OmniRoute / Quick start and deployment

Run OmniRoute where you control it.

Install the package, start the local API and choose a supported deployment method.

Start locally Start with Cheaper Inference Back to overview

Quick start

Install, run and connect.

Install the package, launch the gateway, then point any OpenAI-compatible client at port 20128.

Step 1: Install

Install the `omniroute` npm package globally.

omniroute: install

$ npm install -g omnirouteadded 1 package

Step 2: Run

Launch the API and dashboard together on port 20128.

omniroute: run

$ omniroute▸ dashboard ✓ http://localhost:20128/dashboard▸ api ...... ✓ serving on :20128

Step 3: Connect your tool

Use `http://localhost:20128/v1`; the keyless `auto` route works on a fresh install.

omniroute: connect

$ curl localhost:20128/v1/models✓ models listed

Deployment methods

9 supported ways to run OmniRoute.

Install it on a laptop, server or phone, or connect through a supported editor and plugin.

npm

One command on any supported desktop OS

npm install -g omnirouteOpen guide

Docker

Multi-arch AMD64 and ARM64 image

docker run … diegosouzapw/omnirouteOpen guide

Desktop

Native window and system tray on Windows, macOS and Linux

npm run electron:buildOpen guide

ARM

Raspberry Pi, ARM servers and Apple Silicon

native arm64

Android · Termux

Runs on Android without root

pkg install nodejs && npx -y omnirouteOpen guide

PWA

Fullscreen, offline-ready and installable from a browser

Add to Home ScreenOpen guide

OpenCode plugin

Native OpenCode provider plugin

@omniroute/opencode-providerOpen guide

VS Code

OmniRoute models in the Copilot Chat picker

Install OmniCopilotOpen guide

From source

Hack on it and contribute

npm install && npm run devOpen guide