Models

GET /v1/models — list models currently available in the pool.
Standard OpenAI-shape /v1/models. Returns the set of models advertised by connected providers right now — the list changes as Macs come online and offline.

Endpoint

Response

From Python

Availability

A model appears in the list when at least one connected provider advertises it warm. If every provider serving a given model disconnects, the model drops out of the list within a heartbeat cycle. Requests for a dropped-out model return 404.

Full catalog vs available now

/v1/models shows only what’s available right now. For the full catalog of models the network knows how to serve (including ones not currently loaded on any provider), see Operations → Model catalog.

Rate card

Per-model pricing is served separately at /v1/rate-card:
Returns per-model prompt_rate_per_mtok, completion_rate_per_mtok, and prompt_cache_hit_rate_per_mtok. Rates are set against the OpenRouter frontier and refreshed on operator-defined cadence.