# ChatCompletions 格式

来源: https://docs.aicentos.com/api/chat/openai/chat-completions

Language: zh-CN

> OpenAI 兼容的对话补全接口：端点、鉴权与请求示例

OpenAI 兼容格式的对话补全接口。

`POST /v1/chat/completions`

## 鉴权

Bearer Token：API Key 在控制台「令牌管理」获取，放在请求头 `Authorization`。

## 请求

`Content-Type: application/json`

```bash
export AICENTOS_API_KEY="sk-your-aicentos-api-key"

curl -X POST "https://aicentos.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AICENTOS_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "user", "content": "用一句话介绍你自己" }
    ]
  }'
```

除 `model` 与 `messages` 外，其余参数与 OpenAI 官方一致（`temperature`、`stream`、`tools` 等），原样传入即可。

## 响应

返回 OpenAI 标准结构，回复取 `choices[0].message.content`，用量在 `usage`：

```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "我是 aicentos。" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 21, "completion_tokens": 9, "total_tokens": 30 }
}
```

鉴权失败时返回 `invalid_api_key` 错误，排查方法见[错误处理](https://docs.aicentos.com/billing/errors)：

```json
{
  "error": {
    "message": "Incorrect API key provided",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}
```