Skip to content

Restricted pilot. The API reference is generated from the running API. Successful matches return manual_review until attack detection is validated.

Support and FAQ

How to get help, and answers to the common questions.

Open a request from Organization in the console and include the request_id. GET /v1/models reports the live model release and whether the engine is ready.

FAQ

  • Why do I only get manual_review? Attack detection isn't validated yet, so nothing is approved automatically.
  • Do you search a face against everyone? No. Each check compares one person with their own enrollment.
  • Do you collect employee consent? No. Your organization does, and attests to it at organization level.
  • What accuracy should I expect? See the model evidence. Public benchmark numbers don't predict your phones and lighting.
NextVersioning and changelog