A4F

Documentation

Getting Started

Quickstart

A4F provides a unified API that gives you access to hundreds of AI models through a single endpoint. This allows you to switch between models and providers without changing your code, while automatically handling fallbacks and selecting the most cost-effective options. Get started with just a few lines of code using your preferred SDK or framework.

Using the OpenAI SDK

In the examples below, the A4F-specific headers are optional. Setting them allows your app to appear on the A4F leaderboards.

from openai import OpenAI


client = OpenAI(
  base_url="https://api.a4f.co/v1",
  api_key="YOUR_A4F_API_KEY",
)


completion = client.chat.completions.create(
  model="provider-1/chatgpt-4o-latest", 
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?",
    },
  ],
)
print(completion.choices[0].message.content)

Using the A4F API directly

import requests
import json


response = requests.post(
  url="https://api.a4f.co/v1/chat/completions",
  headers={
    "Authorization": "Bearer YOUR_A4F_API_KEY",
  },
  data=json.dumps({
    "model": "provider-1/chatgpt-4o-latest", 
    "messages": [
      {"role": "user", "content": "What is the meaning of life?"}
    ]
  })
)


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

The API also supports streaming.

Using third-party SDKs

For information about using third-party SDKs and frameworks with A4F, please see our frameworks documentation.

Was this page helpful?

Frequently Asked Questions

Common questions about A4F

Next