Unified endpoint for discovering model endpoints. Supports three usage modes:
1. List Mode (no parameters): Paginated list of all available model endpoints with minimal metadata.
2. Find Mode (endpoint_id parameter):
Retrieve specific model endpoint(s) by ID. Supports single or multiple IDs.
3. Search Mode (search parameters): Filter models by free-text query, category, or status.
Expansion:
Use expand=openapi-3.0 to include the full OpenAPI 3.0 schema inline in the ‘openapi’ field for each model.
Examples of endpoint_id values:
fal-ai/flux/devfal-ai/wan/v2.2-a14b/text-to-videofal-ai/minimax/video-01/image-to-videofal-ai/hunyuan3d-v21See fal.ai Model APIs for more details.
Authentication: Optional. Providing an API key grants higher rate limits.
Common Use Cases:
API key must be prefixed with "Key ", e.g. Authorization: Key YOUR_API_KEY
Maximum number of items to return. Actual maximum depends on query type and expansion parameters.
x >= 150
Pagination cursor from previous response. Encodes the page number.
"Mg=="
Endpoint ID(s) to retrieve (e.g., 'fal-ai/flux/dev'). Can be a single value or multiple values (1-50 models). When combined with search params, narrows results to these IDs. Use array syntax: ?endpoint_id=model1&endpoint_id=model2
["fal-ai/flux/dev", "fal-ai/flux-pro"]Free-text search query to filter models by name, description, or category
"text to image"
Filter by category (e.g., 'text-to-image', 'image-to-video', 'training')
"text-to-image"
Filter models by status - omit to include all statuses
active, deprecated "active"
Fields to expand in the response. Supported values: 'openapi-3.0' (includes full OpenAPI 3.0 schema in 'openapi' field)
["openapi-3.0"]Successfully retrieved model endpoints
Response containing model data with pagination support