GET

/v1/schemas/fal/image/fal-ai/moondream3-preview/segment

Accept:

kind inputactivity imagehash a82610b6…extracted Jul 15, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `8265f0e20eb4889248639941214d7c152bd1d12743c906d70f6458c2d3d6660d` { "fetchedAt": 1784090287, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 2 required · 2 $defs

property	type	description	constraints
image_url*	string	URL of the image to be processed
object*	string	Object to be segmented in the image
settings	SegmentSamplingSettings	Sampling settings for the segmentation model	nullable
preview	boolean	Whether to preview the output and return a binary mask of the image	default: false
spatial_references	Point \| number[][]	Spatial references to guide the segmentation. By feeding in references you can help the segmentation process. Must be either list of Point object with x and y members, or list of arrays containing either 2 floats (x,y) or 4 floats (x1,y1,x2,y2). NOTE: You can also use the [point endpoint](https://fal.ai/models/fal-ai/moondream3-preview/point) to get points for the objects, and pass them in here.	nullable

Types

2 $defs

Pointobject

x*	number	X coordinate of the point in normalized format (0 to 1)
y*	number	Y coordinate of the point in normalized format (0 to 1)

SegmentSamplingSettingsobject

temperature	number	Sampling temperature to use. Higher values will make the output more random, while lower values will make it more focused and deterministic.	0 ≤ n ≤ 1 · default: 1
top_p	number	Nucleus sampling probability mass to use, between 0 and 1.	0 ≤ n ≤ 1 · default: 1
max_tokens	integer	Maximum number of tokens to generate.	n ≥ 1 · nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/moondream3-preview/segment","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}