AWS shows how to track and cap Amazon Bedrock spend per IAM principal using only CUR 2.0 and AWS Budgets, with no code for the common case
Attributing AI spend per person or team and capping it is the first thing finance asks before access expands. How to do attribute, report and enforce with native features.
// Key points
- Bedrock records the IAM user or role for every inference request automatically, with no change to your calls.
- With one role per person, use principal tags on the role; for shared roles or a gateway, pass session tags at AssumeRole to tell users apart.
- Activate the tags as cost allocation tags, then view spend by identity in Cost Explorer or a CUR 2.0 export.
- Create an AWS Budget for Bedrock filtered to one identity or tag, with a budget action that attaches a Deny policy when the threshold is crossed.
Builder's takeThis pairs with the Codex item above: before opening coding tools to more people, see each person's spend and cap it. We would do the same for internal model access, with a session tag per person and the budget action set to alert plus manual approval at first, switching to automatic deny once it is stable so running tasks aren't cut off at month end.