one-api
Developed by songquanpeng
One API is an open-source LLM management and distribution system that provides a unified access layer for dozens of AI models (OpenAI, Anthropic, Google Gemini, DeepSeek, etc.) using the standard OpenAI API format. It features high-performance load balancing, streaming support, comprehensive token/quota management, and flexible model mapping. With support for Docker deployment and multi-node scaling, it acts as a robust API gateway for developers to centralize and manage AI resource consumption efficiently.
- Unified LLM API aggregation
- Load balancing & auto-retry
- Advanced token & quota management
- Multi-machine deployment with Redis
- Custom model mapping & multipliers
web