Verified project record

xtekky/gpt4free

This project aggregates multiple LLM and media generation providers behind a unified OpenAI-compatible interface. It provides Python and JavaScript clients, a local GUI, a REST API, and an MCP server under a community-first license.

Project overview

Project type: MCP · Model Runtime · Infrastructure
Use cases: Chat Assistants
Deployment: Refer to project documentation
License: GPL-3.0

Best for

Developers and general users seeking a self-hosted interface to aggregate and access multiple LLM and media generation providers locally.
Users looking to interact with models via an OpenAI-compatible API or browser-based JavaScript client without mandatory backend requirements.

Key capabilities

Provides a Python client (and async client) to interact with various LLMs and media generation models using an OpenAI-like interface.
FastAPI-based Interference API enabling OpenAI-like workflows routed through the project's provider selection.
An optional local web GUI to chat with models.
Official JavaScript client for browser usage without backend requirements.
Model Context Protocol server allowing AI assistants like Claude to access web search, scraping, and image generation capabilities.
Tooling for image/audio/video generation and media persistence.
Adapters for LLMs, media providers, and local inference backends.
Provides a CLI to start the GUI server and manage the application.

Limitations and risks

Some provider adapters may require platform-specific tooling like Chrome/Chromium, browser cookies, or HAR files.
Providers may be subject to takedowns or access limitations. The project handles takedown requests, which may affect ongoing access to specific models.

Getting started

Install the application via pip or Docker, run the GUI server command, and open the localhost GUI in a browser. Pre-built Docker images and a Windows executable binary are available.

Evidence and sources

README: GPT4Free (g4f) is a community-driven project that aggregates multiple accessible providers and interfaces to make working with modern LLMs and media-generation models easier and m…
README: - Python client library and async client. - Optional local web GUI. - FastAPI-based OpenAI-compatible API (Interference API). - Official browser JS client (g4f.dev distribution).…
Release: Release v7.8.9
README: Install: ```bash pip install -U g4f[all] ``` Synchronous text example: ```python from g4f.client import Client client = Client() response = client.chat.completions.create( model="…
README: - The Interference API enables OpenAI-like workflows routed through GPT4Free provider selection.

Reviewed at: 2026-07-17T06:19:15Z