3. **デフォルトモデル** — API キー、ローカル、custom プロバイダーではプリセット値を使うかモデル ID を直接入力します。
Expand Down
8 changes: 7 additions & 1 deletion docs-site/src/content/docs/ja/guides/providers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,7 @@ Kiro のログインには Kiro CLI が必要です。Unix では `curl -fsSL ht

## 3. API キーカタログ

opencodex v2.7.1 には組み込みプリセットが 50 個含まれています。キー方式 40、OAuth 6、ローカル 3、
opencodex には組み込みプリセットが 61 個含まれています。キー方式 50、OAuth 7、ローカル 3、
デフォルト ChatGPT 転送プリセット 1 です。ダッシュボードの **Add provider** ピッカーはキー発行ページを開き、
入力したキーを検証した後保存します。主な項目は以下のとおりです:

Expand All @@ -133,6 +133,7 @@ opencodex v2.7.1 には組み込みプリセットが 50 個含まれていま
| MiniMax · MiniMax (CN) | `https://api.minimax.io/v1` · `https://api.minimaxi.com/v1` |
| DeepSeek | `https://api.deepseek.com` |
| Cerebras | `https://api.cerebras.ai/v1` |
| DeepInfra | `https://api.deepinfra.com/v1/openai` |
| Together | `https://api.together.xyz/v1` |
| Fireworks | `https://api.fireworks.ai/inference/v1` |
| Moonshot (Kimi API) · Kimi (coding) | `https://api.moonshot.ai/v1` · `https://api.kimi.com/coding/v1` |
Expand All @@ -152,6 +153,11 @@ opencodex v2.7.1 には組み込みプリセットが 50 個含まれていま
大半は bearer キーと共に `openai-chat` アダプターを使い、Anthropic 互換エンドポイントのみを公開する一部
(例: **Xiaomi MiMo**)は `anthropic` アダプター(`x-api-key`)を使います。

**DeepInfra の discovery:** キー方式の OpenAI Chat Completions プロバイダー `deepinfra` は、
`openai-chat` アダプターと Bearer API キーを使います。registry が所有する DeepInfra のモデル一覧 URL から
`chat` タグを持つ行だけを残し、スラッシュを含むネイティブモデル ID を保持します。live discovery は
512 KiB、raw 512 行に制限します。キーは [DeepInfra dashboard](https://deepinfra.com/dash/api_keys) で作成します。

> **Tencent Cloud Coding Plan の利用制限:** Tencent はこのサブスクリプションを対話型
> コーディングツール専用としています。一般的な API 自動化、カスタムアプリのバックエンド、
> 非対話型バッチ利用は禁止されており、プランキーが停止される場合があります。
Expand Down
2 changes: 1 addition & 1 deletion docs-site/src/content/docs/ko/getting-started/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ ocx init

`ocx init`은 다음 과정을 안내합니다:

1. **프로바이더 선택** — 내장 레지스트리 프리셋 50개 중 하나를 고르거나, `custom`을 선택해
1. **프로바이더 선택** — 내장 레지스트리 프리셋 61개 중 하나를 고르거나, `custom`을 선택해
base URL과 adapter를 직접 입력합니다.
2. **API 키** — 키를 붙여넣거나, `${ANTHROPIC_API_KEY}`와 같은 환경 변수를 참조합니다.
3. **기본 모델** — API 키, 로컬, custom 프로바이더에서는 프리셋 값을 쓰거나 모델 id를 직접 입력합니다.
Expand Down
8 changes: 7 additions & 1 deletion docs-site/src/content/docs/ko/guides/providers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,7 @@ Kiro 로그인에는 Kiro CLI가 필요합니다. Unix에서는 `curl -fsSL http

## 3. API 키 카탈로그

opencodex v2.7.1에는 빌트인 프리셋이 50개 들어 있습니다. 키 방식 40개, OAuth 6개, 로컬 3개,
opencodex에는 빌트인 프리셋이 61개 들어 있습니다. 키 방식 50개, OAuth 7개, 로컬 3개,
기본 ChatGPT 포워드 프리셋 1개입니다. 대시보드의 **Add provider** 선택기는 키 발급 페이지를 열고,
입력한 키를 검증한 뒤 저장합니다. 주요 항목은 다음과 같습니다:

Expand All @@ -133,6 +133,7 @@ opencodex v2.7.1에는 빌트인 프리셋이 50개 들어 있습니다. 키 방
| MiniMax · MiniMax (CN) | `https://api.minimax.io/v1` · `https://api.minimaxi.com/v1` |
| DeepSeek | `https://api.deepseek.com` |
| Cerebras | `https://api.cerebras.ai/v1` |
| DeepInfra | `https://api.deepinfra.com/v1/openai` |
| Together | `https://api.together.xyz/v1` |
| Fireworks | `https://api.fireworks.ai/inference/v1` |
| Moonshot (Kimi API) · Kimi (coding) | `https://api.moonshot.ai/v1` · `https://api.kimi.com/coding/v1` |
Expand All @@ -152,6 +153,11 @@ opencodex v2.7.1에는 빌트인 프리셋이 50개 들어 있습니다. 키 방
대부분은 bearer 키와 함께 `openai-chat` 어댑터를 사용하며, Anthropic 호환 엔드포인트만 노출하는 일부
(예: **Xiaomi MiMo**)는 `anthropic` 어댑터(`x-api-key`)를 사용합니다.

