Skip to main content
ME

SAM 3.1

meta/sam-3.1

Meta segmentation model accepting text prompts and images or video, returning object boxes and pixel masks and tracking objects across video frames.

Compare
Context window
-
Input
Image · Text · Video
Output
Other
Released
—

Pricing

Image input

$2.50

USD / 1,000 image

Meta Model API; image segmentation; streaming/non-streaming same

Performance

Overall capability

25.0/100

Coding
—
Reasoning
—
Professional work
—
Knowledge & language
—

No evaluation results available.

Providers

No providers found

ModelRegistry · Catalog updated 2026-10-13