List the provider endpoints that can serve a model

Every Inference Provider endpoint that can serve the model for this key, in the order Stav tries them, each with its own context window, max output tokens and quantization. Same shape and field names as OpenRouter's /api/v1/models/{author}/{slug}/endpoints.

Only endpoints a request could actually reach are listed: your workspace's policy (sovereignty floor, compute region, ZDR, blocked providers) applies. Send an entry's id as model to pin that endpoint.

For a Router (or auto, your workspace's default Router), the list is every endpoint of every model the Router can pick, under the Router's own rules as well, best model first. Each entry's model_id names its model, and data.stav_router is true. The models are paged with page and page_size (at most 100); data.stav_total_models is the whole pool.

Stiparametere

• model_idstringpåkrevd

  Anything you can send as model: a catalogue slug (openai/gpt-oss-120b), a bare name with one match, a Router (@your-workspace/router) or auto.

Spørreparametere

• pageinteger

  Router or auto only. The page of the Router's models.

  Standard: 1
• page_sizeinteger

  Router or auto only. Models per page.

  Standard: 100

Feil

Alle feilkoder, hva de betyr og hva du gjør: Feil.