Amazon Fraud Detector prediction pricing ?


' trying to deep dive on Amazon Fraud Detector deployment pricing. My understanding is that customers pay both a per-hour charge ("hosting charge") and a prediction charge ("fraud prediction charge"). Is that correct?

For example, let's say a customer deploys a fraud model to make 1MM predictions a month.

  • hosting charge = 30 days x 24 hours x 1 model x $0.06 per compute hour = $43.20
  • prediction charge = 0.03400000 + 0.015600000 = $21K


1 Risposta
Risposta accettata

Yes, that looks correct and includes the tiering. (Model training charges are missing, but you only wanted to confirm deployment pricing.)

con risposta 4 anni fa

Accesso non effettuato. Accedi per postare una risposta.

Una buona risposta soddisfa chiaramente la domanda, fornisce un feedback costruttivo e incoraggia la crescita professionale del richiedente.

Linee guida per rispondere alle domande