falVideo to videoComing soon

fal-ai/sam-3/video

Name: fal-ai/sam-3/video
Brand: fal

fal-ai/sam-3/video is a video to video tool from fal that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`video_url` required	URL or file	—	The URL of the video to be segmented.
`prompt`	text		Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').
`text_prompt`	text	—	[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.
`point_prompts`	JSON	[]	List of point prompts
`box_prompts`	JSON	[]	List of box prompt coordinates (x_min, y_min, x_max, y_max).
`apply_mask`	true or false	true	Apply the mask on the video.
`video_output_type`	one of X264 (.mp4), VP9 (.webm)	X264 (.mp4)	The output type of the generated video.
`detection_threshold`	number 0.1 to 1	0.5	Detection confidence threshold (0.0-1.0). Lower = more detections but less precise.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/sam-3/video",
    "input": {
      "video_url": "<video_url>"
    }
  }'