Skip to navigation
PlatformAI Generation

Media · Generate · Discover generation model field schema (step 1 of 3)

View as Markdown

Step 1 — discover the dynamic per-(model, capability) parameter schema before calling generateVideo. Not needed for generateImage, which takes one fixed contract for every model. A single unified endpoint serves both image and video engines, selected by the required type query param.

Response modes (driven by which query params you pass):

  • type only → {models: [...]} — list every registered engine of that type, its capabilities, and metadata (incl. credits_per_image / estimated_time). Use this to pick a model_id.
  • type + model_id → single-model detail with capabilities map.
  • type + model_id + capability → the full FieldDescriptor schema for that (model, capability) pair (labels, field_type, required flags, enum_values, defaults). This is the contract that generateImage / generateVideo’s parameters must match.

Use this before generating — it eliminates 400 errors on invalid / missing parameter keys.

Authentication

AuthorizationApi-Key

Header authentication of the form Api-Key <token>

OR
AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Query parameters

typeenumRequired
Engine type to introspect.
Allowed values:
model_idstringOptional

Engine id (e.g. KLING_VIDEO_PRO). Omit to list all engines of type.

capabilityenumOptional

Capability — required to receive the per-(model, capability) field schema; otherwise you get the model's capability map.

Allowed values:

Response

Shape depends on which query params are present — see operation description. Always JSON.

Errors

400
Bad Request Error
401
Unauthorized Error