New API

Free

One API endpoint for all your AI model providers

#api-gateway#llm-aggregation#openai-compatible#multi-provider#key-management#billing#ai-infrastructure#rate-limiting#failover#self-hosted

Inputs: textOutputs: text

Type

Saas

Visit Website

About New API

New API is an open-source, self-hosted AI gateway and model management system designed to aggregate multiple large language model (LLM) providers behind a single, consistent API endpoint. It acts as a unified hub that handles key management, usage tracking, billing aggregation, and load balancing across providers such as OpenAI, Anthropic, Google, Mistral, and dozens of others. The tool can cross-convert various LLM outputs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats, enabling flexible integration with existing applications. Built as a centralized gateway, it supports personal and enterprise model management, offering deployment options via Docker or direct installation. The project is maintained on GitHub under the QuantumNous organization and is intended for lawful, authorized use cases involving AI API gateway functionality, multi-model authentication, usage analytics, and cost accounting.

Key Features

Unified OpenAI-compatible API for 40+ AI providers including OpenAI, Anthropic, Google, Mistral, and DeepSeek

Automatic key rotation and failover when providers hit rate limits or go down

Per-user API keys with spend quotas and model access controls

Token-level billing with usage dashboards and cost tracking per provider

Docker deployment with SQLite, MySQL, or PostgreSQL backends

React admin panel for provider management, user management, and log viewing

Channel priority system to route requests to preferred providers first

Supports chat completions, embeddings, image generation, and audio endpoints

Ollama integration for routing to local and self-hosted models

Open source under MIT license with active community and regular updates

Pros & Cons

Pros

Open-source and free to self-host (no subscription fees for the software itself)
Reduces complexity by consolidating multiple provider APIs into one endpoint
Supports a wide range of popular LLM providers and formats
Includes built-in key management, usage monitoring, and load balancing
Actively maintained with frequent updates and community support

Cons

Requires self-hosting and technical setup (server, domain, Docker knowledge)
Relies on users obtaining their own upstream API keys and complying with provider terms
Documentation may be limited or primarily in Chinese (based on repository languages)
Free-tier usage depends entirely on user's own provider accounts; no built-in free credits
As an open-source project, official support is limited to community channels

Best For

Development teams: Unify multiple AI provider APIs behind a single endpoint for application simplificationSaaS companies: Resell AI model access with per-user billing and quota managementDevOps engineers: Add automatic failover and redundancy for production AI workloadsFinance teams: Track AI spend across teams and providers in one dashboardPlatform teams: Gradually migrate between AI providers without changing application code

Alternatives to New API

Chatgpt.js

Lightweight and Powerful Client-Side ChatGPT Library

RegEx Generator

Effortlessly generate regular expressions with our user-friendly RegEx generator.

Dynaboard AI

Accelerate Software Development with Dynaboard AI

Codeium

Empower Your Coding Abilities with Codeium

Coderabbit

Transform Code Reviews with CodeRabbit's AI-Powered Tools

Point-e

Boost Your Development Workflow Using OpenAI's Point-E on GitHub