用 Amazon Bedrock tokenomics 数据湖集中查询多账户调用日志
Amazon Bedrock tokenomics data lake
多账户用 Bedrock 的团队值得看：AWS 手把手教你把各账户调用日志汇成一张表，prompt、token 数、逐次成本全查得到。对要做内部计费和成本归因的平台工程或 FinOps 团队很实用。
AWS 发布教程，演示如何把 Amazon Bedrock 在多个关联账户下的调用日志汇入一个集中式数据湖，生成统一可查询表。教程核心是解决多账户使用 Bedrock 时只看到总账单、看不到每次调用内部发生什么的痛点。
具体做法是聚合各账户的 Bedrock invocation logs，使团队能在同一张表里查询每次调用的 prompt 内容、token 数量、所选模型以及逐次调用成本。这样管理员可以按账户、按模型、按 prompt 维度拆解支出，定位成本异常或模型选型不合理的调用。
对在 AWS 组织内大规模部署 Bedrock 的企业来说，这套方案把成本核算从账单层面下钻到调用层面，便于做内部计费、预算管控和模型使用审计，属于面向平台/FinOps 团队的实操工作流。
Amazon Bedrock tokenomics data lake
Running Amazon Bedrock across many accounts shows you the bill but not what happened inside each call. This post builds a centralized observability data lake that aggregates Bedrock invocation logs from every linked account into one queryable table, so you can see prompts, token counts, model choice, and per-invocation cost across your organization.
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Amazon Bedrock, AWS, 数据湖, FinOps.
Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.