Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 9 Nov 2026
One change · claude-code

How Claude Code uses prompt caching changedprompt-caching

Nearest release: v2.1.321, published under an hour after 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 9 Nov 2026 18:57 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 9 Nov 2026 19:07 UTC.

Upstream edited
Recorded here
Lines+2added
Lines−2removed
From line 29 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits61to this page, all time

The whole hunk

from line 29, old and new numbered
/
lines
from line 29
2929Two settings don't appear in the layer table but still affect what stays cached:
3030 
3131* **Model**: each model has its own cache. Switching models recomputes the entire request even when the content is identical. See [Switching models](#switching-models) below.
32* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. On Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 with an API key or a Claude subscription, the cache stays intact by default. See [Changing effort level](#changing-effort-level) below.
32* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. With an API key or a Claude subscription, the cache stays intact by default on Fable 5.1 and later, Opus 5.5, Sonnet 5.5, and Haiku 5.5. See [Changing effort level](#changing-effort-level) below.
3333 
3434> [!TIP]
3535>
from line 90
9090 
9191On most models, changing the [effort level](https://code.claude.com/docs/en/model-config.md#adjust-effort-level) mid-session means the next request reads the entire conversation history with no cache hits. While the cache is still warm, Claude Code asks you to confirm the change first.
9292 
93On Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 with an API key or a Claude subscription, you keep the cache when you change effort. Claude Code [applies the new level](https://code.claude.com/docs/en/model-config.md#when-a-new-effort-level-starts) without asking. On Amazon Bedrock, Google Cloud's Agent Platform, or a [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway), or when you set [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`](https://code.claude.com/docs/en/llm-gateway-protocol#disable-pre-release-capabilities) or your organization has a HIPAA configuration, it works as on most models.
93With an API key or a Claude subscription, changing effort keeps the cache on Fable 5.1 and later, Opus 5.5, Sonnet 5.5, and Haiku 5.5. Claude Code [applies the new level](https://code.claude.com/docs/en/model-config.md#when-a-new-effort-level-starts) without asking. On Amazon Bedrock, Google Cloud's Agent Platform, or a [Claude apps gateway](https://code.claude.com/docs/en/claude-apps-gateway), or when you set [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`](https://code.claude.com/docs/en/llm-gateway-protocol#disable-pre-release-capabilities) or your organization has a HIPAA configuration, it works as on most models.
9494 
9595Before v2.1.260, changing effort on Fable 5.1 with an API key or a Claude subscription also invalidated the cache.
9696 
Feedback