Meta: SAM 3.1

SAM 3.1 is Meta's segmentation model on Meta Model API. Give it a short noun phrase such as "yellow school bus" with an image or video, and it returns every match as a box and a pixel-accurate mask. …

meta/sam-3.1

SAM 3.1 is Meta's segmentation model on Meta Model API. Give it a short noun phrase such as "yellow school bus" with an image or video, and it returns every match as a box and a pixel-accurate mask. One model handles both stills and clips, and in video it follows each object across frames.

Specifications & capabilities

Input
text, image, video
Output
segmentation
Published model ID
sam-3.1
Capabilities
multimodal, segmentation, videoInput, visionInput

Published prices

1–2 / 2

sam-3.1 ↗

$0.0025

Inference provider
meta
Platform
Meta Model API
Unit
image
Currency
USD
Billing conditions
task
segmentation
streaming_price_parity
true
Billing label
Image segmentation / image

sam-3.1 ↗

$0.0002

Inference provider
meta
Platform
Meta Model API
Unit
video_frame
Currency
USD
Billing conditions
task
segmentation
streaming_price_parity
true
Billing label
Video segmentation / frame

Provider specifications & access

1–1 / 1

Meta: SAM 3.1 ↗

source model id
sam-3.1
hosting
meta-hosted
platforms
  • Meta Model API
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • segmentation
capabilities
  • visionInput
  • videoInput
  • segmentation

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

31 / 100

source id
stanfordFMTI
canonical model id
meta/sam-3.1
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Meta
assessment type
organization-level disclosure
metric
disclosure_score
result label
31 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Original sources

1–5 / 5

Meta · Documentation ↗

Meta · Model documentation ↗

Meta · Pricing ↗

GitHub · Catalog ↗

Meta · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace