Cost attribution and controls for AI developer and productivity tools on Amazon Bedrock
Machine Learning Blog
This article explains how to implement per-user cost attribution and controls for AI developer and productivity tools using Amazon Bedrock's IAM principal tracking capabilities.
- Bedrock automatically captures IAM identity of every inference call with no API changes required
- Configure AWS IAM Identity Center with external identity provider for federated per-user attribution
- Session tags (team, cost center) flow into AWS Cost and Usage Reports (CUR 2.0) for organizational cost allocation
- Query per-user costs using Amazon Athena and visualize with Cost Explorer or QuickSight dashboards
- Implement usage controls via AWS Budgets, CloudWatch alarms, DynamoDB quota tracking, or LLM gateway proxies
- Works identically across Claude Desktop, Claude Code, Codex, ChatGPT Work, and other tools routing through Bedrock
Organizations can adopt cost attribution incrementally, starting with Identity Center integration and progressing to real-time usage enforcement based on their governance requirements.
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.
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.