Compatibility Mode Invocation (SDK Integration)

4ALL API fully implements the OpenAI interface protocol, so the official SDK and all OpenAI-compatible clients can be used directly, with no code changes required—even when calling non-OpenAI models such as Claude and Gemini, requests and responses are unified into the OpenAI format.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.4allapi.com/v1",
    api_key="sk-你的令牌",
)

resp = client.chat.completions.create(
    model="claude-sonnet-5",   # 换成任意在售模型即可
    messages=[{"role": "user", "content": "你好"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.4allapi.com/v1',
  apiKey: 'sk-你的令牌',
});

const resp = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(resp.choices[0].message.content);

Environment Variable Method

Most tools support environment variables, so there is no need to modify the code:

export OPENAI_BASE_URL="https://api.4allapi.com/v1"
export OPENAI_API_KEY="sk-你的令牌"

Notes

To switch models across vendors, only the model field needs to be changed; the message format remains unchanged;
Streaming (stream: true), function calling (tools), visual input, and other capabilities are also compatible, see Streaming Output and FC Function Calling;
If you need the native Anthropic / Google protocols, see Claude Native Invocation, Gemini Native Invocation。