创建对话补全 — 完全兼容 OpenAI Chat Completions API，支持流式 / 非流式、工具调用、推理输出等

根据对话历史创建模型响应。完全兼容 OpenAI Chat Completions API，支持流式 / 非流式响应、工具调用（Function Calling）、结构化输出、推理输出等能力。

项目	值
请求方法	`POST`
请求路径	`/v1/chat/completions`
完整 URL	`https://api.amux.ai/v1/chat/completions`
认证方式	`Authorization: Bearer <API_TOKEN>`
请求格式	`application/json`
响应格式	JSON 或 SSE（`stream=true` 时）

本接口完全对齐 OpenAI Chat Completions 协议，可直接使用 OpenAI 官方 SDK 调用，仅需替换 Base URL 和 API Key。

请求体参数

Prop

Type

透传策略：amux-api 对未在上方列出的字段（如供应商专属扩展参数）会原样透传至上游。temperature 等未传值时由上游模型自行使用其默认值，amux-api 不在网关层强制填充默认值。

Message 结构

Prop

Type

Tool 结构

Prop

Type

请求示例

curl https://api.amux.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AMUX_API_KEY" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "你好，请用一句话介绍 Amux API。"}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.amux.ai/v1",
    api_key=os.environ["AMUX_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "你好，请用一句话介绍 Amux API。"},
    ],
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.amux.ai/v1',
  apiKey: process.env.AMUX_API_KEY,
});

const response = await client.chat.completions.create({
  model: 'gpt-5.4',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: '你好，请用一句话介绍 Amux API。' },
  ],
});

console.log(response.choices[0].message.content);

const stream = await client.chat.completions.create({
  model: 'gpt-5.4',
  messages: [{ role: 'user', content: '写一首关于春天的诗' }],
  stream: true,
  stream_options: { include_usage: true },
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

响应示例

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1730000000,
  "model": "gpt-5.4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Amux API 是一个统一、稳定的企业级大模型接口网关。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 18,
    "total_tokens": 42,
    "prompt_tokens_details": { "cached_tokens": 0 },
    "completion_tokens_details": { "reasoning_tokens": 0 }
  }
}

响应字段

Prop

Type

Choice 字段

Prop

Type

流式响应

当 stream=true 时，响应使用 SSE 格式逐帧推送：

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Amux"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

每帧的 choices[].delta 携带本次增量；流结束以 data: [DONE] 标记。

错误响应

{
  "error": {
    "message": "...",
    "type": "invalid_request_error",
    "param": "messages",
    "code": "invalid_value"
  }
}

HTTP 状态码	含义
`200`	请求成功
`400`	请求参数错误
`401`	API 密钥无效或缺失
`403`	模型未授权或额度受限
`404`	模型不存在
`429`	触发速率限制或额度不足
`500` / `502` / `503`	服务端异常或上游不可用

Chat Completions

On this page