falImageComing soon

fal-ai/sam-3/image

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

This tool is listed but not yet available to run.

Pricing

Coming soon

Price pending

Limits

Runs
In the background
Returns
image
Longest queue wait
1 hour
Run deadline
30 minutes
Longest run, end to end
225 minutes
Largest inline input
1 MB
Largest input file
500 MB
Largest output
5 GB
Outputs per run
16

Input

FieldKindDefaultDescription
image_url requiredURL or file—

URL of the image to be segmented

prompttextwheel

Text prompt for segmentation

text_prompttext—

[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.

point_promptsJSON[]

List of point prompts

box_promptsJSON[]

Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.

apply_masktrue or falsetrue

Apply the mask on the image.

output_formatone of
jpeg, png, webp
png

The format of the generated image.

return_multiple_maskstrue or falsefalse

If True, upload and return multiple generated masks as defined by max_masks.

max_masksnumber (whole)
1 to 32
3

Maximum number of masks to return when return_multiple_masks is enabled.

include_scorestrue or falsefalse

Whether to include mask confidence scores.

include_boxestrue or falsefalse

Whether to include bounding boxes for each mask (when available).

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/image",
    "input": {
      "image_url": "https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg"
    }
  }'