QuantumNous/new-api

Project overview

A large language model gateway and asset management system that aggregates OpenAI, Claude, and Gemini APIs behind a unified interface. It provides format cross-conversion, channel routing with retry logic, and per-request billing for teams operating multi-provider AI services.

Project type

Infrastructure

Deployment

Refer to project documentation

License

AGPL-3.0

Best for

• Teams and individuals who need to aggregate multiple external LLM services behind a single endpoint while managing internal user quotas, access tokens, and usage costs.

Key capabilities

• Converts requests between OpenAI Compatible, Claude Messages, and Google Gemini formats.
• Supports channel weighted random distribution, automatic retry on failure, and user-level model rate limiting.
• Provides internal top-up, quota allocation, per-request usage, and cache-hit cost accounting with configurable billing policies.
• Controls access through token grouping, specific model restrictions, and user management features.
• Provides a visual web console and statistical analysis interface for monitoring model usage.

Limitations and risks

• The system requires a 64-bit architecture (amd64 or arm64) and does not support 32-bit systems.
• If using external databases, MySQL must be version 5.7.8 or higher, or PostgreSQL must be version 9.6 or higher.
• Converting Google Gemini requests to OpenAI Compatible format currently supports text only and does not support function calling.
• Operating the system as a public generative AI service or API resale service requires the operator to fulfill all regulatory, licensing, and tax obligations.

Getting started

• Clone the repository, edit the docker-compose.yml file to configure settings, and start the service using Docker Compose for a one-command startup. Access the web GUI immediately by visiting http://localhost:3000.

Evidence and sources

• GitHub project description: A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A central…
• Release: v1.0.0-rc.21
• README: This project is intended solely for lawful and authorized AI API gateway, organization-level authentication, multi-model management, usage analytics, cost accounting, and private…
• README: Next-Generation LLM Gateway and AI Asset Management System
• README: All-in-one AI asset management gateway.

Reviewed at: 2026-07-17T07:40:21Z