Analytics & AI
Amazon Bedrock
- Timebilled
- Bytesnot billed
- Callsbilled
In one line
On-demand meters input and output tokens. Provisioned Throughput rents model units by the hour.
What gets missed
Provisioned Throughput bills per model unit per hour with zero invocations, with or without a 1- or 6-month commitment. Cache-read and cache-write tokens meter separately; batch runs at a discount.
Find it on your bill
Filter Cost Explorer or your Cost and Usage Report by these usage types. A usage type with no region prefix means us-east-1.
input-tokensoutput-tokenscache-read-input-token-countProvisionedThroughput-1month-ModelUnits
Bills the same way
These services turn exactly the same meters, so what you learn here transfers.