SightRadar

About SightRadar

SightRadar is a face recognition API for teams that need face search, verification and detection at scale, without AWS Rekognition pricing. It is a drop-in replacement for AWS Rekognition: it uses the same request and response shapes, so you point the AWS SDK (boto3 and others) at the SightRadar endpoint and your existing code keeps working.

Face search finds one person across thousands of photos from a single selfie, which suits event and wedding photo delivery, media libraries and photo archives. 1:1 verification compares two faces with a similarity threshold you choose, for selfie-based onboarding and KYC checks. Face detection returns confidence scores you can threshold on, and photos with no faces return valid empty results instead of errors.

The API covers CreateCollection, IndexFaces, SearchFacesByImage, CompareFaces, DetectFaces and more. SDKs are available on npm and PyPI, plus a Rekognition shim for Python, so teams already on AWS Rekognition can cut their face API bill without rewriting code.

Billing is per photo, never per face: batch indexing costs $0.00062 per photo and real-time requests cost $0.00093 per photo. There is no subscription, no auto-renewal and no minimums, just pay-as-you-go prepaid credits. It is free to start with trial credits and no credit card required.

Privacy by design: SightRadar is GDPR-ready with a Data Processing Agreement, and face vectors are isolated and encrypted per account and never used for model training. It is built for consented use cases such as photo delivery, identity verification and search within your own collections.