One API
StaleDescription
One API is an LLM API management and redistribution system that unifies OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, and more under a single API. Supports key management, redistribution, and one-click Docker deployment.
Key Features
- Unified API format — Wraps 20+ LLM providers (OpenAI, Azure, Claude, Gemini, DeepSeek, etc.) into standard OpenAI API format
- Load balancing & multi-channel — Configure multiple channels per model with automatic load balancing and failure retry
- Token & quota management — Token expiry, quota limits, IP whitelist, model access control, and batch code generation
- User & group system — User registration via email/GitHub/Feishu/WeChat, user groups and channel groups with independent rate multipliers
- One-click Docker deploy — Docker image with SQLite or MySQL backend options, supports multi-node deployment
- Streaming & image generation — Stream mode for typewriter effect, supports DALL-E and other image generation APIs
Use Cases
💡 Unified LLM API gateway — Provide a single LLM API entry point for teams, abstracting away differences between providers
💡 API key redistribution — Manage multiple keys with independent quotas and access permissions per user or project
💡 Cost control & monitoring — Monitor and control LLM API costs via token quotas and channel rate multipliers
💡 Multi-model redundancy — Configure multiple channels per model for automatic failover when a provider goes down
Strengths & Limitations
✅ Strengths
- • High community interest (36.7k stars)
- • Permissive open-source license (MIT)
- • Established track record (3 years in production)
⚠️ Limitations
- • No updates in over 7 months
Categories
Quick Start
docker run --name one-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/one-api:/data justsong/one-api