About New API
New API is an AI gateway you host yourself, built for apps, agents and teams. It lets you plug in upstream model services, present one consistent API to clients, and handle routing, access, usage and cost management centrally. It is written in Go and released under the AGPL-3.0 license.
It can convert between formats so that various LLMs are reachable through OpenAI-compatible, Claude-compatible or Gemini-compatible interfaces. Supported upstreams range from OpenAI, Anthropic and Gemini to Azure OpenAI, AWS Bedrock, Vertex AI, DeepSeek and Qwen, plus other compatible services, and a web console is used for administration.
Typical uses are sharing authorized model access across a team, switching providers without reconfiguring every client, and operating a private multi-model service. The README stresses lawful, authorized use: users must obtain upstream keys legitimately, follow upstream terms, and meet any regulatory obligations if they offer AI services to the public. It suits teams and organizations that need centralized model management.
Key features
- Unified gateway for multiple upstream model services
- OpenAI, Claude and Gemini compatible formats
- Routing, access control and usage tracking
- Cost accounting and usage analytics
- Web console for administration
- Self-hosted private deployment
Good fit for
- Sharing model access across a team
- Switching providers without changing clients
- Private multi-model service
New API: questions and answers
- What is New API used for?
- New API is a self-hosted AI gateway that connects many upstream model services and exposes one consistent API, with routing, access control, usage tracking and a web console. It is a good fit for sharing model access across a team, switching providers without changing clients and private multi-model service.
- Is New API open source?
- Yes. New API is open source under the AGPL-3.0 licence. Its source code is on GitHub at QuantumNous/new-api and is written mainly in Go.
- Is New API free?
- Yes. New API is open source, so the software itself is free to use.
- Can I self-host New API?
- Yes. New API can be self-hosted on your own server or infrastructure.
- What is New API an alternative to?
- New API is an open-source alternative to OpenRouter and Portkey. Other open-source alternatives to OpenRouter include LiteLLM, Helicone and One API.
- Is New API actively maintained?
- Yes. The most recent commit to New API was on 17 November 2026, and the latest release is v1.0.0-rc.51, published on 13 November 2026. The project has 52k stars on GitHub, with 1.9k added in the last 30 days.
Open-source alternatives to New API
See all
LiteLLM
AI Infrastructure
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (o
OSSvs Amazon Bedrock★ 63k
Helicone
AI Infrastructure
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and expe
Apache-2.0vs OpenRouter★ 6.3k
One API
AI Infrastructure
LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一
MITvs OpenRouter★ 37k
LLM Gateway
AI Infrastructure
Route, manage, and analyze your LLM requests across multiple providers with a unified API
OSSvs Amazon Bedrock★ 1.7k
Portkey AI Gateway
AI Infrastructure
A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardra
MITvs Amazon Bedrock★ 13k
LocalAI
AI Infrastructure
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video -
MITvs ChatGPT★ 50k
SaaS alternatives to New API
See all
OpenRouter
AI Infrastructure
Unified API gateway for accessing many large language models from one endpoint
SaaS
Portkey
AI Infrastructure
AI gateway and observability platform for managing LLM requests
SaaS
AllToken
AI Infrastructure
Unified API gateway to LLMs from OpenAI, Anthropic and Google with usage tracking and routing
SaaSAI Stats
AI Infrastructure
Database of AI models plus an OpenAI-compatible gateway with usage, pricing and reliability monitoring
SaaS
AnyRouter
AI Infrastructure
Unified LLM gateway that routes coding agents and MCP servers through a single endpoint
SaaS
api-hub.ai
AI Infrastructure
Single API for accessing many AI models behind one endpoint
SaaS

