ChatCompletions格式

根据对话历史创建模型响应。支持流式和非流式响应，兼容 OpenAI Chat Completions API

请求参数

请求头

以下参数遵循 OpenAI Chat Completions 请求格式。参数是否可用取决于所选模型和兼容网关；网关不支持的字段会返回 400。

请求体

其中只有 model 和 messages 为必填字段；其余参数均为可选，是否生效取决于所选模型和兼容网关。

消息字段

messages 是按时间顺序排列的消息数组。网关会保留下列字段并按所选上游适配器进行转换；不同模型对多模态内容和推理字段的支持不同。

内容块示例：

{
  "role": "user",
  "content": [
    { "type": "text", "text": "描述这张图片" },
    { "type": "image_url", "image_url": { "url": "https://example.com/image.png", "detail": "auto" } }
  ]
}

输出格式与推理

输出格式、音频输出和推理强度参数请参阅上方请求体参数表。

音频输出配置示例：

{
  "modalities": ["text", "audio"],
  "audio": { "voice": "alloy", "format": "wav" }
}

流式输出

设置 stream 为 true 后，接口会以 SSE 增量事件返回结果；如需在最终事件中获取用量统计，可同时设置 stream_options.include_usage。

工具调用

tools 和 tool_choice 的用途请参阅上方请求体参数表。工具定义使用 type 和 function 对象。function 至少需要 name；可选 description 和 parameters（JSON Schema）。

{
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "查询指定城市的天气",
        "parameters": {
          "type": "object",
          "properties": { "city": { "type": "string" } },
          "required": ["city"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}

请求体示例

{
  "model": "gpt-5.6-sol",
  "messages": [
    { "role": "system", "content": "你是一个简洁的助手." },
    { "role": "user", "content": "介绍一下自己." }
  ],
  "max_completion_tokens": 512,
  "response_format": { "type": "text" },
  "stream": false
}

请求示例代码

curl -X POST "https://10000router.com/v1/chat/completions" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [
      { "role": "system", "content": "You are a concise assistant." },
      { "role": "user", "content": "Introduce yourself." }
    ],
    "max_completion_tokens": 512,
    "response_format": { "type": "text" },
    "stream": false
  }'

const payload = {
  model: "gpt-5.6-sol",
  messages: [
    { role: "system", content: "You are a concise assistant." },
    { role: "user", content: "Introduce yourself." }
  ],
  max_completion_tokens: 512,
  response_format: { type: "text" },
  stream: false
};

const response = await fetch("https://10000router.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.API_KEY,
  },
  body: JSON.stringify(payload)
});
console.log(await response.json());

payload := `{
  "model": "gpt-5.6-sol",
  "messages": [
    { "role": "system", "content": "You are a concise assistant." },
    { "role": "user", "content": "Introduce yourself." }
  ],
  "max_completion_tokens": 512,
  "response_format": { "type": "text" },
  "stream": false
}`
req, err := http.NewRequest("POST", "https://10000router.com/v1/chat/completions", strings.NewReader(payload))
if err != nil {
  log.Fatal(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("API_KEY"))
res, err := http.DefaultClient.Do(req)
if err != nil {
  log.Fatal(err)
}
defer res.Body.Close()

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["API_KEY"], base_url="https://10000router.com/v1")

payload = {
    "model": "gpt-5.6-sol",
    "messages": [
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Introduce yourself."}
    ],
    "max_completion_tokens": 512,
    "response_format": {"type": "text"},
    "stream": False
}

response = client.chat.completions.create(**payload)
print(response.model_dump())

var client = java.net.http.HttpClient.newHttpClient();
var payload = "{"
    + "\"model\":\"gpt-5.6-sol\","
    + "\"messages\":["
    + "{\"role\":\"system\",\"content\":\"You are a concise assistant.\"},"
    + "{\"role\":\"user\",\"content\":\"Introduce yourself.\"}"
    + "],\"max_completion_tokens\":512,"
    + "\"response_format\":{\"type\":\"text\"},\"stream\":false}";
var request = java.net.http.HttpRequest.newBuilder()
    .uri(java.net.URI.create("https://10000router.com/v1/chat/completions"))
    .header("Authorization", "Bearer " + System.getenv("API_KEY"))
    .POST(java.net.http.HttpRequest.BodyPublishers.ofString(payload))
    .build();
var response = client.send(request, java.net.http.HttpResponse.BodyHandlers.ofString());

using System.Net.Http.Json;

using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization = new(
    "Bearer",
    Environment.GetEnvironmentVariable("API_KEY")
);

var payload = new
{
    model = "gpt-5.6-sol",
    messages = new[]
    {
        new { role = "system", content = "You are a concise assistant." },
        new { role = "user", content = "Introduce yourself." }
    },
    max_completion_tokens = 512,
    response_format = new { type = "text" },
    stream = false
};

var response = await client.PostAsJsonAsync(
    "https://10000router.com/v1/chat/completions",
    payload
);
Console.WriteLine(await response.Content.ReadAsStringAsync());

返回响应

响应示例

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "gpt-5.6-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 4,
    "total_tokens": 22
  },
  "system_fingerprint": "fp_example"
}

{
  "error": {
    "message": "Missing required parameter: messages",
    "type": "invalid_request_error",
    "param": "messages",
    "code": null
  }
}

{
  "error": {
    "message": "Rate limit reached",
    "type": "rate_limit_exceeded",
    "param": null,
    "code": null
  }
}

{
  "error": {
    "message": "Invalid authentication credentials",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

返回字段参数

响应字段按对象层级拆分为可折叠区块，默认展开；可收起暂时不关注的对象，减少长响应的视觉干扰。

流式响应

当请求设置 stream=true 时，响应为 Server-Sent Events（SSE），每个事件包含一个 chat.completion.chunk 对象，而不是上面的完整对象：

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1710000000,"model":"gpt-5.6-sol","choices":[{"index":0,"delta":{"role":"assistant","content":"你好"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1710000000,"model":"gpt-5.6-sol","choices":[{"index":0,"delta":{"content":"！"},"finish_reason":"stop"}]}

data: [DONE]

客户端应按顺序拼接 choices[].delta.content。如果请求同时设置 stream_options.include_usage=true，结束事件前还会返回一个包含 usage 的统计块。