1개 답변
- 최신
- 최다 투표
- 가장 많은 댓글
2
You can see the details of Rekognition pricing in the next link: Rekognition pricing.
The inference hours is the total hours that your model is available, that means the time that the model is running up. From the moment you start the model until you stop it (So this is second option that you indicated in your comment).
As recommended in the pricing guide, If you expect to process images in batches (e.g. once a day or week, or at scheduled times during the day), you should provision your custom model at scheduled times, process all your images, and then deprovision your resources. If you do not deprovision your resources, you will continue to be charged even if no images are processed.
답변함 일 년 전
While searching estimation for Rekognition pricing.
I get to know of the Estimate based on -- Number of images processed per month AND Number of inference hours per month
For us Number of images processed per month is suitable and it is cost effective. So how can we enable this (Number of images processed per month) service for running our model in Rekognition service.
Thank you