Appearance

Sam 3

POST/v1/run

Sam 3 Video 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/video.

Default: meta/sam-3/video

stringpromptrequired

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

Default:

Optional<string>video

The URL of the video to be segmented.

Optional<boolean>apply_mask

Apply the mask on the video.

Default: true

Optional<string>text_prompt

[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.

Optional<array<object>>point_prompts

List of point prompts

Default:

Optional<array<object>>box_prompts

List of box prompt coordinates (x_min, y_min, x_max, y_max).

Default:

Optional<string>video_output_type

The output type of the generated video.

Allowed values: X264 (.mp4), VP9 (.webm)

Default: X264 (.mp4)

Optional<number>detection_threshold

Detection confidence threshold (0.0-1.0). Lower = more detections but less precise.

Range: 0.1 to 1

Default: 0.5

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