Appearance

SAM 3.1 Video

POST/v1/run

Sam 3 1 Video Rle is Meta's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to meta/sam-3-1/video-rle.

Default: meta/sam-3-1/video-rle

stringpromptrequired

Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').

Default:

Optional<string>mask

The URL of the mask to be applied initially.

Optional<string>video

The URL of the video to be segmented.

Optional<integer>max_num_objects

Maximum number of objects to track in the video.

Range: 1 to 128

Default: 16

Optional<array<object>>box_prompts

List of box prompts with optional frame_index.

Default:

Optional<array<object>>point_prompts

List of point prompts with frame indices.

Default:

Optional<integer>frame_index

Frame index used for initial interaction when mask_url is provided.

Default: 0

Optional<number>detection_threshold

Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. Defaults: 0.5 for existing, 0.7 for new objects. Try 0.2-0.3 if text prompts fail.

Range: 0.01 to 1

Default: 0.5

Optional<boolean>apply_mask

Apply the mask on the video.

Default: false

Optional<boolean>boundingbox_zip

Return per-frame bounding box overlays as a zip archive.

Default: false

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: video-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async