SAM 2

Name: SAM 2
Author: Meta

Segment Anything Modelv2.1Current

Meta(technology company)

Released July 29, 2024

API Docs Playground

Context--

CategoryImage Model

About SAM 2

SAM 2, or Segment Anything Model 2, is Meta FAIR’s promptable visual segmentation model for images and videos. The official repository provides inference code, SAM 2.1 checkpoints, example notebooks, training resources, and benchmark tables for SA-V, MOSE, and LVOS video object segmentation tasks.

Capabilities

visionimage segmentationvideo segmentationpromptable segmentationopen weights

Input Modalities

imagevideovisual prompts

Output Modalities

segmentation masksmasklets

Technical Details

API Identifier: facebook/sam2-hiera-large
Category: Image Model

Benchmarks

Performance scores for SAM 2 across standard benchmarks.

SA-V test J&Fofficial SAM 2 README, sam2.1_hiera_large · Sep 2024

79.5%

MOSE val J&Fofficial SAM 2 README, sam2.1_hiera_large · Sep 2024

74.6%

LVOS v2 J&Fofficial SAM 2 README, sam2.1_hiera_large · Sep 2024

80.6%

Speed FPS A100official SAM 2 README, sam2.1_hiera_large · Sep 2024

39.5 frames/s

Pricing and access

Open checkpoints and code are provided under Apache 2.0 in the official repository; compute costs depend on the user’s hardware or cloud environment.

Metatechnology company

Build the future of human connection and the technology that makes it possible

5 Tools8 ModelsFounded 2004Menlo Park, California, United States

View full profile

5 Tools·8 Models

Tools by Meta

Other AI tools from the same organization.

CM3leon by Meta

Natural Language Processing

Discover CM3leon: The Versatile Multimodal AI for Text and Image Generation

Animated Drawings By Meta AI Research

Animation

Animate Your Child's Imaginations!

analogenie

Content Creation

Enhance Your Writing with Analogenie - The Ultimate Analogy Generator

Assistr.ai

Content Creation

Effortless Content Creation with AI Article Generator

Meta Muse

AI Assistant

Research, plan and carry out everyday tasks across connected apps

AI Models by Meta

AI models from the same organization.

Model	Context Window	Price (In / Out per M)	Capabilities
Muse Spark 1.1Current	1.0M	$1.25 / $4.25	reasoningtool usecomputer usecoding+3
DINOv3Current	--	-- / --	visionembeddingsimage understandingself supervised learning
Llama Guard 4 12BCurrent	164K	$0.18 / $0.18	textvisioncode
Llama 4 MaverickCurrent	1.0M	$0.15 / $0.60	textvisioncode
Llama 4 ScoutCurrent	328K	$0.08 / $0.30	textvisioncode
Llama Guard 3 8BCurrent	131K	$0.48 / $0.03	textcode