Meta

This page is auto-generated from model configurations. Last updated: 2026-03-13.

This reference lists all available Meta video generation models and their parameters. Use these parameter names when calling the Generation API.


SAM3 Video

Segment videos using Meta's SAM (Segment Anything Model) 3. Supports prompt-based and tracking-based segmentation.

Model ID: model_meta-sam-3-video

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_meta-sam-3-video/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----Video to segment
videoPromptingTextstringYes----Text prompt for prompt-based video segmentation