LLM Reference

Segment Anything Models by AI at Meta

2 models

Details

ResearcherAI at Meta
Models2

Capabilities

VisionAll models
MultimodalAll models

Links

Website

About

Meta's Segment Anything foundation-model family for promptable image and video segmentation, including the distinct SAM 2 and SAM 3 releases.

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

Use when the workload needs image segmentation and multimodal inputs.

Unknown releaseimage segmentationmultimodal inputs

Use when the workload needs image segmentation and multimodal inputs.

Unknown releaseimage segmentationmultimodal inputs

Release Timeline

1 release group
Unknown release
2 current
Segment Anything Model 2
image segmentationmultimodal inputs
Current
Segment Anything Model 3
image segmentationmultimodal inputs
Current

Specifications(2 models)

Segment Anything model specifications comparison
ModelReleasedVisionMultimodal
Segment Anything Model 2YesYes
Segment Anything Model 3YesYes

Available From(1 provider)

Frequently Asked Questions

What is Segment Anything used for?
Segment Anything is used for image segmentation and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
How does Segment Anything compare to Chameleon?
Segment Anything by AI at Meta is strongest where you need image segmentation, while Chameleon by AI at Meta is the closest related family to check for coding. Segment Anything has 2 listed variants, while Chameleon reaches up to 4k context, so compare the specs and pricing tables before choosing a production model.
Which Segment Anything model should I use?
If price is the main constraint, use the pricing table first because Segment Anything does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Segment Anything Model 2 with multimodal inputs.