news

Analyzing Claude Code usage with CloudWatch and OpenTelemetry | Amazon Web Services

AWS engineers detail how to export Claude Code OpenTelemetry metrics into CloudWatch via bearer-token API keys, tracking claude_code.token.usage and cost.usage per developer — under $15/month for a 200-person org.

Published 2026-06-17Source: Amazon Web Services
Amazon Web Services source artwork

Why it matters

Most teams fly blind on coding-agent spend. This wires per-developer token and cost metrics into CloudWatch with no collector to run, so finance can see who burns tokens and where via attributes like user.id, team.id, and cost_center.

Tokenmaxxing read

Tokenmaxxing dies in the dark — you cannot cut spend you cannot see. At under $15/month to meter 200 engineers, observability is the cheapest lever before routing or caching. Slice claude_code.cost.usage by department to find the heavy seats, then ration.

Source takeaway

AWS's own walkthrough by Rodrigue Koffi, Gianluca Cacace, and Vadim Omeltchenko — recent (June 17). It assumes Bedrock-backed Claude Code; adapt metric names for other providers, and note CloudWatch retains these metrics for 15 months.

Topic links

tokenmaxxingcoding-agentstopicagentstopicscoreboards
Related projects

Tools that match this angle

#4In spirit
Agents

LangGraph

langchain-ai/langgraph

A framework for building resilient stateful agents with explicit graphs, persistence, human-in-the-loop flows, and controllable execution.

36K6KMIT
agentsstateworkflows
#5Direct
Evaluation

promptfoo

promptfoo/promptfoo

A CLI and CI workflow for testing prompts, agents, and RAG systems across models, with evals and red-team style checks.

22.7K2KMIT
prompt-evalscirag
#6In spirit
Evaluation

DSPy

stanfordnlp/dspy

A framework for programming and optimizing language-model pipelines rather than hand-tuning one prompt at a time.

35.6K3KMIT
optimizationprogrammingevals
Related feed

More source-linked context

Ars Technica source artwork
newsAT
news

Anthropic "pauses" token-based billing for its Claude Agent SDK

Anthropic paused its plan to move Claude Agent SDK power users onto metered API pricing, updating its billing page to put the rollout on hold while it reworks how heavy agent usage is charged on subscription plans.

tokenmaxxingcoding-agentsagents
Read note
WIRED source artwork
newsW
news

‘Pretty Crazy’ Token Usage Is Testing Bosses’ Bet on AI

WIRED maps the new 'tokenomics' scramble: across earnings calls and C-suites, companies from 8x8 to Cisco are tallying soaring AI token bills, some celebrating savings, others slapping on usage caps.

tokenmaxxingcoding-agentsagents
Read note
Generated Tokenmaxxing editorial thumbnail for Claude Fable 5 and Claude Mythos 5 - Anthropic
newsA
news

Claude Fable 5 and Claude Mythos 5 - Anthropic

Anthropic shipped Claude Fable 5 (GA, with classifier safeguards) and Claude Mythos 5 (safeguards lifted, vetted partners only) on June 9 — $10 per million input tokens, $50 per million output, under half the Mythos Preview price.

agentscoding-agentspricing
Read note