Skip to main content
GET
Returns the model catalog: the models selectable as judge models (for grading configs, AI analysis, and online evaluators) and the pricing rows used for cost estimation on traces and model-portability replays. The catalog is seeded with a small default set on first boot, a few commonly traced real-world models (gpt-4o-mini, gemini-2.5-pro, gemini-2.5-flash) are ensured on every boot unless you deliberately deleted them, and everything is editable from the dashboard’s Settings pricing panel (or via POST/PUT/DELETE on this same path). Use a model’s id (the exact model string sent to the provider’s API) wherever a judgeModel is accepted. The default judge model is gpt-5.6-luna, unless Platform Settings > Platform model overrides it; the catalog’s isDefault flag only decides which row this list puts first.
The hosted platform’s GET /custom-agent-evaluations/models route is not available on the self-host engine and returns 404 - this catalog endpoint is the replacement. The Python SDK’s client.evaluations.list_models() targets the hosted route; on self-host, read the catalog from this endpoint directly.

Authentication

string
required
Project API key.

Response

array
The default row first, alphabetical after that. Each model object has:
  • GET /api/v1/agent-monitoring/portability/models/unpriced - models seen on token-bearing traces in the last 30 days that have no catalog pricing (so unpriced spend is visible instead of a silent $0).