Loading page
Loading page

AI · OpenRouter alternative
One OpenAI and Anthropic compatible endpoint in front of all your AI providers, with routing, fallbacks and cost tracking.
Tera Router is a self-hosted AI router. It gives you one gateway that speaks both the OpenAI and the Anthropic API formats. Behind it, you connect as many providers as you like. A dashboard manages accounts, routing rules, model catalogs and cost.
Routing is flexible. You can set chains with priority, round-robin or load balancing, and add fallback steps. Model aliases define the public model list. When a provider and model pair keeps failing, Tera Router can exclude it for a while.
It is for developers and teams that use several AI providers and are tired of managing keys in every app. It also helps anyone who wants to see what each model costs.
A hosted router sees every prompt you send. Running your own keeps the routing layer, the keys and the usage data on your server.
The trade-off is that you run another service in the request path. If it is down, your AI calls stop. You look after updates, backups of its data and the admin login in the Environment tab. Your prompts still go to the providers you connect.
Containers: ghcr.io/montara-project/tera-router:v1.23.0, ghcr.io/headroomlabs-ai/headroom:0.41.0
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Tera Router, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Tera Router setup screen.