Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · claude-code

How Claude Code uses prompt caching changed

prompt-caching

Nearest release: v2.1.280, published 7 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 22 Sep 2026 23:19 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 22 Sep 2026 23:37 UTC.

Upstream edited
Recorded here
Lines+6added
Lines−6removed
From line 31 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits32to this page, all time

The whole hunk

from line 31, old and new numbered
/
lines
from line 31
3131Two settings don't appear in the layer table but still affect what stays cached:
3232 
3333* **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.
34* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. On 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.
34* **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 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.
3535 
3636<Tip>
3737 Pick your model and effort level at the top of a session, then save `/compact` for natural breaks between tasks. The fewer changes you make mid-task, the higher your cache hit rate.
from line 92
9292 
9393On most models, changing the [effort level](/docs/en/model-config#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.
9494 
95On Fable 5.1 with an API key or a Claude subscription, changing effort keeps the cache, and Claude Code applies the new level without asking. This doesn't apply on Amazon Bedrock, Google Cloud's Agent Platform, or a [Claude apps gateway](/docs/en/claude-apps-gateway), or when you set [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`](/docs/en/llm-gateway-protocol#disable-pre-release-capabilities) or your organization has a HIPAA configuration.
95On Opus 5.5 and Fable 5.1 with an API key or a Claude subscription, changing effort keeps the cache, and Claude Code applies the new level without asking. This doesn't apply on Amazon Bedrock, Google Cloud's Agent Platform, or a [Claude apps gateway](/docs/en/claude-apps-gateway), or when you set [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`](/docs/en/llm-gateway-protocol#disable-pre-release-capabilities) or your organization has a HIPAA configuration.
9696 
9797Before v2.1.260, changing effort on Fable 5.1 with an API key or a Claude subscription also invalidated the cache.
9898 
from line 300
300300 
301301Cache performance shows up as two token counts the API reports on every response. The most direct way to watch them live is a [statusline script](/docs/en/statusline) that reads the `current_usage` object:
302302 
303| Field | Meaning |
304| ----------------------------- | --------------------------------------------------------------------------------------- |
305| `cache_creation_input_tokens` | Tokens written to the cache on this turn, billed at the cache write rate |
306| `cache_read_input_tokens` | Tokens served from cache on this turn, billed at roughly 10% of the standard input rate |
303| Field | Meaning |
304| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
305| `cache_creation_input_tokens` | Tokens written to the cache on this turn, billed at the cache write rate |
306| `cache_read_input_tokens` | Tokens served from cache on this turn, billed at the model's [cached token rate](https://platform.claude.com/docs/en/about-claude/pricing), below the standard input rate |
307307 
308308A high read-to-creation ratio means caching is working well. If creation stays high turn after turn, something is changing in your prefix. The [actions that invalidate the cache](#actions-that-invalidate-the-cache) section lists the usual causes.
309309 
Feedback