> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anyone.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Anyone REST endpoints: overview and base URL

> Anyone exposes a unified REST API compatible with OpenAI, Anthropic Claude, and Google Gemini formats. Use one API key to reach every endpoint.

Anyone provides a single HTTP gateway that accepts requests in OpenAI, Anthropic Claude, and Google Gemini formats and routes them to the appropriate upstream provider. You authenticate with an API key you create in the dashboard, and Anyone handles format translation automatically — so you can point an existing OpenAI client at Anyone without any code changes.

## Base URL

```
https://api.anyone.ai
```

All endpoints below are relative to this base URL. Use your API key in the `Authorization` header for all requests.

## Endpoints

<CardGroup cols={2}>
  <Card title="Chat & Completions" icon="message" href="/api-reference/chat-completions">
    OpenAI-compatible chat and text completions via `POST /v1/chat/completions` and `POST /v1/completions`.
  </Card>

  <Card title="OpenAI Responses" icon="bolt" href="/api-reference/responses">
    OpenAI Responses format via `POST /v1/responses`.
  </Card>

  <Card title="Claude Messages" icon="robot" href="/api-reference/claude-messages">
    Anthropic Claude Messages format via `POST /v1/messages`.
  </Card>

  <Card title="Gemini Chat" icon="google" href="/api-reference/gemini-chat">
    Google Gemini generateContent format via `POST /v1beta/models/{model}:generateContent`.
  </Card>

  <Card title="Images" icon="image" href="/api-reference/images">
    Image generation and editing via `POST /v1/images/generations` and `POST /v1/images/edits`.
  </Card>

  <Card title="Audio" icon="microphone" href="/api-reference/audio">
    Speech-to-text, translation, and text-to-speech via the `/v1/audio/*` endpoints.
  </Card>

  <Card title="Video" icon="video" href="/api-reference/video">
    Video generation tasks via Sora-compatible, Kling, Jimeng, Doubao, and Vidu providers.
  </Card>

  <Card title="Embeddings" icon="brackets-curly" href="/api-reference/embeddings">
    Text embeddings via `POST /v1/embeddings`.
  </Card>

  <Card title="Rerank" icon="arrow-up-wide-short" href="/api-reference/rerank">
    Document reranking (Cohere/Jina format) via `POST /v1/rerank`.
  </Card>

  <Card title="Realtime" icon="waveform" href="/api-reference/realtime">
    WebSocket-based realtime conversations via `GET /v1/realtime`.
  </Card>

  <Card title="Models" icon="list" href="/api-reference/models">
    List available models via `GET /v1/models`.
  </Card>
</CardGroup>

## Common request headers

| Header              | Required                 | Description                                                |
| ------------------- | ------------------------ | ---------------------------------------------------------- |
| `Authorization`     | Yes (for most endpoints) | Bearer token: `Authorization: Bearer YOUR_TOKEN`           |
| `Content-Type`      | Yes                      | Set to `application/json` for all JSON request bodies      |
| `x-api-key`         | Yes (Claude endpoints)   | Your Anyone API key when calling `/v1/messages`            |
| `anthropic-version` | Yes (Claude endpoints)   | Must be `2023-06-01` when using the Claude Messages format |
| `x-goog-api-key`    | Yes (Gemini endpoints)   | Your Anyone API key when calling `/v1beta/models/*`        |

See [Authentication](/api-reference/authentication) for a full explanation of which header to use with each endpoint.

## HTTP status codes

| Code  | Meaning                                                                        |
| ----- | ------------------------------------------------------------------------------ |
| `200` | Request succeeded. The response body contains the model output.                |
| `400` | Bad request. The request body is malformed or missing required fields.         |
| `401` | Unauthorized. The API key is missing or invalid.                               |
| `403` | Forbidden. The API key does not have permission to use the requested model.    |
| `429` | Too many requests. You have exceeded the rate limit for this API key or model. |
| `500` | Internal server error. An unexpected error occurred on the Anyone server.      |
| `503` | Service unavailable. No upstream channel is available for the requested model. |