Private Models are currently in invite-only beta for Enterprise Plan customers. To request access, email product@openrouter.ai or contact your OpenRouter account representative.
How It Works
Once your private model endpoint is onboarded:- Approved users and organizations call it through the standard OpenRouter API — the same endpoints they use for public models (chat completions and responses).
- The model slug behaves like any other OpenRouter model. It can be used with Model Fallbacks, Provider Selection, and other routing features.
- Approved private endpoints are prioritized for callers with access, while public fallback candidates remain available if you list them.
Who It’s For
Private Models is a good fit if:- You already have a hosted model endpoint, a fine-tuned model, or a dedicated deployment of a public model that you want to route through OpenRouter.
- Your endpoint is OpenAI-compatible, or close enough that we can integrate it quickly.
- You want your team or organization to access these models through OpenRouter without exposing them publicly.
- You’re on the Enterprise Plan and can share product feedback during the beta.
Requesting Access
Email product@openrouter.ai or reach out to your account representative with:- A short description of the model or endpoint you want to connect.
- The provider or hosting setup you use today.
- Whether the endpoint supports standard chat completions.
- The users or organization who should be given access.
- Any context on how you plan to use it, so we can prioritize the right integration work.