**DeepInfra 검색:** 키 기반 OpenAI Chat Completions 제공자인 `deepinfra`는 `openai-chat` 어댑터와
Bearer API 키를 사용합니다. registry가 소유하는 DeepInfra 모델 목록 URL에서 `chat` 태그가 있는 행만
유지하고, 슬래시가 포함된 네이티브 모델 ID를 보존합니다. live discovery는 512 KiB 및 raw 512행으로
제한합니다. 키는 [DeepInfra dashboard](https://deepinfra.com/dash/api_keys)에서 생성합니다.

> **Tencent Cloud Coding Plan 사용 제한:** Tencent는 이 구독을 대화형 코딩 도구 전용으로
> 안내합니다. 일반 API 자동화, 사용자 애플리케이션 백엔드 및 비대화형 일괄 호출은 금지되며
> 플랜 키가 정지될 수 있습니다.
Expand Down
2 changes: 1 addition & 1 deletion docs-site/src/content/docs/ru/getting-started/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ ocx init

`ocx init` проведёт вас по следующим шагам:

1. **Выбор провайдера** — выберите один из 50 встроенных пресетов реестра или `custom`, чтобы
1. **Выбор провайдера** — выберите один из 61 встроенного пресета реестра или `custom`, чтобы
ввести базовый URL и адаптер вручную.
2. **API-ключ** — вставьте ключ или сошлитесь на переменную окружения вида `${ANTHROPIC_API_KEY}`.
3. **Модель по умолчанию** — для провайдеров с ключом, локальных и `custom` примите значение из
Expand Down
9 changes: 8 additions & 1 deletion docs-site/src/content/docs/ru/guides/providers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,7 @@ OAuth-провайдеры, чьи учётные данные содержат

## 3. Каталог API-ключей

opencodex поставляется с 53 встроенными пресетами: 42 на основе ключей, семь OAuth, три локальных и
opencodex поставляется с 61 встроенным пресетом: 50 на основе ключей, семь OAuth, три локальных и
пресет ChatGPT-форварда по умолчанию. Селектор **Add provider** в дашборде открывает страницу
выдачи ключей провайдера, проверяет ключ и сохраняет его. Наиболее заметные записи:

Expand All @@ -143,6 +143,7 @@ opencodex поставляется с 53 встроенными пресетам
| MiniMax · MiniMax (CN) | `https://api.minimax.io/v1` · `https://api.minimaxi.com/v1` |
| DeepSeek | `https://api.deepseek.com` |
| Cerebras | `https://api.cerebras.ai/v1` |
| DeepInfra | `https://api.deepinfra.com/v1/openai` |
| Together | `https://api.together.xyz/v1` |
| Fireworks | `https://api.fireworks.ai/inference/v1` |
| Moonshot (Kimi API) · Kimi (coding) | `https://api.moonshot.ai/v1` · `https://api.kimi.com/coding/v1` |
Expand All @@ -163,6 +164,12 @@ opencodex поставляется с 53 встроенными пресетам
только Anthropic-совместимую конечную точку (например, **Xiaomi MiMo**), используют адаптер
`anthropic` (`x-api-key`).

**Discovery для DeepInfra.** `deepinfra` — провайдер OpenAI Chat Completions с аутентификацией по
ключу; он использует адаптер `openai-chat` и Bearer API-ключ. Принадлежащий registry URL списка
моделей DeepInfra оставляет только строки с тегом `chat`, сохраняет нативные id моделей со знаком
`/` и ограничивает live discovery 512 KiB и 512 исходными строками. Ключи создаются в
[дашборде DeepInfra](https://deepinfra.com/dash/api_keys).

> **Ограничение Tencent Cloud Coding Plan:** Tencent разрешает использовать эту подписку только
> в интерактивных инструментах программирования. Автоматизация общего API, серверы пользовательских
> приложений и неинтерактивные пакетные вызовы запрещены и могут привести к блокировке ключа плана.
Expand Down
2 changes: 1 addition & 1 deletion docs-site/src/content/docs/zh-cn/getting-started/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ ocx init

`ocx init` 会引导你完成:

1. **选择 provider** —— 从内置 registry 的 50 个预设中选择一个，或选择 `custom` 手动输入
1. **选择 provider** —— 从内置 registry 的 61 个预设中选择一个，或选择 `custom` 手动输入
base URL 和 adapter。
2. **API key** —— 粘贴一个 key,或引用一个环境变量,例如 `${ANTHROPIC_API_KEY}`。
3. **默认模型** —— 对于 API key、本地和 custom provider，可接受预设值或输入模型 id。
Expand Down
8 changes: 7 additions & 1 deletion docs-site/src/content/docs/zh-cn/guides/providers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ Kiro 登录需要 Kiro CLI：Unix 使用 `curl -fsSL https://cli.kiro.dev/instal

