New API
A free, open-source self-hosted gateway that puts a single API in front of a dozen different AI providers (OpenAI, Claude, Gemini and more), with built-in usage tracking and billing — useful if you're reselling or managing AI access for a team or product.
🔗 Visit New API
Description
Managing access to multiple AI providers across a team or product usually means juggling separate API keys, separate billing, and separate rate limits for each one. New API solves that by sitting in front of all of them as a single, self-hosted gateway: your application talks to one OpenAI/Claude/Gemini-compatible endpoint, and New API handles routing, tracking and billing behind the scenes.
New API is an open-source (AGPLv3) self-hosted hub that converts requests between OpenAI, Claude and Gemini API formats, supports 10+ underlying LLM providers, and adds organization-level authentication, permission management, and per-user usage analytics and cost accounting. It includes intelligent routing with automatic retry on failure, Docker-based deployment, a multi-language admin UI, and built-in billing integration (Stripe, EPay) for teams that need to charge internal or external users for AI access. It's a very actively developed project with over 46,000 GitHub stars.
💬 Our review
The short version: if you're managing AI API access for a team, a product with multiple users, or reselling AI capacity, New API is a mature, feature-rich self-hosted gateway that adds the billing and access-control layer most simple proxy tools skip.
The differentiator versus a lighter routing tool like LiteLLM is scope: New API isn't just protocol translation, it's a full internal platform with organization accounts, permissions, usage analytics, cost accounting, and payment integration (Stripe, EPay) baked in — closer to a mini AI-billing SaaS you run yourself than a simple pass-through proxy. Its huge community (46,000+ stars, thousands of commits) also means a lot of real-world battle-testing across deployment scenarios. Compared to using each AI provider's dashboard directly, centralizing everything through one gateway gives a single place to see cost, usage, and access across every model your organization touches.
The honest limits: it's licensed AGPLv3, which is a copyleft license — running a modified version as a network service can trigger source-disclosure obligations, so legal review is worth doing before deploying it commercially, especially compared to more permissively-licensed alternatives. Multi-node production deployments also need a shared database and secrets management, adding real operational complexity. For a team or product that genuinely needs multi-provider access control and billing, it's a strong, free option to self-host; for a solo developer who just wants to call multiple AI APIs from one client library, a lighter tool like LiteLLM has far less overhead.
💰 Pricing
📊 Global score
🤖 AI-enriched data
Outil open-source (AGPLv3), gratuit à auto-héberger ; support commercial disponible séparément. Attention : AGPLv3 impose des obligations de divulgation du code pour un usage en service réseau modifié.
Pros
Passerelle unique pour 10+ fournisseurs LLM, compatible formats OpenAI/Claude/Gemini
Gestion d'organisation, permissions et suivi d'usage/coût par utilisateur intégrés
Facturation intégrée (Stripe, EPay) — utile pour revendre ou refacturer l'accès IA
Communauté très active (46k+ étoiles) — solution éprouvée en production
Cons
Licence AGPLv3 — obligations de divulgation de code à vérifier avant usage commercial
Déploiement multi-nœuds nécessite base de données partagée et gestion de secrets
Plus complexe qu'un simple proxy comme LiteLLM si le besoin est basique