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

# Overview of Text Series

> The text series covers OpenAI-compatible text interfaces, Claude native message interface, Gemini native interface, OpenAI Responses, multimodal input, model list, and Realtime.

# Text Series

<CardGroup cols={2}>
  <Card title="Model Support Matrix" icon="table-cells" href="/en/texts/model-matrix">
    View the support scope of the text series, typical model families, and recommended entry points by protocol style and capability type.
  </Card>

  <Card title="Chat Completions" icon="messages-square" href="/en/texts/chat-completions-stream">
    `POST /v1/chat/completions`, suitable for chat, Agents, long-text generation, and multimodal input.
  </Card>

  <Card title="OpenAI Responses" icon="bot" href="/en/texts/openai-responses">
    `POST /v1/responses`, suitable for tool calling, structured outputs, and context continuation.
  </Card>

  <Card title="Claude Native" icon="file-text" href="/en/texts/claude-messages">
    `POST /v1/messages`, preserving the Anthropic Messages protocol.
  </Card>

  <Card title="Gemini Native" icon="sparkles" href="/en/texts/gemini-native">
    `POST /v1beta/models/{model}:{action}` and `GET /v1beta/models`.
  </Card>
</CardGroup>

## Authentication

Most text relay interfaces use a Bearer Token:

```http theme={null}
Authorization: Bearer YOUR_API_KEY
```

The Claude native format also supports:

```http theme={null}
x-api-key: YOUR_API_KEY
anthropic-version: 2023-06-01
```

The Gemini native format also supports:

```http theme={null}
x-goog-api-key: YOUR_API_KEY
```

## Interface List

| Method | Path                              | Page                                                                                   | Description                                                                                      |
| ------ | --------------------------------- | -------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
| `POST` | `/v1/chat/completions`            | [Chat Completions Interface (streaming by default)](./chat-completions-stream)         | OpenAI Chat Completions-compatible format, the documentation shows the streaming call by default |
| `POST` | `/v1/chat/completions`            | [Chat Completions Interface (non-streaming by default)](./chat-completions-non-stream) | Non-streaming usage of the same route                                                            |
| `POST` | `/v1/completions`                 | [Text Completions Interface](./completions)                                            | Legacy Completions-compatible format                                                             |
| `POST` | `/v1/messages`                    | [Claude Messages Interface](./claude-messages)                                         | Anthropic Messages native protocol                                                               |
| `POST` | `/v1/responses`                   | [OpenAI Multimodal Responses Interface](./openai-responses)                            | Responses API                                                                                    |
| `POST` | `/v1/responses/compact`           | [OpenAI Multimodal Responses Interface](./openai-responses#上下文压缩)                      | Context compression                                                                              |
| `GET`  | `/v1/realtime`                    | [Realtime Interface](./realtime)                                                       | OpenAI Realtime-compatible WebSocket                                                             |
| `GET`  | `/v1/models`                      | [Model List](./models)                                                                 | OpenAI/Claude/Gemini-compatible model list                                                       |
| `GET`  | `/v1/models/{model}`              | [Model List](./models)                                                                 | Single model query                                                                               |
| `GET`  | `/v1beta/models`                  | [Gemini Native Format](./gemini-native)                                                | Gemini native model list                                                                         |
| `POST` | `/v1beta/models/{model}:{action}` | [Gemini Native Format](./gemini-native)                                                | Gemini native inference and image/video-related actions                                          |
| `GET`  | `/v1beta/openai/models`           | [Model List](./models)                                                                 | Gemini-compatible model list                                                                     |
| `POST` | `/pg/chat/completions`            | [Chat Completions Interface (non-streaming by default)](./chat-completions-non-stream) | Playground debugging route, using login session instead of API Key                               |

## Common Error Codes

| Status Code | Description                                                                                                          |
| ----------- | -------------------------------------------------------------------------------------------------------------------- |
| `400`       | Invalid request parameters, such as a non-existent model name, invalid message structure, or invalid tool definition |
| `401`       | Missing, invalid, or expired API Key                                                                                 |
| `402`       | Quota insufficient                                                                                                   |
| `413`       | Request body too large                                                                                               |
| `429`       | Request rate limit exceeded                                                                                          |
| `500`       | Internal server error                                                                                                |
| `503`       | Upstream unavailable or the system is temporarily overloaded                                                         |

<Tip>
  If an interface page marks a parameter as "optional," it does not mean that all models support that field. Whether it is ultimately passed through and takes effect still depends on the capabilities of the actual channel it is distributed to.
</Tip>

## Recommended Reading Order

1. [Text Model Support Matrix](./model-matrix)
2. [Chat Completions Interface (streaming by default)](./chat-completions-stream)
3. [OpenAI Multimodal Responses Interface](./openai-responses)
4. [Claude Messages Interface](./claude-messages)
5. [Gemini Native Format](./gemini-native)
6. [Model List](./models)
7. [Realtime Interface](./realtime)