SightRadar is a face recognition API for teams that need face search, verification and detection at scale, without AWS Rekognition's pricing. It is Rekognition-compatible: point the AWS SDK (boto3 and others) at SightRadar's endpoint and your existing code keeps working.
Key features
- Drop-in AWS Rekognition replacement: same API shapes (CreateCollection, IndexFaces, SearchFacesByImage, CompareFaces, DetectFaces), change only the endpoint
- Face search across your own collections from a single selfie
- 1:1 face verification with a similarity threshold you choose
- Face detection with confidence scores you can threshold on
- Photos with no faces return valid empty results, not errors
- Per-photo billing (never per face), no subscription or minimums
- Privacy by design: GDPR-ready with a Data Processing Agreement, face vectors isolated and encrypted per account, never used for model training
- SDKs for JavaScript (npm) and Python (PyPI), plus a Rekognition shim for Python
Use cases
- Event and wedding photographers delivering each guest's photos from one selfie
- Apps adding selfie-based identity verification (KYC, onboarding)
- Media libraries and DAMs tagging and searching people across their own archives
- Teams on AWS Rekognition cutting their face-API bill without rewriting code
Pricing
- Free to start: trial credits, no credit card required
- Batch indexing: $0.00062 per photo
- Real-time: $0.00093 per photo
- Search by face ID: $0.00062; face storage $6 per million faces per month
- Pay-as-you-go prepaid credits, no subscription, no auto-renewal, no minimums
Links
Docs: https://sightradar.com/docs
Pricing: https://sightradar.com/pricing
Migration guide: https://sightradar.com/migrate
