# Private Endpoints: Bring Your Fine-Tuned Models and Capacity to OpenRouter By Steven Van · 2026-10-14 Available by request as an Enterprise add-on, it serves fine-tuned models and reserved capacity under the same slugs, with public providers as optional backup. Enterprise customers can now route their own fine-tuned models and dedicated deployments through [OpenRouter](), alongside the public catalog. [Private Endpoints]() are visible only within the registering organization, and requests use the same API, model slug and routing preferences the team already uses. ## What it covers The feature is meant for fine-tuned models, dedicated deployments of public models, and capacity reserved with a provider. A private endpoint never appears in public model lists, rankings, search, charts or benchmarks, and only organizations the owner approves can see it. Public providers can be set as an optional backup if the endpoint goes down or hits its rate limit. As an example, an organization with a dedicated Azure deployment of DeepSeek V4 Pro can register it as a private endpoint for deepseek/deepseek-v4-pro, and apps keep calling that slug. For that organization the endpoint moves to the front of the provider list by default. Model Fallbacks, Provider Selection and the rest of routing work as they do for any provider. OpenRouter reaches the deployment with the organization's Azure key through BYOK, so Azure bills the customer directly. Reserved capacity gets the same treatment: the organization's traffic goes there first by default, and when it is rate-limited or unavailable, OpenRouter can send the overflow to public providers within the provider preferences and BYOK fallback settings already set. ## Setting up an endpoint An organization admin registers the deployment from the Private Endpoints page in their account. Two requirements apply: - The deployment must be hosted by a provider supported for BYOK, since OpenRouter reaches it with the customer's own key. - It must serve a model already in the OpenRouter catalog, because it inherits that model's slug and capabilities. Custom pricing can be attached so the endpoint shows up accurately in cost reporting, and the admin declares whether the deployment retains prompts. Before anything routes to it, OpenRouter sends one real request through the provider key saved in one of the organization's workspaces. That request checks that the key is accepted, the deployment speaks the OpenAI-compatible format, streaming works, usage comes back for billing, and the model ID matches the registration. After it passes, the admin activates the endpoint and workspaces in the organization can call it by slug. Until then it stays hidden and cannot be called. ## Managing endpoints from code The Private Endpoints API covers the full lifecycle: registering a draft, running the test checks, activation, pricing updates, pausing and deletion. It is authenticated with an organization Management API key, and a single create call registers, tests and activates an endpoint. If the checks fail, the draft is kept and returned with the failed checks so it can be patched and retried. An Idempotency-Key header makes retries safe, since a repeated key returns the endpoint the first request created. The OpenRouter Terraform provider wraps this in an openrouter\_private\_endpoint resource: terraform apply registers, tests and activates the endpoint, and terraform destroy removes it. ## Limits and caveats - A private endpoint is not a Zero Data Retention endpoint. The provider handles prompts as before, and OpenRouter records the data policy declared at registration. - In-Region Routing works if OpenRouter can work out a region from the endpoint's address or one is declared during setup. Requests to us.openrouter.ai or eu.openrouter.ai then route to the deployment inside that region. - The provider key must be saved under BYOK in every workspace that calls the endpoint, and the setup test needs it there too. - Each organization can have up to **10** private endpoints by default, and endpoints still being set up count toward that limit. ## Availability Private Endpoints is an add-on to the **Enterprise plan**. An account representative has to enable it for the organization, after which an admin can add the first endpoint from the Private Endpoints page or through the API. ![OpenRouter]() OpenRouter One API for 500+ AI models across 80+ providers — pay with credits that work anywhere, with automatic fallback when a provider goes down. [View OpenRouter →]() [Original source]() [Read Private Endpoints: Bring Your Fine-Tuned Models and Capacity to OpenRouter on Creators Toolbox]() --- Canonical source: https://creatorstoolbox.com/blog/openrouter-private-endpoints-bring-your-fine-tuned-models-and-capacity