<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Cost Allocation on The road</title><link>https://kane.mx/tags/cost-allocation/</link><description>Recent content in Cost Allocation on The road</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Wed, 29 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kane.mx/tags/cost-allocation/index.xml" rel="self" type="application/rss+xml"/><item><title>Track Claude Code Cost Per Project with Bedrock Tagging</title><link>https://kane.mx/posts/2026/claude-code-cost-per-project/</link><pubDate>Wed, 29 Apr 2026 00:00:00 +0000</pubDate><guid>https://kane.mx/posts/2026/claude-code-cost-per-project/</guid><description>
&lt;p>If you run &lt;code>claude&lt;/code> against Amazon Bedrock across a dozen repos, your bill arrives as one opaque number. Until recently, the workaround was clunky — create an application inference profile per project, swap them by hand, hope you remembered which one was active. In April 2026, AWS &lt;a href="https://aws.amazon.com/blogs/machine-learning/introducing-granular-cost-attribution-for-amazon-bedrock/">shipped native per-principal cost attribution for Bedrock&lt;/a>: every &lt;code>InvokeModel&lt;/code> call now carries the caller's IAM principal and session tags straight into Cost Explorer and CUR 2.0. That is enough to turn a ~60-line shell recipe into a per-repo billing system.&lt;/p>
&lt;p>&lt;a href="https://kane.mx/posts/2026/claude-code-cost-per-project/">Read More&lt;/a>&lt;/p></description></item></channel></rss>