cita-777/metapi

把你在各处注册的 New API / One API / OneHub / DoneHub / Veloera / AnyRouter / Sub2API 等站点， 汇聚成 一个 API Key、一个入口，自动发现模型、智能路由、成本最优

What it solves

Metapi is a meta-aggregation layer that solves the fragmentation of AI API providers. Instead of managing multiple API keys, balances, and model lists across various aggregation sites (like New API, One API, or official providers), it consolidates them into a single entry point and one API key for all downstream tools.

How it works

It acts as a unified gateway that connects to multiple upstream AI model providers and aggregation panels. It automatically discovers available models from these sources and routes requests based on configurable strategies. It converts formats between OpenAI and Claude standards to ensure compatibility with a wide range of AI clients.

Who it’s for

Developers and power users who use multiple AI API providers or aggregation sites and want a single, stable, and cost-effective way to access various LLMs without manually switching keys or configurations in their tools.

Highlights

  • Unified Gateway: Provides a single API key and entry point compatible with OpenAI and Claude formats.
  • Smart Routing: Automatically selects the best channel based on cost, balance, and usage rates, with automatic failover and cooling periods for failed channels.
  • Multi-Platform Aggregation: Supports a wide array of upstream platforms including New API, One API, and official endpoints for DeepSeek, Gemini, and others.
  • Automated Management: Features automatic daily check-ins for credits, balance monitoring with alerts, and automatic token renewal.
  • Model Marketplace: A dashboard to compare pricing, coverage, and performance metrics across different upstream providers.
  • Self-Hosted: All data is stored locally in the user's own environment for privacy and security.

Related

  • Project
    modelbus/one-api-pro

    An enterprise-grade AI API gateway that unifies 30+ model providers under one OpenAI-compatible interface with built-in subscription management and billing.

  • Project
    labring/aiproxy

    A production-ready AI gateway that provides intelligent routing, protocol conversion, and multi-tenant management for multiple AI providers via an OpenAI-compatible API.

  • Project
    MAX-API-Next/MAX-API

    MAX API is an open‑source gateway that unifies access to many LLM providers, adds governance (auth, rate‑limits, quotas), recoverable billing, and a SmartOps dashboard for evidence‑driven monitoring. It’s built with Go, Gin, React and supports SQLite, MySQL, PostgreSQL and Redis. Ideal for teams needing a secure, cost‑controlled, multi‑vendor model layer for agents and AI applications.

  • Project
    BenedictKing/ccx

    A high-performance AI API proxy and gateway that unifies Claude, OpenAI, and Gemini APIs into a single entry point with built-in channel management and failover.

  • Project
    QuantumNous/new-api

    New API is an open‑source, self‑hosted gateway that unifies access to many LLM providers behind a single OpenAI‑compatible API. It handles routing, usage/cost tracking, fine‑grained access control, and offers a multilingual web console plus extensible JavaScript task plugins. Deployable via Docker or Docker‑Compose, it’s built with Go (backend) and React/Bun (frontend) and is licensed under AGPL‑v3.