List Models

Response for GET /inference/models.

Lists the VLM models supported for the element-locator task, each with its context window and final per-token pricing, so a client can compare cost and validate find(model=...) up front instead of round-tripping to /locate and getting a 400.

The set is curated: these are the vision-capable models supported for UI grounding. /locate enforces it — an unsupported model is rejected, so this is the authoritative allowlist, not just advisory.

Shaped like a standard /v1/models response ({object: "list", data: [...]}).