Sam 3
/v1/runSam 3 Image Rle is Meta's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.
Request body
Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.
Model identifier. Set to meta/sam-3/image-rle.
Default: meta/sam-3/image-rle
Text prompt for segmentation
Default: wheel
URL of the image to be segmented
The format of the generated image.
Allowed values: jpeg, png
Default: png
Apply the mask on the image.
Default: true
Maximum number of masks to return when `return_multiple_masks` is enabled.
Range: 1 to 32
Default: 3
Whether to include mask confidence scores.
Default: false
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.
Default:
If True, upload and return multiple generated masks as defined by `max_masks`.
Default: false
[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.
List of point prompts
Default:
Whether to include bounding boxes for each mask (when available).
Default: false
Response Schema
The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.
Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.
Current public run status.
Allowed values: pending, running, completed, failed, timeout
Public SandBase model name used for this run.
Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.
Present only for failed or timeout runs. Contains a public error type and sanitized message.
Stable public error category.
Sanitized error message safe to show to clients.
Usage details when available.
Model capabilities
Capabilities declared by the model registry.
Default: image-to-image
Execution mode declared by the model registry.
Default: async