GPT 对接

GPT 文本模型通过 NewAPI 对接，Base URL 统一使用：

https://api.zmoapi.cn/v1

请求头：

Authorization: Bearer 你的 API Key
Content-Type: application/json

查看模型

curl https://api.zmoapi.cn/v1/models \
  -H "Authorization: Bearer sk-xxxxxxxx"

Chat Completions

curl https://api.zmoapi.cn/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {"role": "user", "content": "写一段电商产品卖点文案"}
    ],
    "stream": false
  }'

返回示例：

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "这里是模型返回内容"
      }
    }
  ]
}

流式输出

curl https://api.zmoapi.cn/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {"role": "user", "content": "给我写一个短视频脚本"}
    ],
    "stream": true
  }'

Responses 接口

部分客户端更适合使用 /v1/responses：

curl https://api.zmoapi.cn/v1/responses \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "帮我整理一份商品详情页结构"
  }'

JavaScript 示例

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-xxxxxxxx",
  baseURL: "https://api.zmoapi.cn/v1",
});

const completion = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [
    { role: "user", content: "写一段电商产品卖点文案" },
  ],
});

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

Python 示例

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxx",
    base_url="https://api.zmoapi.cn/v1",
)

completion = client.chat.completions.create(
    model="gpt-5.5",
    messages=[
        {"role": "user", "content": "写一段电商产品卖点文案"},
    ],
)

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