New APINew API
The AI Application Foundation

Connect every AI.
One foundation.

The world's intelligence, drawn to a single interface — OpenAI, Claude, Gemini, and everything yet to come.Open source as our covenant, self-hosted as our ground — built to carry what the future runs on.

Deploy Your Gateway
GitHubAtomGit
40K+GitHub Stars
30+Model Providers
500+Releases Shipped

Inspired by Gargantua from Interstellar

Powering AI applications worldwide

  • LangChain
  • Cline
  • Open WebUI
  • Dify
  • LobeHub
  • FastGPT
  • Cherry Studio
  • n8n
  • Roo Code
  • Coze
Trusted By

Trusted by our users & partners

From hyperscale clouds to frontier AI labs, teams across industries run New API in production.

PKU Big Data Research Institute
Alibaba Cloud
Features

Enterprise-Grade AI Gateway

New API is a powerful AI gateway and asset management system that unifies access to 30+ AI providers with intelligent routing and cost control.

One API for All
100% OpenAI compatible endpoint for all AI providers.

Unified API Access

Access 30+ AI providers through a single, unified endpoint.

Learn more
gpt-5.5
claude-opus-4-8
gemini-3.1-pro
deepseek-v4-pro
llama-4-maverick
mistral-large-3

Model Selection

Choose from 100+ models across multiple providers.

Learn more
New API

Multi-Provider Support

Seamlessly integrate with OpenAI, Claude, Gemini, and more.

Learn more

Usage Analytics

Monitor usage, track costs, and optimize performance.

Learn more
The Process

Deploy AI gateway in 3 steps

Follow these simple steps to deploy, integrate, and scale your AI infrastructure with confidence.

1

Configure Channels

Add and configure your AI service providers with flexible channel management and priority settings.

2

Deploy & Integrate

One-click deployment with 100% OpenAI-compatible API. Seamless integration with your existing applications.

3

Monitor & Optimize

Track usage, analyze costs, and optimize performance with comprehensive analytics and insights.

AstrLink · On-device privacy

Your agent reads .env. The model doesn't need to.

AstrLink runs on your computer. It swaps sensitive values for placeholders before a request leaves and restores them in the reply.

Your computer
Your agentClaude Code · Codex
AstrLinkRedact · restore
New APINew APIKeys · quotas · routing
Upstream modelsOpenAI · Claude · Gemini
What your agent reads
# .envDB_URL=postgres://admin:q7Vt2LmX9pRk@10.0.3.17/prodONCALL=Zhang Wei <[email protected]>
What the model receives
# .envDB_URL=postgres://admin:secret@IP/prodONCALL=name <email>
Replies are restored on your machine, so your agent carries on.Fictional example. Results depend on your policies.

Quotas on the server, privacy on the laptop

New API manages keys and quotas. AstrLink swaps out sensitive data on each dev machine first.

One local endpoint for everything

Subscriptions, provider APIs and your New API behind one address.

See why an agent stalled

Who answered, how long it took, every retry and the estimated cost.

Explore AstrLinkStar on GitHub

Open source · Apache-2.0 · macOS / Windows / Linux

Step into the future of AI infrastructure

Experience the cutting-edge solution that unifies all AI providers. Build faster, scale smarter with intelligent routing and cost optimization.

Deploy your gateway