Amazon Rekognition billing

Question

I'm developing an application with AWS rekognition and have some billing questions. This application allows customers who attended an event to use the app to view the photos in which they appeared.

Assume that each person who attended the event has a profile image that will be used to detect their faces in all photos shot at the event. This profile image is saved in indexfaces to form a collection.

500 images from a certain event are saved in an S3 bucket.

What would it cost if we take a single client image from Indexface and search through all 500 images that are now stored in the S3 bucket to find the images that the customer appeared in and present them to them?

Which of the following is how we will be charged?

1. Since we only utilize one index face to search among the 500 stored images in the S3 bucket, will it be just one cost.

2. Is it going to be 1x500? That is, we will be charged based on the quantity of photos kept in the S3 bucket.

3. Assume the customer appears in only 10 of the 500 images stored in the S3 bucket. Will the facial detection fee be 1x10?

Answer

The document stated the following.  
In other words, I think it falls under number 2 in the options you described.  
https://aws.amazon.com/rekognition/faqs/?nc1=h_ls
> Q: How does Amazon Rekognition count the number of images processed?
> 
> For APIs that accept images as inputs, Amazon Rekognition counts the actual number of images analyzed as the number of images processed. DetectLabels,  DetectModerationLabels, DetectFaces, IndexFaces, RecognizeCelebrities, and SearchFaceByImage, and Image Properties belong to this category. For the CompareFaces API, where two images are passed as input, only the source image is counted as a unit of images processed.

Amazon Rekognition billing

Relevant content