New API
ActiveDescription
New API is a unified AI model hub for aggregation and distribution, supporting cross-conversion of various LLMs into OpenAI, Claude, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management.
Key Features
- Multi-model protocol conversion — Cross-convert various LLMs into OpenAI, Claude, Gemini-compatible formats through a unified API
- Organization-level billing — Per-request, usage-based, and cache-hit billing for OpenAI, Azure, DeepSeek, Claude, Qwen supported models
- Channel management & load balancing — Multi-channel management, auto failover, API key rotation for high-availability model calls
- Permission & security — Token grouping, model restrictions, user management, OAuth2/Discord/LinuxDO authorization login
- Data dashboard — Visual console with analytics on usage, costs, and model call distribution
- Multi-language UI — Supports Simplified Chinese, Traditional Chinese, English, French, and Japanese interfaces
Use Cases
💡 Enterprise unified API gateway — Centralize OpenAI, Claude, Gemini API keys with per-department quotas and permissions
💡 API proxy & cost optimization — Channel load balancing and cache billing analytics to reduce multi-model calling costs
💡 AI SaaS billing — Usage statistics, top-up, and quota management for end users with EPay/Stripe payment support
💡 Model access control — Role-based model restrictions per user to prevent abuse and control token consumption
💡 Private deployment gateway — One-click Docker deploy with SQLite/MySQL, ideal for intranet model proxy and management
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (47.1k stars)
- • Established track record (2 years in production)
⚠️ Limitations
- • Restrictive license (AGPL-3.0)
Categories
Quick Start
```bash
docker run --name new-api -d --restart always \
-p 3000:3000 \
-e TZ=Asia/Shanghai \
-v ./data:/data \
calciumion/new-api:latest
# Visit http://localhost:3000
```