news

Anthropic quietly nerfed Claude Code's 1-hour cache, and your token budget is paying the price - XDA

Claude Code users reported burning through usage quotas faster after Anthropic shortened the tool’s effective cache window, reducing how much prior context could be reused without re-paying input tokens.

Published 2026-04-20Source: XDA
Generated Tokenmaxxing editorial thumbnail for Anthropic quietly nerfed Claude Code's 1-hour cache, and your token budget is paying the price - XDA

Why it matters

Caching policy changes can swing the effective cost of agentic coding dramatically. If your workflow depends on long-running projects and repeated context reuse, a cache-window reduction can turn ‘steady’ spend into surprise overages overnight.

Tokenmaxxing read

Tokenmaxxing isn’t just verbosity—it’s cache economics. Track cache hit rates and billed input tokens, budget for cache misses, and design flows to avoid replaying long context (summaries, state files, retrieval, smaller diffs).

Source takeaway

The article points to Claude Code JSONL logs (`~/.claude/projects/`) with cache fields like `ephemeral_5m_input_tokens` vs `ephemeral_1h_input_tokens`, plus a mid-April Anthropic comment on a Claude Code GitHub issue about the shorter cache.

Topic links

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.

33.6K5.7KMIT
agentsstateworkflows
#15In spirit
Agents

Zep

getzep/zep

A memory layer and integration collection for AI agents and knowledge-graph-backed language-model applications.

4.6K632Apache-2.0
memoryagentsknowledge-graph
#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.

21.8K1.9KMIT
prompt-evalscirag
Related feed

More source-linked context

Generated Tokenmaxxing editorial thumbnail for Introducing Claude Opus 4.8 - Anthropic
newsA
news

Introducing Claude Opus 4.8 - Anthropic

Our latest model, Claude Opus 4.8, is an upgrade to our Opus class of models, with stronger performance across coding, agentic tasks, and professional work, and the consistency to handle long-running work.

tokenmaxxingcoding-agentsagents
Read note
CFO.com source artwork
newsC
news

Claude pricing raises new budgeting questions for CFOs

CFO.com explains how Claude’s consumption-style pricing is pushing finance teams to budget for AI like a variable utility bill, not a flat SaaS seat.

tokenmaxxingcoding-agentsagents
Read note
Yahoo Finance source artwork
newsYF
news

AI Cost Crisis Emerges as Claude Usage and Agentic Coding Bills Spiral

Yahoo Finance flags an emerging AI cost crunch: agentic coding and heavy Claude usage can spike bills fast, forcing leaders to rethink budgeting and ROI.

tokenmaxxingcoding-agentsagents
Read note