Gemini Balance is a load balancer and API proxy service that manages multiple Gemini API keys and implements key rotation, authentication, and model filtering through configuration.
The tool solves the problem of managing multiple Gemini API keys and distributing requests across them. It provides a proxy layer built with FastAPI that handles key rotation automatically, filters which models are available, monitors API health, and supports authentication. The service also integrates image generation capabilities and can proxy requests in OpenAI API format, allowing existing OpenAI-compatible clients to work with Gemini endpoints.
Teams managing multiple Gemini API keys or wanting to distribute load across them should consider this tool. It suits projects that need to work around rate limits by spreading requests across multiple keys, or that want a unified interface to manage Gemini access. The project explicitly prohibits commercial resale of the service, so it is intended for direct deployment and use rather than as a managed offering.
The project maintains a substantial base of adopters who report issues from real-world use rather than the core team generating most reports. Maintainers respond to new issues and pull requests within hours. Work in the issue tracker focuses on enhancements, bug fixes, and documentation improvements.
