Three Steps to Get Started

4All API is fully compatible with the OpenAI interface protocol. Existing OpenAI SDK / HTTP clients only need to replace the Base URL and API Key to work; in most cases, no code changes are needed.

Step 1: Register an account

Open api.4allapi.com to register an account and log in to the console. New users can view their balance and available models in the console after registration.

Step 2: Create an API token

Go to Tokens(API Keys) in the left menu of the console;
Click New Token to set the name, quota limit, expiration time, and available model groups;
After creation, copy the generated key starting with sk- and keep it safe.

Step 3: Send your first request

curl

curl https://api.4allapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AIPROXY_KEY" \
  -d '{
    "model": "gpt-5.6",
    "messages": [{"role": "user", "content": "你好,介绍一下你自己"}]
  }'

Python(OpenAI SDK)

from openai import OpenAI

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

resp = client.chat.completions.create(
    model="gpt-5.6",
    messages=[{"role": "user", "content": "你好,介绍一下你自己"}],
)
print(resp.choices[0].message.content)

Node.js(OpenAI SDK)

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.4allapi.com/v1',
  apiKey: process.env.AIPROXY_KEY,
})

const resp = await client.chat.completions.create({
  model: 'gpt-5.6',
  messages: [{ role: 'user', content: '你好,介绍一下你自己' }],
})
console.log(resp.choices[0].message.content)

Next steps

Browse Model Overview to choose the right model;
See Chat Completions Reference to learn all parameters;
Find the integration method for your commonly used tool in Use Cases.