## 3. API 密钥目录

opencodex v2.7.1 内置 50 个预设：40 个密钥预设、6 个 OAuth 预设、3 个本地预设，以及默认的
opencodex 内置 61 个预设：50 个密钥预设、7 个 OAuth 预设、3 个本地预设，以及默认的
ChatGPT 转发预设。仪表盘的 **Add provider** 选择器会打开密钥提供商的控制台，验证并保存密钥。
主要条目包括：

Expand All @@ -125,6 +125,7 @@ ChatGPT 转发预设。仪表盘的 **Add provider** 选择器会打开密钥提
| MiniMax · MiniMax (CN) | `https://api.minimax.io/v1` · `https://api.minimaxi.com/v1` |
| DeepSeek | `https://api.deepseek.com` |
| Cerebras | `https://api.cerebras.ai/v1` |
| DeepInfra | `https://api.deepinfra.com/v1/openai` |
| Together | `https://api.together.xyz/v1` |
| Fireworks | `https://api.fireworks.ai/inference/v1` |
| Moonshot (Kimi API) · Kimi (coding) | `https://api.moonshot.ai/v1` · `https://api.kimi.com/coding/v1` |
Expand All @@ -143,6 +144,11 @@ ChatGPT 转发预设。仪表盘的 **Add provider** 选择器会打开密钥提

大多数使用带 bearer 密钥的 `openai-chat` adapter；少数仅暴露 Anthropic 兼容端点的提供商（例如 **Xiaomi MiMo**）使用 `anthropic` adapter（`x-api-key`）。

**DeepInfra 发现：**`deepinfra` 是使用 `openai-chat` adapter 和 Bearer API 密钥的密钥型
OpenAI Chat Completions 提供商。registry 固定的 DeepInfra 模型列表 URL 仅保留带 `chat` 标签的记录，
同时保留含 `/` 的原生模型 id，并把实时发现限制为 512 KiB 和 512 条原始记录。
密钥可在 [DeepInfra 控制台](https://deepinfra.com/dash/api_keys)创建。

> **腾讯云 Coding Plan 使用限制：**腾讯将此订阅限定为交互式编程工具使用。禁止通用 API
> 自动化、自定义应用后端和非交互式批量调用；违规使用可能导致套餐密钥被停用。

Expand Down
1 change: 1 addition & 0 deletions src/codex/catalog/provider-fetch.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -345,6 +345,7 @@ export function catalogHintsFromModelsApiItem(providerName: string, item: Provid
const contextWindow =
positiveSafeInteger(
limits?.max_context_length,
metadata?.context_length,
item.context_length,
item.context_size,
item.max_model_len,
Expand Down
21 changes: 21 additions & 0 deletions src/providers/registry.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -829,6 +829,27 @@ export const PROVIDER_REGISTRY: readonly ProviderRegistryEntry[] = [
},
// llama-3.3-70b was deprecated by Cerebras on 2026-02-16. Evidence: devlog/_plan/260710_provider_hardening/003_research_aggregators.md.
{ id: "cerebras", label: "Cerebras", baseUrl: "https://api.cerebras.ai/v1", adapter: "openai-chat", authKind: "key", dashboardUrl: "https://cloud.cerebras.ai/platform/apikeys", defaultModel: "gpt-oss-120b" },
{
id: "deepinfra",
label: "DeepInfra",
baseUrl: "https://api.deepinfra.com/v1/openai",
adapter: "openai-chat",
authKind: "key",
dashboardUrl: "https://deepinfra.com/dash/api_keys",
liveModels: true,
preserveCustomDestination: true,
modelDiscovery: {
// DeepInfra documents the OpenAI model catalog outside the chat-compatible `/v1/openai`
// namespace, so keep this destination registry-owned instead of deriving it from baseUrl.
url: "https://api.deepinfra.com/v1/models",
maxResponseBytes: 512 * 1024,
maxModels: 512,
filter: {
allOf: [{ path: ["metadata", "tags"], containsAny: ["chat"] }],
},
},
note: "OpenAI-compatible chat models only; live discovery excludes non-chat rows from DeepInfra's mixed model catalog.",
},
// FREEZE 2026-07-10: exact serverless ids remain auth-gated/unverified. Evidence: devlog/_plan/260710_provider_hardening/003_research_aggregators.md.
{ id: "together", label: "Together", baseUrl: "https://api.together.xyz/v1", adapter: "openai-chat", authKind: "key", dashboardUrl: "https://api.together.xyz/settings/api-keys" },
{ id: "fireworks", label: "Fireworks", baseUrl: "https://api.fireworks.ai/inference/v1", adapter: "openai-chat", authKind: "key", dashboardUrl: "https://fireworks.ai/account/api-keys" },
Expand Down
Loading
Loading