MetaSAM 3 VideoVideo → Video
Segment and track objects through a video from a text prompt — name several objects separated by commas and SAM 3 keeps each one masked across every frame.
SegmentationObject TrackingVideo Input
Params
Billed at this model’s published rate.
Result
Other models from Meta
Same vendor, same API call — the differences are below.
| Model | Use case | Price | Resolution | Duration | Count | Added |
|---|---|---|---|---|---|---|
| Muse Image 1.0 | Text → Image | $0.011 / gen | — | — | 1–10 | Mon, Aug 31 |