OpenAI SDK 使用

你可以使用 OpenAI 官方 SDK 接入 Zivv API，只需修改 base_url 即可。

Python

安装

pip install openai

基本用法

from openai import OpenAI

client = OpenAI(
    base_url="https://zivv.pro/v1",
    api_key="sk-你的Key",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

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

流式输出

from openai import OpenAI

client = OpenAI(
    base_url="https://zivv.pro/v1",
    api_key="sk-你的Key",
)

stream = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[
        {"role": "user", "content": "用 Python 写一个快速排序"}
    ],
    stream=True,
)

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

图像生成

from openai import OpenAI

client = OpenAI(
    base_url="https://zivv.pro/v1",
    api_key="sk-你的Key",
)

response = client.chat.completions.create(
    model="YOUR_IMAGE_MODEL_ID",
    messages=[
        {"role": "user", "content": "画一只卡通猫咪"}
    ],
)

# 图片以 base64 格式返回在响应内容中
print(response.choices[0].message.content)

Node.js / TypeScript

安装

npm install openai

基本用法

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://zivv.pro/v1',
  apiKey: 'sk-你的Key',
})

const response = await client.chat.completions.create({
  model: 'YOUR_MODEL_ID',
  messages: [
    { role: 'user', content: 'Hello!' }
  ],
})

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

流式输出

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://zivv.pro/v1',
  apiKey: 'sk-你的Key',
})

const stream = await client.chat.completions.create({
  model: 'YOUR_MODEL_ID',
  messages: [
    { role: 'user', content: '用 TypeScript 写一个快速排序' }
  ],
  stream: true,
})

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

注意事项

• 常用 OpenAI Chat Completions 参数可直接传入；具体参数是否生效取决于目标模型和协议转换能力
• 输出 Token 上限取决于模型、协议和当前网关限制，请以模型广场和实际错误响应为准
• 请使用 模型广场 中列出的精确模型 ID