Deploy OmniRoute

By NEXUS AI Team · Contact: nexusai.run/contact

A free AI gateway: one OpenAI-compatible endpoint for hundreds of model providers.

A free AI gateway: one OpenAI-compatible endpoint for hundreds of model providers.

OmniRoute is an MIT-licensed AI gateway with quota-aware automatic fallback, token compression, MCP and A2A support, and a dashboard. It works with Claude Code, Codex, Cursor, OpenCode, and other coding tools. The template deploys it with no configuration; it generates its own secrets on first start.

Deploy OmniRoute to NEXUS AI · OmniRoute on GitHub · Tested 2026-09-24 · MIT license

Security

The API requires a key from the start, and the dashboard stays locked until you complete setup with the token from the logs.

What gets created

• The OmniRoute gateway and dashboard, built from the repository's Dockerfile
• A public HTTPS URL on port 20128
• Its database and generated secrets inside the container

Before you deploy

• Accounts or API keys for the providers you want to connect, including free ones
• Runs on the Free plan
• First build takes several minutes

How to deploy

1. Press Deploy. Sign in or create a NEXUS AI account and you return to the same page.
2. Choose a name for your URL, review the settings, and press Deploy again.
3. Wait for the build, then open your URL when the status is Running.

After it deploys

1. Open your URL. The setup wizard asks for a one-time setup token
2. Copy the token from the deployment's Logs tab in NEXUS AI, paste it, and choose your password
3. Connect a provider under Providers and copy an API key from Endpoints
4. Point your tools at https://<your-app>.nexusai.run/v1

Your data

Data and generated secrets live inside the container. Stopping and starting keeps them; rebuilding the deployment starts fresh.

OmniRoute is an independent open-source project. NEXUS AI is not affiliated with it, and the name belongs to its owners.

Browse all templates

Start for free · Read the documentation · About NEXUS AI · Contact