SightRadar
Face recognition API, Rekognition-compatible, pay per photo
8
views
0
comments
0
clicks out
Gallery
About SightRadar
SightRadar is a high-accuracy face recognition API built as a drop-in replacement for AWS Rekognition. It uses the same request and response shapes (CreateCollection, IndexFaces, SearchFacesByImage, CompareFaces, DetectFaces), so you migrate by changing the endpoint URL. Find a person across thousands of photos from one selfie, run 1:1 verification with your own similarity threshold, or detect faces with confidence scores. Billing is per photo, never per face, with no subscription or minimums.
Overview
Who is it for?
Developers adding consented face search, selfie KYC or event photo delivery, and teams moving off AWS Rekognition
Problem
Face recognition APIs like AWS Rekognition get expensive at scale, and switching providers usually means rewriting integration code.
Solution
SightRadar keeps the Rekognition request and response shapes, so you point the AWS SDK (boto3 and others) at a new endpoint and your existing code keeps working, billed per photo with free trial credits to start.
What makes it different
Drop-in Rekognition compatibility (change only the endpoint), per-photo billing that never charges per face, no subscription or minimums, photos with no faces return valid empty results, and face vectors encrypted per account and never used for model training. SDKs on npm and PyPI.
Discussion · 0
Sign in to join the discussion. Free, and it takes one click with Google.
No comments yet — be the first to give this maker real feedback.
