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

# 对话补全 Chat Completions

> 兼容 OpenAI Chat Completions 的对话接口

## 请求

**POST** `/v1/chat/completions`

### 请求头

| 名称              | 必填 | 说明                 |
| --------------- | -- | ------------------ |
| `Authorization` | 是  | `Bearer <令牌>`      |
| `Content-Type`  | 是  | `application/json` |

### 请求体参数

| 参数            | 类型            | 必填 | 说明                                  |
| ------------- | ------------- | -- | ----------------------------------- |
| `model`       | string        | 是  | 模型名称，如 `gpt-4o`、`claude-3-5-sonnet` |
| `messages`    | array         | 是  | 对话消息列表                              |
| `stream`      | boolean       | 否  | 是否流式返回，默认 `false`                   |
| `temperature` | number        | 否  | 采样温度 0\~2                           |
| `top_p`       | number        | 否  | 核采样阈值                               |
| `max_tokens`  | integer       | 否  | 最大生成 token 数                        |
| `tools`       | array         | 否  | 工具调用定义                              |
| `tool_choice` | string/object | 否  | 工具选择策略                              |

### 示例

```bash theme={null}
curl https://your-domain.com/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "你是有用的助手"},
      {"role": "user", "content": "介绍一下量子计算"}
    ],
    "stream": true
  }'
```

## 响应

```json theme={null}
{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1712000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "..."},
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 128,
    "total_tokens": 140
  }
}
```