Sam 3

Name: Sam 3
Author: fal

other

SAM 3 is a unified foundation model for promptable segmentation in images and videos.

Capabilities

Show unsupported (8)

No supported capabilities recorded.

Model IDfal-ai/sam-3/image/embed

Providerfal

Creatorfal

Family—

License—

Statusactive

Typeother

Input modalitiesimage

Output modalities—

Open weight—

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2025-11-20

Sourceofficial

GET/v1/models/fal/fal-ai/sam-3/image/embed