Find tools › Open-source projects › Spend less on AI

new-api
Open-source project · by QuantumNous
A hub you run on your own server that combines many AI services into one address and one set of keys.
Some setupVery popular
What it costs
Free and open source; you may pay for the AI model it uses.
Use it to
- Route all your AI tools through one shared key
- Mix cheaper and premium AI models behind one address
- Share AI access with a team and see usage
How to start
Install Docker on the computer or server that will host it.
In a terminal, run the docker run command from the README to start it.
Open localhost port 3000 in your browser to set it up and add provider keys.
Before you install
- Checked by a personWe read what it does before listing it.
- License: AGPL-3.0You are allowed to use it under these terms.
- Last updated 2026-11-18
More detail
A self-hosted AI gateway that aggregates and distributes various LLM services under unified API formats.
It solves the problem of managing multiple upstream LLM providers and disparate API keys by centralizing routing, access control, usage analytics, and cost accounting. Reach for it when you want to run a private multi-model service or share authorized model access across a team.
Similar tools
Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map