Track and cap Amazon Bedrock spend per IAM identity with CUR 2.0 and AWS Budgets
Source Amazon AWS Machine Learning blog

At a glance
This guide explains how to see Amazon Bedrock AI costs for each IAM identity, a user or role, and block access once a set limit is passed, using only built-in AWS features. Most cases need no custom code.
Key points
Bedrock automatically records which IAM identity made each request.
Adding cost tags lets you see per-person spending in Cost Explorer or CUR 2.0.
AWS Budgets can set a limit and attach a Deny policy that blocks access when it is crossed.
How you tag depends on whether each person or app has its own role.
Why it matters
Companies need to know who spends how much on AI and set limits before expanding access, so they can control costs.
Original article
Tokenomics at scale: Track and cap Amazon Bedrock spend per IAM principal with CUR 2.0 and AWS Budgets
Amazon AWS Machine Learning blog · Nov 13, 2026, 4:29 AM GMT+9 · aws.amazon.com
Read on Amazon AWS Machine Learning blogAI read the original article and summarized it in plain language. It may contain mistakes, so please check the original for accuracy. The article's copyright belongs to Amazon AWS Machine Learning blog.