Question

A media company runs a single Bedrock generative AI application on Anthropic Claude that serves three internal business units (News, Sports, Entertainment). Finance requires monthly cost breakdowns per business unit so each team can be charged back accurately. The application already uses on-demand invocation and the team wants a solution that provides granular per-business-unit spend visibility in AWS Cost Explorer with minimal code changes. Which approach best meets this requirement?

Accepted Answer

Create separate application inference profiles for each business unit, apply cost allocation tags to each profile, and route each business unit's invocations through its corresponding profile.

Answer

Enable model invocation logging to CloudWatch and parse the logs with a Lambda function to sum input and output token counts per business unit each month.

Answer

Purchase separate provisioned throughput commitments for each business unit and use the commitment ARNs to attribute cost in Cost Explorer.

Answer

Add a custom 'businessUnit' field to every InvokeModel request body and enable CloudTrail data events to aggregate spend by that field.