SAM 3 is a unified foundation model for promptable segmentation in images and videos.
Usage-based, per image
Output
Example
Example output from SAM 3
Overview
Built by Meta, Segment Anything Model 3 is a image editing model. SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. Users can expect precision edits that preserve the original's integrity in production. Automatic provider failover keeps your pipeline running when others go down.
Frequently asked questions
Related models
FLUX.2 [klein] 9B — Edit
black-forest-labs/flux-2-klein-9b/edit
Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs. Precise mo...
Reve Edit
reve/edit
Reve's edit model lets you upload an existing image and then transform it via a ...
Wan 2.7 Pro Edit
alibaba/wan/v2.7/pro/edit
Edit and transform images using text instructions with the WAN 2.7 Pro model for...
Nano Banana 2 — Edit
google/nano-banana-2/edit
Nano Banana 2 is Google's new state-of-the-art image generation and editing mode...
Start generating with SAM 3
Get API access in minutes. No GPU setup, no infrastructure to manage.