Tracking AI coding spend like Claude Code per project and client
10/03/2026 — 10/03, 18:56·1 sources·1 reports
Story overview
On October 3, 2026, DEV Community published a post titled “How to track AI coding spend like Claude Code by project and client.” The article targets a common reporting gap for teams that deliver software with Claude Code, Cursor, or raw API keys. Such teams may have a rough sense of their monthly AI spend, but they almost certainly cannot answer a more specific question: “Which project — or which client — consumed that spend?”
The author argues that this question matters whenever any of the work is billed. Hours and licenses already show up on invoices, while AI costs currently hide inside a terminal. The post therefore explains how to break down AI spending generated by Claude Code, Cursor, or direct API key usage and attribute it to specific projects and clients, so that the cost can appear on invoices alongside hours and licenses.
The article is not a general overview of AI pricing; it focuses on attribution — taking raw usage records and assigning them to a project or client. The author describes the mechanics: where the usage data actually lives, how to convert that data into per-project amounts, and how to run the supplied tool with a single command. The tool is written by the author and is presented as a one-command solution.
AI-generated from 1 reports · updated 2 hours ago
Latest turnThis post explains how to attribute AI coding spend from Claude Code, Cursor, or raw API keys to specific projects and clients, so those costs can appear on invoices alongside hours and licenses. It covers where the usage data actually lives, how to turn it into per-project dollars, and the author's one-command tool.

- Heat index
- 95
- Sources
- 1
- Reports
- 1
- First seen
- 3 hours ago
Reports on this story headlines open the original
This post explains how to attribute AI coding spend from Claude Code, Cursor, or raw API keys to specific projects and clients, so those costs can appear on invoices alongside hours and licenses. It covers where the usage data actually lives, how to turn it into per-project dollars, and the author's one-command tool.
Other stories people are talking about
- 529RisingApple tightens macOS Full Disk Access over AI agent risks8 sources
- 453NVIDIA launches 64GB DGX Spark desktop AI computer at $4,9998 sources
- 334SurgeClaude Opus 5.5 and GPT-6 Sol: comparing cost per task4 sources
- 327Meta open-sources Muse Gadgets firmware and SDK5 sources
- 219Microsoft AI releases MAI-Transcribe-2-Streaming real-time transcription model4 sources
- 192Amazon Weighs Moving $8 Billion of Nvidia Chips into a Financing Vehicle3 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion
