A FastAPI proxy that transforms Google's Gemini CLI into OpenAI-compatible and native Gemini API endpoints for easy integration.
Gemini CLI to API Proxy is a FastAPI-based server that converts Google's Gemini CLI tool into standard API endpoints. It provides both OpenAI-compatible and native Gemini API interfaces, allowing developers to integrate Gemini's AI capabilities into applications using familiar API patterns. The proxy enables access to Google's free Gemini API quota through a standardized interface.
Developers and teams building AI-powered applications who want to use Google's Gemini models through API interfaces compatible with OpenAI's format or direct Gemini API calls.
It provides a drop-in replacement for OpenAI's API while leveraging Google's free Gemini quota, offers both streaming and multimodal support, and is containerized for easy self-hosting. The proxy eliminates the need to adapt tools specifically for Gemini's CLI, enabling broader integration.
Gemini CLI to API Proxy is a FastAPI-based server that converts the Gemini CLI tool into standard API endpoints. It enables developers to use Google's free Gemini API quota through familiar OpenAI API interfaces or direct Gemini API calls, making it simple to integrate Gemini capabilities into existing applications.
The project aims to bridge the gap between Google's Gemini CLI and the broader ecosystem of AI tools by providing a standardized, easy-to-deploy API layer that maintains compatibility with popular interfaces.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Acts as a drop-in replacement for OpenAI's chat completions API, enabling seamless integration with existing tools and libraries, as shown in the Python example using the openai client.
Proxies all Gemini API endpoints, allowing use of advanced features like thinking controls and Google Search grounding through model variants like '-search' and '-maxthinking'.
Supports real-time streaming responses and handles text and image inputs, leveraging Gemini's capabilities for interactive and vision-based applications.
Containerized with Docker and configured for Hugging Face Spaces, simplifying setup and scaling across different hosting environments.
Requires managing Google OAuth credentials or API keys, which adds initial configuration overhead compared to simpler authentication methods and can be error-prone.
Tied exclusively to Google's Gemini models, limiting flexibility if you need to switch to or incorporate other AI providers like OpenAI or Anthropic.
Adds an extra network hop as a proxy layer, which can increase latency and become a bottleneck in high-demand scenarios without built-in clustering or load balancing.