💬 聊天 Chat Completions

接口地址

POST https://portx.asia/v1/chat/completions

请求头

参数	值
Content-Type	application/json
Authorization	Bearer 你的Key

请求参数

参数	类型	必填	说明
model	string	✅	可用模型
messages	array	✅	消息列表
temperature	number	❌	随机性，0-2
max_tokens	number	❌	最大输出 Token 数
stream	boolean	❌	是否流式返回

示例代码

Python

import openai

client = openai.OpenAI(
    api_key="sk-你的Key",
    base_url="https://portx.asia/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "你好，请介绍一下自己"}
    ]
)

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

cURL

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

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-你的Key",
  baseURL: "https://portx.asia/v1"
});

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

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

流式响应（Streaming）

设置 stream: true 即可开启流式返回：

stream = client.chat.completions.create(
    model="gpt-4o",
    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="")

下一步

• 查看可用模型
• 常见问题