AWS marketplace documentation change
Summary
Updated ML pricing documentation to clarify that asynchronous inference endpoints also use hourly pricing and fixed grammar in billing description
Security assessment
This change clarifies pricing models for different ML product types and fixes a minor grammatical error. There's no mention of security vulnerabilities, incidents, or security features. The change is purely about billing and pricing documentation.
Diff
diff --git a/marketplace/latest/userguide/machine-learning-pricing.md b/marketplace/latest/userguide/machine-learning-pricing.md index 8d1982871..172ee1387 100644 --- a//marketplace/latest/userguide/machine-learning-pricing.md +++ b//marketplace/latest/userguide/machine-learning-pricing.md @@ -61 +61,12 @@ When the buyer runs your software by hosting an endpoint to continuously perform -Batch transform processes always use hourly pricing. Training jobs for algorithm products also always use hourly pricing. You can set these prices independently of the inference pricing, and of each other. +The following ML product types always use hourly pricing: + + * Batch transform jobs + + * Asynchronous inference endpoints + + * Training jobs for algorithm products + + + + +You set the price for each type independently of the inference pricing and of each other. @@ -70 +81 @@ By default, with inference pricing, AWS Marketplace charges your buyer for each -For inference pricing, AWS Marketplace only charges buyer for requests where the HTTP response code is `2XX`. +For inference pricing, AWS Marketplace only charges the buyer for requests where the HTTP response code is `2XX`.