创建对话请求 (OpenAI)

简介

通用文本对话接口，支持 OpenAI 兼容的大语言模型生成对话回答。通过统一的 API 接口，您可以调用 OpenAI、Claude、DeepSeek、Grok、通义千问等多个主流大模型。

认证

Bearer Token，如 Bearer sk-xxxxxxxxxx

请求参数

model

string

required

模型标识，支持的模型包括：

OpenAI 系列：gpt-4o、gpt-4o-mini、o3-mini、o4-mini 等
Claude 系列：claude-opus-4-6、claude-sonnet-4-5-20250929 等
DeepSeek 系列：deepseek-v3、deepseek-r1 等
Gemini 系列：gemini-3-pro-preview、gemini-3-flash-preview 等
国产模型：glm-5、kimi-k2.5、doubao-seed-1-8-251228 等

messages

array

required

对话消息列表，每个元素包含 role（user/system/assistant）和 content

temperature

number

随机性控制，0-2，值越高回复越随机

stream

boolean

是否启用流式输出，返回 SSE 格式的分片数据

max_tokens

integer

最大生成 token 数，控制回复长度

基础示例

非流式请求
流式请求（SSE）
Python 示例

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "glm-5",
    "messages": [
      {"role": "system", "content": "你是一个有用的助手"},
      {"role": "user", "content": "请用中文简要介绍人工智能"}
    ],
    "temperature": 0.7
  }'

curl -N -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "doubao-seed-1-8-251228",
    "stream": true,
    "messages": [
      {"role": "system", "content": "你是一个有用的助手"},
      {"role": "user", "content": "请用中文简要介绍人工智能"}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxxxx",
    base_url="https://console.mixroute.io/v1"
)

# 非流式
completion = client.chat.completions.create(
    model="glm-5",
    messages=[
        {"role": "system", "content": "你是一个有用的助手"},
        {"role": "user", "content": "请用中文简要介绍人工智能"}
    ],
    temperature=0.7
)
print(completion.choices[0].message.content)

# 流式
stream = client.chat.completions.create(
    model="doubao-seed-1-8-251228",
    messages=[
        {"role": "user", "content": "请用中文简要介绍人工智能"}
    ],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

高级功能

支持 OpenAI 兼容的工具调用格式：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "glm-5",
    "messages": [
      {"role": "user", "content": "上海的天气怎么样？"}
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "根据城市获取天气信息",
          "parameters": {
            "type": "object",
            "properties": {
              "city": {"type": "string"}
            },
            "required": ["city"]
          }
        }
      }
    ],
    "tool_choice": "auto"
  }'

使用 JSON Schema 约束模型输出格式：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-4o",
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "Answer",
        "schema": {
          "type": "object",
          "properties": {
            "summary": {"type": "string"}
          },
          "required": ["summary"]
        }
      }
    },
    "messages": [
      {"role": "user", "content": "返回一个包含 summary 字段的 JSON"}
    ]
  }'

DeepSeek
通义千问
Gemini

DeepSeek R1 系列支持深度思考能力：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "deepseek-r1",
    "messages": [
      {"role": "user", "content": "请分析这道数学题：如果 x^2 + 2x - 3 = 0，求 x 的值"}
    ],
    "temperature": 0.6
  }'

响应将包含 reasoning_content 字段展示思考过程。

通义千问 QwQ 系列支持思考能力：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "qwq-32b",
    "messages": [
      {"role": "user", "content": "分析一下人工智能的发展趋势"}
    ],
    "enable_thinking": true
  }'

Gemini 2.0 Flash Thinking 支持思考能力：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gemini-2.0-flash-thinking-exp",
    "messages": [
      {"role": "user", "content": "解释量子计算的基本原理"}
    ]
  }'

通义千问支持额外的扩展参数：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "qwen-max",
    "messages": [
      {"role": "user", "content": "你好"}
    ],
    "enable_search": true,
    "search_options": {
      "search_strategy": "standard",
      "forced_search": false
    }
  }'

参数	说明
`enable_search`	启用联网搜索
`search_options.search_strategy`	搜索策略：`standard`/`pro`
`search_options.forced_search`	强制搜索

Claude 搜索
Grok 搜索

Claude 模型支持联网搜索功能：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "messages": [
      {"role": "user", "content": "今天有什么重大新闻？"}
    ],
    "tools": [
      {
        "type": "web_search_20250305",
        "name": "web_search",
        "max_uses": 5
      }
    ]
  }'

Grok 模型支持实时联网搜索：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "grok-3",
    "messages": [
      {"role": "user", "content": "最新的科技新闻有哪些？"}
    ],
    "search_parameters": {
      "mode": "auto",
      "return_citations": true
    }
  }'

GPT 模型支持直接处理文件内容：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "请分析这个文档的内容"},
          {
            "type": "file",
            "file": {
              "url": "https://example.com/document.pdf"
            }
          }
        ]
      }
    ]
  }'

支持的文件类型包括 PDF、Word、Excel、图片等。

Grok 模型支持增强推理能力：

curl -X POST "https://console.mixroute.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "grok-3-mini",
    "messages": [
      {"role": "user", "content": "分析以下逻辑问题：如果所有A都是B，且所有B都是C，那么..."}
    ],
    "reasoning_effort": "high"
  }'

reasoning_effort	说明
`low`	快速响应，基础推理
`medium`	平衡模式
`high`	深度推理，更精确

响应格式

非流式响应
流式响应

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "glm-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "回复内容..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 100,
    "total_tokens": 125
  }
}

流式响应使用 Server-Sent Events (SSE) 格式：

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1234567890,"model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant","content":"你"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1234567890,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"好"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1234567890,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

每个 chunk 包含增量内容，最后以 [DONE] 结束。

错误处理

异常类型	触发场景
AuthenticationError	API密钥无效或未授权
NotFoundError	模型不存在或不被支持
APIConnectionError	网络中断或服务器未响应
RateLimitError	请求频率超限

curl --request POST \
  --url https://console.mixroute.io/v1/chat/completions \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "glm-5",
    "messages": [
      {"role": "system", "content": "你是一个有用的助手"},
      {"role": "user", "content": "请用中文简要介绍人工智能"}
    ],
    "temperature": 0.7
  }'

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "glm-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "人工智能是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门新的技术科学..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 100,
    "total_tokens": 125
  }
}

当下热门模型

OpenAI 官方库使用

文本系列

文本向量系列

图像系列

视频系列

其他

创建对话请求 (OpenAI)

简介

认证

请求参数

基础示例

高级功能

响应格式

错误处理

当下热门模型

OpenAI 官方库使用

文本系列

文本向量系列

图像系列

视频系列

其他

​简介

​认证

​请求参数

​基础示例

​高级功能

​响应格式

​错误处理

简介

认证

请求参数

基础示例

高级功能

响应格式

错误处理