Selfie ↔ ID matching
Built for document photos: small, printed, sometimes years old.
Face API · 1:1 face match
Face verification API.
Confirm two photos show the same person. Compare a selfie with an ID document or a stored profile and get a similarity score and a match decision in one call.
POST /v1/verifyEndpoint
One call. Structured JSON back.
Same token, same error model and the same response conventions as every other SIMSIM endpoint.
POST/v1/verifyConfirm two photos show the same person (1:1) — selfie-to-ID for KYC.
Capabilities
What you can build.
Similarity score
Tune one threshold to balance false matches against friction.
Liveness in the same flow
Add a liveness verdict so a photo of a photo doesn't pass.
Step-up re-authentication
Re-verify returning users before withdrawals or profile changes.
Use cases
Where teams use it.
FAQ
Face Verification questions.
Is face verification high-risk under the EU AI Act?
Biometric verification whose sole purpose is confirming a person is who they claim to be is excluded from the Act's high-risk biometric category. Your GDPR obligations still apply.
What threshold should I use?
Start with the default, then tune on your own traffic. Lower thresholds cut friction but raise the false-match rate — our guide explains the trade-off.
Does it work with old ID photos?
Yes, within reason. Age gaps, glare and low print quality all reduce similarity, so design a manual-review fallback for borderline scores.
Ready to build on faces?
Create a free account, grab your token and make your first recognition call in minutes.