Tokenomics at scale: Track and cap Amazon Bedrock spend per IAM principal with CUR 2.0 and AWS Budgets
Machine Learning Blog
This article explains how to achieve per-identity Amazon Bedrock cost visibility and enforce spending limits using AWS-native services without custom application code.
- Amazon Bedrock automatically captures IAM principal identity for every inference request
- Activate cost allocation tags on IAM principals to enable per-user or per-team cost tracking
- Use Cost Explorer for console-based reporting or CUR 2.0 with Amazon Athena for detailed SQL analysis
- Create AWS Budgets with budget actions to automatically deny access to expensive models when thresholds are crossed
- Support both static principal tags and dynamic session tags for flexible identity attribution
- Budget data refreshes up to three times daily, so spend may overshoot thresholds before enforcement
Organizations can now answer critical tokenomics questions—what we spend per person, can we cap it, and how much effort is required—using only native AWS services.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Oct 30
2026
2026
Managing Amazon Bedrock costs end to end: A playbook for FinOps and platform teams
Nov 10
2026
2026
Amazon Bedrock tokenomics data lake
Aug 11
2026
2026
Amazon Bedrock expands IAM principal cost allocation to the bedrock-mantle endpoint
Sep 1
2026
2026
Tokenomics at scale: How Jamf built real-time spend enforcement for Amazon Bedrock
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.