SightRadar
Face recognition API, Rekognition-compatible, pay per photo
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. Free to start with trial credits, no credit card required.
Features
- Drop-in AWS Rekognition replacement: same API shapes, change only the endpoint
- Face search across collections from a single selfie
- 1:1 face verification with configurable similarity thresholds
- Face detection with confidence scores
- Per-photo billing (never per face), no subscription or minimums
- GDPR-ready with a DPA; vectors encrypted per account, never used for training
- SDKs for JavaScript (npm) and Python (PyPI)
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 archives
- Teams on AWS Rekognition cutting their face-API bill without rewriting code
Comments
Hi Fazier, I'm Hitesh, the maker of SightRadar. I built it for teams who need face search, 1:1 verification and face detection without AWS Rekognition-level bills. The API is Rekognition-compatible (CreateCollection, IndexFaces, SearchFacesByImage, CompareFaces, DetectFaces), so existing boto3 or AWS SDK code works by changing the endpoint URL. Billing is per photo, never per face: batch indexing from $0.00062 per photo, with no subscription or minimums. Typical uses are event photographers delivering each guest's photos from one selfie, selfie-based KYC and onboarding, and searching people across your own media library. It's built for consented use: face vectors are isolated and encrypted per account and never used for training. You can try it free with trial credits, no card needed, and there's a live demo on the homepage. I'd love your feedback on the API and docs.
Premium Products
Sponsors
Buy
Makers
Makers
Comments
Hi Fazier, I'm Hitesh, the maker of SightRadar. I built it for teams who need face search, 1:1 verification and face detection without AWS Rekognition-level bills. The API is Rekognition-compatible (CreateCollection, IndexFaces, SearchFacesByImage, CompareFaces, DetectFaces), so existing boto3 or AWS SDK code works by changing the endpoint URL. Billing is per photo, never per face: batch indexing from $0.00062 per photo, with no subscription or minimums. Typical uses are event photographers delivering each guest's photos from one selfie, selfie-based KYC and onboarding, and searching people across your own media library. It's built for consented use: face vectors are isolated and encrypted per account and never used for training. You can try it free with trial credits, no card needed, and there's a live demo on the homepage. I'd love your feedback on the API and docs.
Premium Products
New to Fazier?
Find your next favorite product or submit your own. Made by @FalakDigital.
Copyright ©2026. All Rights Reserved