← All projects
Running AI at scale

One API

One gateway for reaching many AI providers, such as OpenAI, Claude and Gemini, in a single standard way.

What it does

Each AI company has its own API (a doorway that lets programs talk to its models). One API sits in the middle so apps can reach many providers through one OpenAI-style doorway.

Administrators can manage access keys, set usage limits, spread traffic across accounts, and track usage. The README asks users to follow providers' terms and local laws.

Who it's for

Teams and administrators who manage access to several AI services.

Can I use it without coding?

With some setup. Runs on a server, usually with one Docker command, and is managed through a web page. New to this? Start here.

Can I run it?

Cost
Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
Runs on
Server
Privacy
Sends what you give it to an online service
API key
Needed. An API key is a password-like code from an online AI service. What's that?

Try it

  1. Run One API on a server with Docker, or download the program from its releases page.
  2. Log in to its web admin page and change the default password straight away.
  3. Add your AI providers' API keys as channels, then create an access token for your apps.
Official download page

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
  • What you type or upload is sent to an online service. Avoid sharing private or sensitive information.
  • More on staying safe