Chat Completions

/v1/chat/completions 用于兼容 OpenAI Chat Completions 调用方式，适合直接复用现有 SDK、HTTP 客户端或第三方工具。

请求地址

POST https://mux.la/v1/chat/completions

常用请求字段

字段	必填	说明
model	是	模型名称，例如 gpt-4o
messages	是	对话消息数组，至少包含一条消息
temperature	否	采样温度
max_tokens	否	最大输出 token 数
stream	否	是否使用流式返回，true 时返回 SSE 数据流
store	否	是否存储该 completion
metadata	否	自定义元数据

请求示例

curl https://mux.la/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

返回结构示例

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1738960610,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 10,
    "total_tokens": 18
  }
}

流式输出

将 stream 设置为 true：

curl https://mux.la/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "stream": true,
    "messages": [
      {
        "role": "user",
        "content": "请用三句话介绍 Muxla"
      }
    ]
  }'

OpenAI SDK 示例

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: process.env.MUXLA_API_KEY,
  baseURL: 'https://mux.la/v1'
})

const completion = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: '你好' }]
})

console.log(completion.choices[0]?.message?.content)