I decide the prompt cache TTL by where I come back to, not how long I was away
Claude Code v2.1.242 added promptCacheTtl and subagentPromptCacheTtl. Whether the one-hour cache pays off depends on returning to the same directory and the same git state, not on how long the break was. Here is the order I check things in.
When Prompt Caching Was On but the Bill Didn't Move — Field Notes on Instrumenting cache_read to Close the Hit-Rate Gap
You added cache_control but your Claude API bill barely changed. Before guessing at fixes, record cache_read and cache_creation on every request and split the hit-rate gap into three causes: non-deterministic prefixes, TTL expiry, and sub-threshold blocks.
Your Cache Hit Rate Resets to Zero the Morning You Switch Models — Prompt Cache Rewarm Design for the Opus 4.8 to Sonnet 5 Cutover
Prompt caches are scoped per model, so day one of a model migration starts at a 0% hit rate. Why percentage-based rollouts break cache economics twice over, and how cohort cutover by task family preserves them — with working measurement code.
When Context Editing Made My Agent Re-run the Same Search — Field Notes on Clear Boundaries and Cache Invalidation
After turning on Context Editing to auto-clear tool results, the agent forgot what it had just read, re-ran the same tool, and the cache rebuilt every turn so costs went up. Field notes on instrumenting the silent regression and setting trigger, keep, and clear_at_least from measured data.
I Edited One Line of a Tool Description and the Whole Prompt Cache Rebuilt — Where to Place cache_control Breakpoints
Hit rate suddenly flatlined at zero because a volatile block sat upstream of stable ones. This walks through how prefix-cache cascade invalidation works, how to reorder blocks from stable to volatile, and where to spend your four cache_control breakpoints — with code and decision tables.
My Morning Batch Was Missing the Prompt Cache Every Time — Warming Cadence and the Break-Even Math for the 1-Hour TTL
Jobs that run a few hours apart cold-miss the prompt cache even with a 1-hour TTL. Here is how to back out the right warming interval from the TTL, and how to write the break-even formula that decides whether warming pays off — with numbers from a four-site daily generation pipeline.
When Claude API Prompt Caching Quietly Stops Hitting in Production — Field Notes on TTL and Measured Savings
Prompt caching works beautifully the day you ship it, then quietly stops hitting in production. The five things that break the prefix, how to choose between 5-minute and 1-hour TTL, and how to measure real savings from usage instead of guessing.
Stop Terminology Drift in Localized Apps: A Consistent Localizable.strings Pipeline with the Batch API and a Cached Glossary
Translating UI strings one at a time invites inconsistency. Pair Claude's Message Batches API with a prompt-cached glossary to translate Localizable.strings across 10+ languages consistently, with measured costs and the pitfalls I hit in production.
When a Long-Running Agent's Context Quietly Decays — Budgeting and Compaction
An agent that runs all night gets sloppier by morning. The cause is dilution from accumulated context. Here is how to treat context as a budget, measure its decay, and keep it healthy with compaction — with working code and field notes.
Splitting Claude API prompt cache into 5m and 1h tiers — separate TTLs cut cost and stabilize ops
Anthropic's cache_control supports two TTLs: 5 minutes and 1 hour. Splitting them into a two-tier layout — 1h for static system/tools, 5m for variable few-shot — meaningfully changed both my costs and my on-call life. Here's the design with the numbers I observed.
Diagnosing Claude API Prompt Cache Misses — How to Read the usage Field
If your Claude API prompt cache isn't reducing your bill, the usage field is where to start. This guide walks through the five most common reasons cache_read_input_tokens stays at zero and how to fix each one.
How I Cut My Claude API Bill in Half With Prompt Caching
Done right, Anthropic's prompt caching can roughly halve your monthly API spend on workloads with long, repeated system prompts. Here is the design playbook I use after six months of running it in production.