# Protocol compatibility (/en/docs/developers/model/concepts/protocols)



Protocol compatibility lets you keep your client’s request format. It does not mean every model supports every protocol or every official feature. Check the model’s `supported_apis` and endpoint support notes.

One address, `https://api.deepraxis.com`, with one entry per protocol family:

| Entry        | Protocols           |
| ------------ | ------------------- |
| `/openai`    | OpenAI protocols    |
| `/anthropic` | Anthropic protocols |
| `/google`    | Google Gemini API   |

## OpenAI Chat Completions [#openai-chat-completions]

`POST /openai/v1/chat/completions`. A common chat protocol; streaming (SSE), tool calls, and multimodal input depend on the model. See [Chat API](/docs/api/compatible/openai/createChatCompletion) for field support and [session affinity](/docs/developers/model/concepts/session-affinity) for session identifiers.

## OpenAI Responses [#openai-responses]

`POST /openai/v1/responses` plus retrieve / delete / cancel / input\_items. OpenAI's stateful next-generation protocol; agents like Codex use it. See [Responses API](/docs/api/compatible/openai/createResponse) for support. Response compaction and input-token counting endpoints are not implemented and return 501.

## OpenAI Files [#openai-files]

`/openai/v1/files`: upload `user_data` files for later requests; list, retrieve metadata, download, delete.

## OpenAI Images [#openai-images]

`POST /openai/v1/images/generations`: use a model that declares image-generation support in the catalog.

## Anthropic Messages [#anthropic-messages]

`POST /anthropic/v1/messages`. Claude Code and the Anthropic SDK use it. See [Messages API](/docs/api/compatible/anthropic/createMessage) for support.

## Anthropic Files [#anthropic-files]

`/anthropic/v1/files`: upload, list, retrieve metadata, delete; **uploads are not downloadable** (same as upstream).

## Google Gemini API (generateContent) [#google-gemini-api-generatecontent]

`POST /google/v1beta/models/{model}:generateContent`. Currently image generation and editing with the native Gemini protocol.

## Model catalog [#model-catalog]

Use `GET /openai/v1/models?api=responses` to find Responses models; `api=chat,embeddings` matches either API. The native catalog `GET /model/v1/models` and its model detail endpoint expose each model’s `supported_apis`; filter the native list with `?supported_api=openai.responses`.

`GET /openai/v1/models`: the models this key can call, OpenAI-shaped; clients such as Kilo Code discover models through it.

Anthropic clients use `GET /anthropic/v1/models`; Google clients use `GET /google/v1beta/models`. Each returns the corresponding protocol’s model list.

## Standardized paths [#standardized-paths]

Every entry also has a standardized long path `/v1/router/<vendor>/...` with identical semantics — see the [API reference](/docs/api/compatible).

→ Go deeper: [OpenAI-compatible API](/docs/developers/model/guides/openai-compatible) · [Anthropic-compatible API](/docs/developers/model/guides/anthropic-compatible)

[API reference →](/docs/api/compatible/openai) · [Cookbook →](/docs/cookbook)