OpenAI API Base URL 配置完全指南

OpenAI API 的 base_url 决定了请求发送到哪个服务端点。通过修改 base_url，你可以将请求指向中转站、私有部署或其他兼容服务。

什么是 Base URL？

默认情况下，OpenAI SDK 将请求发送到 https://api.openai.com/v1。通过修改 base_url，你可以：

• 使用 API 中转服务，绕过网络限制
• 指向自建的 OpenAI 兼容服务
• 连接 Azure OpenAI、本地 Ollama 等

环境变量方式

# Linux / macOS
export OPENAI_API_KEY="your-api-key"
export OPENAI_BASE_URL="https://claude4u.com/v1"

# Windows PowerShell
$env:OPENAI_API_KEY="your-api-key"
$env:OPENAI_BASE_URL="https://claude4u.com/v1"

# Windows CMD
set OPENAI_API_KEY=your-api-key
set OPENAI_BASE_URL=https://claude4u.com/v1

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://claude4u.com/v1"
)

response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Node.js SDK

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your-api-key',
  baseURL: 'https://claude4u.com/v1',
});

const response = await client.chat.completions.create({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);

在各工具中配置

Open WebUI

在 Admin Settings > Connections 中设置 OPENAI_API_BASE_URL。

LangChain

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4",
    openai_api_key="your-key",
    openai_api_base="https://claude4u.com/v1"
)

curl 命令

curl https://claude4u.com/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4","messages":[{"role":"user","content":"Hi"}]}'