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

# 文本与多模态对话

> 使用 OpenAI Chat Completions 格式调用文本和视觉模型

# 文本与多模态对话

使用 OpenAI Chat Completions 兼容格式调用文本模型或视觉模型。支持普通文本、图片输入、多图输入和流式响应。

## 请求参数

<ParamField body="model" type="string" required>
  模型 ID。可通过 [模型列表](/llm-gateway/api/models) 查询
</ParamField>

<ParamField body="messages" type="array" required>
  对话消息列表
</ParamField>

<ParamField body="messages[].role" type="string" required>
  消息角色，支持 `system`、`user`、`assistant`
</ParamField>

<ParamField body="messages[].content" type="string | array" required>
  消息内容。文本模型可传字符串；视觉模型可传 OpenAI 多模态 content 数组
</ParamField>

<ParamField body="stream" type="boolean">
  是否使用 Server-Sent Events 流式响应
</ParamField>

<ParamField body="temperature" type="number">
  采样温度
</ParamField>

<ParamField body="max_tokens" type="integer">
  最大输出 token 数
</ParamField>

## 响应参数

<ResponseField name="id" type="string">
  响应 ID
</ResponseField>

<ResponseField name="object" type="string">
  响应类型，通常为 `chat.completion`
</ResponseField>

<ResponseField name="model" type="string">
  实际调用的模型 ID
</ResponseField>

<ResponseField name="choices" type="array">
  输出候选列表

  <Expandable title="choices">
    <ResponseField name="message.role" type="string">
      输出消息角色
    </ResponseField>

    <ResponseField name="message.content" type="string">
      输出文本
    </ResponseField>

    <ResponseField name="finish_reason" type="string">
      停止原因
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="usage" type="object">
  token 用量
</ResponseField>

## 代码示例

<CodeGroup>
  ```python Python theme={null}
  import requests

  url = "https://api.chenyu.cn/v1/chat/completions"
  headers = {
      "Authorization": "Bearer your_api_key",
      "Content-Type": "application/json"
  }
  payload = {
      "model": "doubao-seed-2-0-lite-260428",
      "messages": [
          {"role": "user", "content": "你好，简单介绍一下你自己"}
      ]
  }

  response = requests.post(url, headers=headers, json=payload)
  print(response.json()["choices"][0]["message"]["content"])
  ```

  ```javascript JavaScript theme={null}
  const axios = require('axios');

  axios.post('https://api.chenyu.cn/v1/chat/completions', {
    model: 'doubao-seed-2-0-lite-260428',
    messages: [
      { role: 'user', content: '你好，简单介绍一下你自己' }
    ]
  }, {
    headers: {
      Authorization: 'Bearer your_api_key',
      'Content-Type': 'application/json'
    }
  }).then((response) => {
    console.log(response.data.choices[0].message.content);
  });
  ```

  ```curl cURL theme={null}
  curl -X POST "https://api.chenyu.cn/v1/chat/completions" \
    -H "Authorization: Bearer your_api_key" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "doubao-seed-2-0-lite-260428",
      "messages": [
        {"role": "user", "content": "你好，简单介绍一下你自己"}
      ]
    }'
  ```
</CodeGroup>

## 多模态示例

```json theme={null}
{
  "model": "doubao-seed-1-6-vision-250815",
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "这张图片里有什么？"},
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.png"
          }
        }
      ]
    }
  ]
}
```

## 响应示例

```json theme={null}
{
  "id": "chatcmpl_xxx",
  "object": "chat.completion",
  "created": 1780000000,
  "model": "doubao-seed-2-0-lite-260428",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好，我是晨羽智云大模型服务。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 12,
    "total_tokens": 32
  }
}
```