meta
meta/sam-3-video/Released Nov 2025

Segment Anything 3 - Video

Detects, segments, and tracks objects across video frames using text, exemplars, points, or masks, with memory for occlusions and real-time streaming.

Provider
meta
Modality
video-to-video
Released
Nov 2025
Pricing
$0.02 / image

Ready to build with Segment Anything 3 - Video?

Sign in to grab your API key and start making requests.
bash
curl -sSf -X POST https://staging.hub.oxen.ai/api/videos/generate \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "sam-3-video",
  "input_video": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4",
  "prompt": "the ox horns",
  "apply_mask": true
}'