接入文档

AIPort 完全兼容 OpenAI API 格式，您可以使用任何支持 OpenAI 的 SDK 或工具直接接入。

快速开始

只需两步即可接入 AIPort：1) 注册并获取 API Key 2) 配置环境变量

export OPENAI_API_KEY="your-api-key"
export OPENAI_BASE_URL="https://ai.aiport.me/v1"

Python

使用 OpenAI Python SDK:

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://ai.aiport.me/v1"
)

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

Node.js

使用 OpenAI Node.js SDK:

import OpenAI from 'openai';

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

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

cURL

直接使用 curl 调用:

curl https://ai.aiport.me/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

the assistant (IDE)

在 VS Code 或 JetBrains 中配置 the assistant:

// ~/.assistant/settings.json
{
  "apiProvider": "openai-compatible",
  "openaiBaseUrl": "https://ai.aiport.me",
  "openaiApiKey": "your-api-key",
  "openaiModelId": "claude-sonnet-4-20250514"
}

Codex CLI

配置 OpenAI Codex CLI:

# ~/.codex/config.toml
[api]
api_key = "your-api-key"
api_base = "https://ai.aiport.me/v1"
model = "gpt-4.1"

Gemini CLI

配置 Gemini CLI:

export GEMINI_API_KEY="your-api-key"
# Or configure in settings

桌面客户端

下载 AIPort Desktop Switch 桌面客户端，一键切换 API Key 和环境变量，支持 the assistant / Codex / Gemini CLI 等工具。

macOSWindowsLinux