How Claude Code uses prompt caching changedprompt-caching
Nearest release: v2.1.302, published 8 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 17 Oct 2026 01:14 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 17 Oct 2026 01:37 UTC.
Upstream edited
Recorded here
Lines+1added
Lines−3removed
From line
171
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits52to this page, all time
The whole hunk
from line 171, old and new numbered
/
from line 171
171171
172172To produce the summary, Claude Code sends a separate request with the same system prompt, tools, and history as your conversation, plus a summarization instruction appended as a final user message. While the cache is warm, that request reads your prefix from the cache, so a mid-session `/compact` costs a fraction of what the context size suggests and spends most of its time generating the summary.
173173
174After a break longer than the [cache lifetime](#cache-lifetime), there is no cache left to read, so the summarization request reprocesses the full history as uncached input. This is why `/compact` costs the most when you [resume an old session](/docs/en/sessions#resume-from-a-summary). In both the warm and cold cases, the turn after compaction rebuilds the conversation cache for only the much shorter summary, so that turn is not the slow part.
174After a break longer than the [cache lifetime](#cache-lifetime), there is no cache left to read, so the summarization request reprocesses the full history as uncached input. This is why `/compact` costs the most when you [resume an old session](/docs/en/sessions#resume-a-session). In both the warm and cold cases, the turn after compaction rebuilds the conversation cache for only the much shorter summary, so that turn is not the slow part.
175175
176176<Tip>
177177 Compaction works in your favor when the context you discard is content you no longer need. To choose when its overhead happens, run `/compact` at a natural break in your work, such as between tasks, instead of waiting for auto-compaction to trigger mid-task. If you've gone down a path you want to abandon entirely, [`/rewind`](#rewinding-the-conversation) to an earlier turn instead. Rewinding truncates back to a prefix that is already cached, rather than building a new one as compaction does.
from line 251
251251## Cache lifetime
252252
253253Cached prefixes expire after a period of inactivity. Each request that hits the cache resets the timer, so the cache stays warm as long as you keep working. After a long enough gap, the next request recomputes the full input and re-establishes the cache, which is why the first turn back after stepping away can be noticeably slower.
254
255On a Pro or Max plan, when you resume a large session after a long break, Claude Code [offers to resume from a summary](/docs/en/sessions#resume-from-a-summary) so later requests don't carry the full history.
256254
257255The time to live (TTL) controls how long a gap the cache survives. The API offers two: a five-minute TTL, and a [one-hour TTL](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#1-hour-cache-duration) that keeps the cache warm through longer breaks but [charges a higher rate for cache writes](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing). The longer TTL helps when you leave a session idle and come back to it, because you skip the reprocessing an expired prefix costs. It costs more on short bursts of work that never idle past five minutes, where the higher write rate applies and the longer cache lifetime goes unused.
258256
No line in this hunk matches that.