Meta logo

Segment Anything Model

Segment Anything Modelv1Current
byMetaMeta(technology company)
Released April 5, 2023
Context--
Training CutoffSA-1B dataset release, 2023
CategoryVision Model

About Segment Anything Model

Segment Anything Model (SAM) is Meta AI Research's promptable image segmentation foundation model for producing object masks from points, boxes, or other prompts in images. The public repository provides inference code, trained checkpoints, and example notebooks for using the model.

Capabilities

visionimage segmentationpromptable segmentationresearch

Input Modalities

imagepoint-promptbox-promptmask-prompt

Output Modalities

segmentation-mask

Technical Details

API Identifier
facebookresearch/segment-anything
Category
Vision Model

Tags

image-segmentationcomputer-visionfoundation-modelmeta-aiopen-sourceresearch-model

Pricing and access

Open-source research model and checkpoints; no hosted API pricing is documented in the repository. Users pay their own compute costs.

Meta logo
Metatechnology company

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

4 Tools8 ModelsFounded 2004Menlo Park, California, United States
View full profile

Tools by Meta

Other AI tools from the same organization.

AI Models by Meta

AI models from the same organization.

ModelContext WindowPrice (In / Out per M)
Muse Spark 1.1Current1.0M$1.25 / $4.25
DINOv3Current---- / --
Llama Guard 4 12BCurrent164K$0.18 / $0.18
Llama 4 MaverickCurrent1.0M$0.15 / $0.60
Llama 4 ScoutCurrent328K$0.08 / $0.30
Llama Guard 3 8BCurrent131K$0.48 / $0.03

Related News

Latest coverage and updates.