Launch
SightRadar
Visit
Example Image

SightRadar

Face recognition API, Rekognition-compatible, pay per photo

Visit

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.

Example Image
Example Image
Example Image
Example Image
Example Image

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! SightRadar is a face recognition API that's a drop-in replacement for AWS Rekognition: same request and response shapes, so you migrate by changing the endpoint URL. Index, search, compare and detect faces, billed per photo (from $0.00062), never per face, with no subscription. New accounts get free trial credits, no card required. Try it at https://sightradar.com/playground. Feedback is welcome. — SightRadar Team

The drop-in Rekognition compatibility is the standout idea here — changing only the endpoint to migrate is a much lower-risk pitch than asking teams to rewrite face-search code. Per-photo billing instead of per-face also makes the wedding/event photographer use case easy to cost out. One question: how do you handle false positives at scale when a collection grows to tens of thousands of faces, and can similarity thresholds be set per collection rather than globally?

Drop-in compatibility with the same request shapes is the smart wedge - migration cost is the real blocker for Rekognition users. Two things people will ask before switching: where face indexes are stored (biometrics mean GDPR/CCPA duties) and whether an existing collection can be bulk-imported. Do you support that?

custom-img
Founder of Social Booster Up — building ...

Congrats on the launch! Making this a true drop-in replacement for AWS Rekognition where developers only need to swap the endpoint URL is a huge time-saver—nobody wants to rewrite their entire integration just to switch providers. Billing per photo instead of per face with zero minimums or subscriptions also makes pricing way more predictable for indie apps. Best of luck with the launch!

Premium Products

Comments

Hi Fazier! SightRadar is a face recognition API that's a drop-in replacement for AWS Rekognition: same request and response shapes, so you migrate by changing the endpoint URL. Index, search, compare and detect faces, billed per photo (from $0.00062), never per face, with no subscription. New accounts get free trial credits, no card required. Try it at https://sightradar.com/playground. Feedback is welcome. — SightRadar Team

The drop-in Rekognition compatibility is the standout idea here — changing only the endpoint to migrate is a much lower-risk pitch than asking teams to rewrite face-search code. Per-photo billing instead of per-face also makes the wedding/event photographer use case easy to cost out. One question: how do you handle false positives at scale when a collection grows to tens of thousands of faces, and can similarity thresholds be set per collection rather than globally?

Drop-in compatibility with the same request shapes is the smart wedge - migration cost is the real blocker for Rekognition users. Two things people will ask before switching: where face indexes are stored (biometrics mean GDPR/CCPA duties) and whether an existing collection can be bulk-imported. Do you support that?

custom-img
Founder of Social Booster Up — building ...

Congrats on the launch! Making this a true drop-in replacement for AWS Rekognition where developers only need to swap the endpoint URL is a huge time-saver—nobody wants to rewrite their entire integration just to switch providers. Billing per photo instead of per face with zero minimums or subscriptions also makes pricing way more predictable for indie apps. Best of luck with the launch!

Premium Products