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

Image

SAM 3.1 Image

Select objects in an image with SAM 3.1 segmentation masks.

  • Image editing
Create with SAM 3.1 Image
Preview for SAM 3.1 Image

Catalog preview for SAM 3.1 Image. Review your own result before publishing.

A starting point.

Prepare an object selection for a later cutout or editing step.

Before you publish.

Inspect thin edges, holes and nearby objects included in the mask.

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

Supply image_url, then identify the target with prompt, point_prompts or box_prompts. Boxes use x_min, y_min, x_max and y_max coordinates.

apply_mask controls the masked preview. return_multiple_masks, include_scores and include_boxes expose additional results; choose output_format for delivery. This operation selects regions rather than generating a new scene.

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-3-1/image. Other modes may require different inputs.

Input types, requirements and limits for sam-3-1/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—

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

Use SAM 3.1 Image through the API.

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

sam-3-1/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.