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

Video

Segment Anything 2

Select regions in a still image with Segment Anything 2’s image mode.

  • Image editing
  • Video editing
Create with Segment Anything 2
Preview for Segment Anything 2

Catalog preview for Segment Anything 2. Review your own result before publishing.

A starting point.

Select regions in a still image with Segment Anything 2’s image mode. Use spatial selection rather than a scene-generation prompt.

Before you publish.

Check selected boundaries and excluded regions; inspect the output format before relying on transparency.

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

Send image_url and supply point prompts or box_prompts using the schema’s coordinate structure.

apply_mask controls applying the selection to the image. For video, choose the separate video operation and its schema.

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 sam2/image. Other modes may require different inputs.

Input types, requirements and limits for sam2/image
InputTypeRequirementOptions and limits
image_urlTextRequired—
apply_maskOn/offOptional—
box_promptsListOptional—
output_formatTextOptionaljpeg, png, webp
promptsListOptional—

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

Other modes and their inputs

Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.

Video editingsam2/video

Supported inputs

These fields come from the current studio form for sam2/video. Other modes may require different inputs.

Input types, requirements and limits for sam2/video
InputTypeRequirement
video_urlTextRequired
apply_maskOn/offOptional
boundingbox_zipOn/offOptional
box_promptsListOptional
mask_urlTextOptional
promptsListOptional

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

Open this operation in the studio

Use Segment Anything 2 through the API.

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

sam2/image

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

Available 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.