Segment Anything Model (SAM)
Video & Audio
Overview
Segment Anything Model (SAM) is an AI-powered image segmentation model from Meta AI that can segment any object in an image through point prompts, bounding boxes, or text prompts. It enables zero-shot segmentation without task-specific training. SAM is designed for researchers and developers building image editing, medical imaging, and computer vision applications needing versatile object segmentation.
- Pricing model
- Free
- Deployment
- Self-hosted / on-premises, API / SDK
- Regions served
- Global
- Categories
- Free, Software & technology, Document review, API / SDK, Self-hosted / on-premises, Video & Audio, Computer vision, Developer tool
- Last updated
- 1 October 2026
- Published
- 1 October 2026
Use cases
Deployment options
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Editorially Reviewed
- Primary source
- segment-anything.com
- Sources cited
- 1
- Last reviewed
- 28 September 2026
- Last updated
- 1 October 2026
Spotted something out of date?
Anyone can suggest a correction — you don't need an account. An editor checks every suggestion against the sources before the record changes.