MOmoda
media

Fal Catalog

Changed on

fal's public model catalogue (GET https://api.fal.ai/v1/models with the same query), for Voyager's model discovery and schema checks. Served from a fleet-wide cache for up to 18 hours, then while fal fails, so one agent pricing many models is not limited by fal per address. An endpoint_id neither Studio nor fal (asked again, uncached) knows is a 404 model_not_found naming the closest real models (details.suggestions); one Studio runs that fal does not list, or that fal answers busy, is an empty page. 503 when fal did not answer and nothing is cached (catalog_unavailable with Retry-After when fal was busy; catalog_invalid, not worth retrying, when fal's answer broke its contract). 400 invalid_cursor when fal refuses cursor (one no page issued).

get/media/fal-catalog

Request

  • Base URL
    https://api.moda.app/v1
  • URL
    https://api.moda.app/v1/media/fal-catalog
  • Auth
    HTTP bearer

Query parameters

endpoint_idstring nullable
expand'openapi-3.0' nullable
qstring nullable
categorystring nullable
status'active' | 'deprecated' nullable
cursorstring nullable
limitinteger nullable

Headers

Moda-Version'2026-04-12' | '2026-05-01'
Example:2026-05-01

Calendar-dated API version pin. New integrations should pin 2026-05-01 to opt into the newest response shapes. For back-compat the server also accepts requests with no header and resolves them to the current default (today: 2026-04-12); that default advances on each sunset date. Any unsupported value returns 400 unsupported_version.

Response

Successful Response

modelsobject[] required

fal's catalogue entries, with openapi when expanded.

next_cursorstring nullable

The cursor of the next page, if any.

has_moreboolean nullable

Whether another page follows.

Changes