Skip to content
Reduced motion is on. Play a preview to watch it.
Explore models

Image

SAM 3 Image

Select an object or region in an image to produce segmentation masks.

  • Image editing
Create with SAM 3 Image
Preview for SAM 3 Image

Catalog preview for SAM 3 Image. Review your own result before publishing.

A starting point.

Select an object or region in an image to produce segmentation masks. Use a text description, points or boxes to guide the selection; this is not a new-scene generator.

Before you publish.

Compare each mask with the source at the edges and around overlapping objects. A confidence score is a selection aid, not proof that every pixel is correct.

Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.

How credits work · Use the API · Content guidelines

Settings and model questionsCheck the available settings and guidance when preparing your input.

Inputs and settings

Provide image_url, then choose prompt, point_prompts or box_prompts for your selection. Check the full schema for coordinate and grouping rules.

Use include_scores or include_boxes when you need that metadata, and return_multiple_masks when you need separate candidate masks.

Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.

Supported inputs

These fields come from the current studio form for sam-3/image. Other modes may require different inputs.

Input types, requirements and limits for sam-3/image
InputTypeRequirementOptions and limits
image_urlTextRequired—
apply_maskOn/offOptional—
box_promptsListOptional—
include_boxesOn/offOptional—
include_scoresOn/offOptional—
output_formatTextOptionaljpeg, png, webp
point_promptsListOptional—
promptTextOptional—
return_multiple_masksOn/offOptional—
text_promptTextOptional—

Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.

Use SAM 3 Image through the API.

Start with this model ID for the endpoint featured on this page:

sam-3/image

Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.

Check the current model schema for supported inputs and options. Other tasks may use different model IDs.

From quote to result.

Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.

Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.