### Python 调用 EveryLinks 聊天补全

Source: https://tokens.everylinks.com/docs

使用 OpenAI Python SDK 调用 EveryLinks 的 OpenAI 兼容接口。需要先注册账户并获取 API Key，将 <EVERYLINKS_API_KEY> 替换为实际密钥。

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://gw.everylinks.com/v1",
    api_key="<EVERYLINKS_API_KEY>"
)

completion = client.chat.completions.create(
    model="doubao/doubao-seed-2.0-pro",
    messages=[
        {"role": "user", "content": "你好，请介绍一下自己"}
    ]
)

print(completion.choices[0].message.content)
```

--------------------------------

### HTTP 请求聊天补全接口

Source: https://tokens.everylinks.com/docs

向 /v1/chat/completions 发送 POST 请求，使用 OpenAI 兼容的请求体。支持所有 OpenAI 参数，如 temperature、top_p、max_tokens、tools、response_format 等。

```http
POST /v1/chat/completions

{
  "model": "doubao/doubao-seed-2.0-pro",
  "messages": [
    {"role": "system", "content": "你是一个有用的助手。"},
    {"role": "user", "content": "你好！"}
  ],
  "temperature": 0.7,
  "max_tokens": 1000,
  "stream": false
}
```

--------------------------------

### POST /v1/chat/completions

Source: https://tokens.everylinks.com/docs

Creates a chat completion using the OpenAI-compatible interface. This endpoint accepts a list of messages and model parameters, and returns a completion response.

```APIDOC
## POST /v1/chat/completions

### Description
Creates a chat completion using the OpenAI-compatible interface. This endpoint accepts a list of messages and model parameters, and returns a completion response.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model identifier, e.g., "doubao/doubao-seed-2.0-pro".
- **messages** (array) - Required - An array of message objects with role and content.
- **temperature** (number) - Optional - Sampling temperature, e.g., 0.7.
- **max_tokens** (integer) - Optional - Maximum number of tokens to generate.
- **stream** (boolean) - Optional - If true, uses streaming response.
- **top_p** (number) - Optional - Nucleus sampling parameter. Supported.
- **tools** (array) - Optional - Tool definitions for function calling. Supported.
- **response_format** (object) - Optional - Response format specification. Supported.

### Request Example
{
  "model": "doubao/doubao-seed-2.0-pro",
  "messages": [
    {"role": "system", "content": "你是一个有用的助手。"},
    {"role": "user", "content": "你好！"}
  ],
  "temperature": 0.7,
  "max_tokens": 1000,
  "stream": false
}

### Response
#### Success Response (200)
The response is a chat completion object with choices containing the generated message content.

#### Response Example
{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "你好！有什么我可以帮助你的吗？"
      }
    }
  ]
}
```

--------------------------------

### curl 流式输出聊天补全

Source: https://tokens.everylinks.com/docs

使用 curl 发起流式聊天补全请求，设置 stream: true 以接收 SSE 事件流。流式请求同样会计费。

```bash
curl https://gw.everylinks.com/v1/chat/completions \
  -H "Authorization: Bearer <EVERYLINKS_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao/doubao-seed-2.0-pro",
    "messages": [{"role": "user", "content": "你好"}],
    "stream": true
  }'
```

--------------------------------

### POST /v1/chat/completions (streaming)

Source: https://tokens.everylinks.com/docs

Streams chat completions using Server-Sent Events (SSE) by setting the stream parameter to true. This allows real-time token delivery.

```APIDOC
## POST /v1/chat/completions (streaming)

### Description
Streams chat completions using Server-Sent Events (SSE) by setting the stream parameter to true. This allows real-time token delivery.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Query Parameters
None documented.

#### Request Body
- **model** (string) - Required - The model identifier.
- **messages** (array) - Required - An array of message objects.
- **stream** (boolean) - Required - Must be true to enable streaming.

### Request Example
curl https://gw.everylinks.com/v1/chat/completions \
  -H "Authorization: Bearer <EVERYLINKS_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao/doubao-seed-2.0-pro",
    "messages": [{"role": "user", "content": "你好"}],
    "stream": true
  }'

### Response
#### Success Response
An SSE stream of completion events.

#### Response Example
No static example provided; the response is streamed as SSE events.
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.