LLM cost, attributed.
Guides on LLM cost attribution, per-agent cost tracking, and keeping agentic AI spend under control.
30 June 2026 · 8 min read
How to detect anomalies in LLM API usage (spend spikes, error storms, and rogue agents)
Four things break quietly in LLM usage: a spend spike, an error storm, a new model someone shipped, and a new agent that started calling. Here's how to detect each — per agent, not just per project — and get alerted before the bill arrives.
Read more →3 June 2026 · 7 min read
What is LLM cost attribution (and why your provider bill can't do it)
LLM cost attribution ties each API call's cost back to the agent, run, and feature that caused it. Here's what it is, why provider invoices can't tell you, and how to add it without a proxy.
Read more →3 June 2026 · 9 min read
How to track LLM API costs per agent in Node.js
A practical guide to attributing OpenAI and Anthropic spend to the agent and run that made each call in Node.js — with a drop-in SDK, no proxy, and a hard budget cap before the call.
Read more →