GET
/v1/schemas/fal/video/fal-ai/sam-3/video
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source tracec40632a951248f6ac1e3a6af057562c5978233fa6e2555d41dcc189d9b155bbf{
"fetchedAt": 1785214897,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
8 properties · 1 required · 2 $defs| property | type | description | constraints |
|---|---|---|---|
| video_url* | string | The URL of the video to be segmented. | |
| apply_mask | boolean | Apply the mask on the video. | default: true |
| detection_threshold | number | Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. | 0.1 ≤ n ≤ 1 · default: 0.5 |
| point_prompts | PointPromptBase[] | List of point prompts | default: [] |
| video_output_type | enum | The output type of the generated video. | X264 (.mp4) | VP9 (.webm) · default: "X264 (.mp4)" |
| prompt | string | Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth'). | default: "" |
| text_prompt | string | [DEPRECATED] Use 'prompt' instead. Kept for backward compatibility. | nullable · deprecated |
| box_prompts | BoxPromptBase[] | List of box prompt coordinates (x_min, y_min, x_max, y_max). | default: [] |
Types
2 $defsBoxPromptBaseobject
| object_id | integer | Optional object identifier. Boxes sharing an object id refine the same object. | nullable |
| y_max | integer | Y Max Coordinate of the box | nullable |
| y_min | integer | Y Min Coordinate of the box | nullable |
| x_min | integer | X Min Coordinate of the box | nullable |
| x_max | integer | X Max Coordinate of the box | nullable |
PointPromptBaseobject
| y | integer | Y Coordinate of the prompt | nullable |
| object_id | integer | Optional object identifier. Prompts sharing an object id refine the same object. When a text prompt is also given, the id selects which detected object the points refine. | nullable |
| label | enum | 1 for foreground, 0 for background | 0 | 1 · nullable |
| x | integer | X Coordinate of the prompt | nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/sam-3/video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}