# Amazon explains how to build a Bedrock invocation observability data lake

> Original title: Amazon Bedrock tokenomics data lake

- Source: AWS Machine Learning Blog
- Published: 2026-11-10T16:56:36.000Z
- Bad Influence: https://badinfluence.news/items/ow5ncd6e67cn2k7ljb9a8fp8v
- Original: https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-tokenomics-data-lake/

## Summary

Amazon's AWS Machine Learning Blog explains how to deploy a centralized observability data lake for Amazon Bedrock model invocations across multiple accounts. The lake pulls invocation logs from linked accounts into Amazon CloudWatch, forwards them to a central account, converts them through Amazon Data Firehose, and exposes them in Amazon Athena. The deployment uses two AWS CloudFormation templates, with code and SQL queries in an AWS sample GitHub repository.