Request 2 caches its request content (not the response) changedbuild-with-claude/prompt-caching
Nearest release: v2.1.321, published under an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+8added
Lines−4removed
From line
7
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits41to this page, all time
The whole hunk
from line 7, old and new numbered
/
from line 7
77 eligibility: eligible
88 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Your prompts and Claude's outputs are not stored. KV cache representations and cryptographic hashes are held in memory for the cache TTL and promptly deleted after expiry.
99 supportedModels:
10 - claude-fable-5-2
11 - claude-mythos-5-2
1012 - claude-fable-5-1
1113 - claude-mythos-5-1
1214 - claude-fable-5
from line 260
258260
259261| Model | Base input tokens | 5m cache writes | 1h cache writes | Cache hits and refreshes | Output tokens |
260262| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------- | :-------------- | :-------------- | :----------------------- | :------------ |
263| Claude Fable 5.2 | $8 / MTok | $10 / MTok | $16 / MTok | $0.20 / MTok<sup>1</sup> | $40 / MTok |
264| Claude Mythos 5.2 ([limited availability](https://support.claude.com/en/articles/14604842)) | $8 / MTok | $10 / MTok | $16 / MTok | $0.20 / MTok<sup>1</sup> | $40 / MTok |
261265| Claude Fable 5.1 | $10 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok<sup>1</sup> | $50 / MTok |
262266| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $10 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok<sup>1</sup> | $50 / MTok |
263267| Claude Fable 5 | $10 / MTok | $12.50 / MTok | $20 / MTok | $1 / MTok | $50 / MTok |
from line 283
279283| Claude Haiku 5.5 (for prompts over 100,000 tokens) | $0.50 / MTok | $0.625 / MTok | $1 / MTok | $0.05 / MTok | $2.50 / MTok |
280284| Claude Haiku 4.5 | $1 / MTok | $1.25 / MTok | $2 / MTok | $0.10 / MTok | $5 / MTok |
281285
282*<sup>1 Cache hits and refreshes on Claude Fable 5.1 and Claude Mythos 5.1 are priced at 0.025x the base input price.</sup>*
286*<sup>1 Cache hits and refreshes on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1 are priced at 0.025x the base input price.</sup>*
283287
284288*<sup>2 Cache hits and refreshes on Claude Opus 5.5 and Claude Sonnet 5.5 are priced at 0.05x the base input price.</sup>*
285289
from line 622
618622
619623On the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), the minimum cacheable prompt length is:
620624
621* 512 tokens for Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), and Claude Haiku 5.5
625* 512 tokens for Claude Fable 5.2, [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), and Claude Haiku 5.5
622626* 2,048 tokens for [Claude Mythos Preview](https://anthropic.com/glasswing) and Claude Opus 4.7
623627* 4,096 tokens for Claude Opus 4.6 and Claude Opus 4.5
624628* 1,024 tokens for Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Opus 4.1 ([retired, except on Claude Models on Google Cloud (Google managed) and Bedrock](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Sonnet 4 ([retired, except on Claude Models on Google Cloud (Google managed) and Bedrock](https://platform.claude.com/docs/en/about-claude/model-deprecations))
from line 685
681685| **Thinking parameters** | Model-specific | Model-specific | ✘ | The thinking configuration (mode, and `budget_tokens` in extended mode) is rendered into the prompt, so changing it always invalidates message blocks; tool and system caches are also invalidated on models that render the configuration ahead of them. See [Thinking and prompt caching](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-prompt-caching). |
682686| **Effort setting** | Model-specific | Model-specific | ✘ | Changing the [`output_config.effort`](https://platform.claude.com/docs/en/build-with-claude/effort) value always invalidates message blocks, with the same model-specific effect on tool and system caches as thinking parameters. Setting effort explicitly to the model’s default is equivalent to omitting it and does not invalidate. On models that support [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta), an effort change carried in a `role: "system"` message inside `messages` leaves the cached prefix intact. |
683687| **Non-tool results passed to requests with thinking** | ✓ | ✓ | Model-specific | On Opus 4.5+, Sonnet 4.6+, and Haiku 5.5, thinking blocks are preserved by default, so the cache remains valid (✓). On earlier Opus/Sonnet models and Haiku models through Claude Haiku 4.5, all previously-cached thinking blocks are stripped from context, and any messages that follow those thinking blocks are removed from the cache (✘). For more details, see [Caching with thinking blocks](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#caching-with-thinking-blocks). |
684| **Dropped thinking blocks** | ✓ | ✓ | ✘ | When the API drops a Claude 5.1 or later model’s thinking block that isn’t [preserved](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking) on that request, the cached prefix changes from that block’s position onward on that request. Blocks the receiving model can read, passed back unchanged, keep the cache intact. |
688| **Dropped thinking blocks** | ✓ | ✓ | ✘ | When the API drops a thinking block that isn’t [preserved](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking) on that request, the cached prefix changes from that block’s position onward on that request. Blocks the receiving model can read, passed back unchanged, keep the cache intact. |
685689
686690On models that support [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes), the `inline-tools-2026-09-15` beta header lets you add a tool, or change a tool’s definition, partway through a conversation without editing `tools`. Send the definition in a `tool_addition` block in a mid-conversation system message and leave `tools` exactly as you first sent it. The cached prefix still matches, so only the appended message is processed as new input. The one exception is a `tools` array with no non-deferred tool, where the first tool defined this way costs one full cache miss on that request. See [Define tools in a message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta).
687691
688692<Note>
689 On Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Opus 5.5, Claude Opus 4.8, Claude Opus 5, Claude Sonnet 5.5, and Claude Haiku 5.5, you can add a new system instruction partway through a conversation without invalidating the system or message caches. Append a `{"role": "system"}` message to `messages` instead of editing the top-level `system` field, so the cached prefix stays unchanged. This feature is not available on Claude Sonnet 5. Use the top-level `system` field instead. See [Mid-conversation system messages and tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
693 On Claude Fable 5.2, [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Opus 5.5, Claude Opus 4.8, Claude Opus 5, Claude Sonnet 5.5, and Claude Haiku 5.5, you can add a new system instruction partway through a conversation without invalidating the system or message caches. Append a `{"role": "system"}` message to `messages` instead of editing the top-level `system` field, so the cached prefix stays unchanged. This feature is not available on Claude Sonnet 5. Use the top-level `system` field instead. See [Mid-conversation system messages and tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
690694</Note>
691695
692696### Tracking cache performance
No line in this hunk matches that.