GPT4Free (g4f) is a free tool that gives you access to powerful AI models: GPT-4/5, Claude, Gemini, DeepSeek. It works by reverse-engineering public APIs.

⚠️ Note: For educational and testing purposes only. May violate some services’ ToS.

Install in 2 minutes

Requirements

  • Any computer with internet
  • Python 3.10+ (check “Add to PATH” during install)

One command

pip install -U g4f[all]

Done. Library is ready.

Run it

Option 1: Web UI (chat in your browser)

python -m g4f.cli gui --port 8080

Open in browser: http://localhost:8080/chat/

Option 2: Developer mode (local API)

python -m g4f --port 1337

Now you can connect any app that supports OpenAI API.

Your first script: 5 lines

Create test.py:

from g4f.client import Client

client = Client()

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Why is potato a state of mind?"}]
)

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

Run it:

python test.py

Generate images

from g4f.client import Client

client = Client()

img = client.images.generate(
    model="flux",
    prompt="Cyberpunk potato in a neon city",
    response_format="url"
)

print(f"Done: {img.data[0].url}")

Working models (March 2026)

ModelStatusBest for
gpt-4o-mini✅ StableFast chat, quick answers
gpt-4o✅ StableComplex tasks, reasoning
deepseek-v3✅ StableCode, math, logic
gemini-2.5-pro⚠️ IntermittentMultimodal tasks
llama-3.3-70b✅ StableOpen-source alternative
gpt-5🔶 ExperimentalMay not work

💡 List changes often. Get the live list via:
GET http://localhost:8080/backend-api/models

Connect to any OpenAI-compatible app

After running python -m g4f --port 1337:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:1337/v1",
    api_key="doesnt-matter"  # any value works
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Tell me a potato joke"}]
)

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

Works with LibreChat, Flowise, AnythingLLM, and more.

Troubleshooting

# Update the library
pip install -U g4f

# Install errors on Windows
pip install --upgrade pip setuptools wheel

# Model not responding
# → Try a different model
# → Enable VPN
# → Wait 10-30 seconds (some providers are slow)

# Using Docker? Give the browser more shared memory:
docker run -p 8080:8080 --shm-size="2g" hlohaus789/g4f:latest

Docker (for servers & advanced users)

docker run -p 8080:8080 --shm-size="2g" hlohaus789/g4f:latest
  • Web UI: http://localhost:8080
  • API: http://localhost:8080/v1