MetamodelSAM 3.1 in the Meta Model API
Meta's object detection and tracking model is now a hosted API call instead of something you run yourself.
Details
- Detects objects from a short text phrase, returns pixel-precise segmentation masks, and tracks them across video frames with identity preserved, all from one call
- Runs on inference built specifically for SAM 3.1's DETR architecture, so there is nothing to host or tune
- Priced at $2.50 per 1,000 images and $0.20 per 1,000 video frames
- Comes with a playground for trying your own media, and works with clients built for the OpenAI SDK
Best for
Pulling specific objects out of images or following them through video without training anything.
When to use it
You need pixel-level cutouts or object tracking and don't want to stand up GPU infrastructure for it.
Who benefits
Developers building media, creative, or video analysis tools who were previously self-hosting SAM.
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →