Chat Completions API

创建模型响应，支持对话、函数调用等。

请求

POST /v1/chat/completions

请求头

参数	类型	必填	说明
Authorization	string	✅	Bearer sk-你的密钥
Content-Type	string	✅	application/json

请求体

{
  "model": "gpt-4o-mini",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "你好！"}
  ],
  "temperature": 0.7,
  "max_tokens": 1000,
  "stream": false
}

参数说明

参数	类型	必填	说明
model	string	✅	模型名称，如 gpt-4o-mini
messages	array	✅	对话消息列表
temperature	float	❌	温度参数 (0-2)，默认 1.0
max_tokens	int	❌	最大生成 token 数
stream	bool	❌	是否流式输出，默认 false
top_p	float	❌	Top-p 参数 (0-1)
frequency_penalty	float	❌	频率惩罚 (-2 to 2)
presence_penalty	float	❌	存在惩罚 (-2 to 2)
stop	array	❌	停止词列表
tools	array	❌	函数调用工具列表
tool_choice	string	❌	函数调用选择

响应

成功响应

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！有什么可以帮你的吗？"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

流式响应

设置 stream: true 后，响应为 SSE (Server-Sent Events) 格式：

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

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

data: [DONE]

示例

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的密钥",
    base_url="https://api.nextapi.pro/v1"
)

# 普通请求
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "你好！"}]
)
print(response.choices[0].message.content)

# 流式请求
stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "写一首诗"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Node.js

const OpenAI = require('openai');

const openai = new OpenAI({
  apiKey: 'sk-你的密钥',
  baseURL: 'https://api.nextapi.pro/v1'
});

// 普通请求
async function chat() {
  const completion = await openai.chat.completions.create({
    model: 'gpt-4o-mini',
    messages: [{ role: 'user', content: '你好！' }],
  });
  
  console.log(completion.choices[0].message.content);
}

// 流式请求
async function streamChat() {
  const stream = await openai.chat.completions.create({
    model: 'gpt-4o-mini',
    messages: [{ role: 'user', content: '写一首诗' }],
    stream: true,
  });

  for await (const chunk of stream) {
    if (chunk.choices[0]?.delta?.content) {
      console.log(chunk.choices[0].delta.content);
    }
  }
}

chat();

cURL

# 普通请求
curl https://api.nextapi.pro/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-你的密钥" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "你好！"}]
  }'

# 流式请求
curl https://api.nextapi.pro/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-你的密钥" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "写一首诗"}],
    "stream": true
  }'

错误处理

HTTP 状态码	说明	解决方案
400	请求参数错误	检查请求格式
401	认证失败	检查 API Key
403	权限不足	检查用户权限
429	请求过于频繁	降低请求频率
500	服务器错误	联系客服

下一步

• Images API
• Embeddings API
• 错误码参考