g4f-working
g4f-working is a daily-updated list of working no-auth AI providers and models from @xtekky/gpt4free. It helps developers, testers, and AI enthusiasts instantly
What is g4f-working?
g4f-working is a daily-updated list of working no-auth AI providers and models from @xtekky/gpt4free. It helps developers, testers, and AI enthusiasts instantly find which models are currently online and accessible without any API keys, tokens, or cookies.
Overview of g4f-working
What it is
g4f-working is a daily-updated list of working no-auth AI providers and models from @xtekky/gpt4free. It helps developers, testers, and AI enthusiasts instantly find which models are currently online and accessible without any API keys, tokens, or cookies. The project spins up a fresh g4f API server daily, enumerates every provider and model (typically 70+ providers, 3,000+ models), sends real test requests for text, image, audio, and video capabilities, and publishes the list of working ones as plain-text files. No Python, dependencies, or API keys are needed to consume the results; users can fetch the files with curl or wget. The codebase was refactored in v2.0 from a single 1,160-line file into a clean, modular Python package with full CLI, environment variable support, and a comprehensive test suite of 76 unit tests. All output file names and formats are 100% backwards-compatible with v1.0.
Key features
- Daily automated testing of 70+ providers and 3,000+ models from gpt4free.
- Zero authentication required: no API keys, tokens, or cookies needed.
- Results published as plain-text files (models.txt, working_results.txt) fetchable via curl or wget.
- Modular Python package (g4f_tester) with CLI overrides for port, timeout, batch size, and custom prompts.
- Environment variable support (G4F_PORT, G4F_API_KEY, G4F_TIMEOUT, G4F_NO_SERVER).
- Reusable as a Python library: import Config and run from your own code.
- Comprehensive test suite with 76 unit tests covering all modules.
Use cases
- Developers who want to quickly find working AI models without setting up authentication.
- Testers who need to verify provider availability and model capabilities daily.
- AI enthusiasts who want to experiment with various models without managing API keys.
- Automation pipelines that consume the result files to integrate working models into applications.
Getting started
For end users (just want the working list):bashcurl -sL https://raw.githubusercontent.com/maruf009sultan/g4f-working/refs/heads/main/working/models.txtcurl -sL https://raw.githubusercontent.com/maruf009sultan/g4f-working/refs/heads/main/working/working_results.txtFor developers (want to run the tests yourself):bashgit clone https://github.com/maruf009sultan/g4f-working.gitcd g4f-workingsudo apt-get install -y ffmpeg flac # macOS: brew install ffmpeg flacpip install -r requirements.txtpython provider_tester.pyCommon CLI overrides:bashpython provider_tester.py --port 9000python provider_tester.py --timeout 180python provider_tester.py --batch-size 10 --max-concurrent 25python provider_tester.py --no-server --base-url http://10.0.0.5:8081
License and pricing
The license is stated as CC BY-NC 4.0 in the LICENSE.md file. The project is open source with no pricing information provided.
Based on the project's public README and repository metadata.