441 pages for caching.

search-results Claude Developer Platform · in the page build-with-claude/search-results …true }, "cache_control": { "type": "ephemeral" } } ``` See [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for minimum cacheable lengths and other requirement… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide …v", version: "latest" }] } ``` </CodeGroup> ### Prompt caching considerations If you use [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), changin… structured-outputs Claude Developer Platform · in the page build-with-claude/structured-outputs …/CodeGroup> ## Important considerations ### Grammar compilation and caching Structured outputs use constrained sampling with compiled grammar artifacts. This introduces some performance characteris… task-budgets Claude Developer Platform · in the page build-with-claude/task-budgets …a new `task_budget` in `output_config` on the next request. Keep the caching consequence in mind: the budget value participates in the rendered prompt, so a changed value does not match cache entries… thinking Claude Developer Platform · in the page build-with-claude/thinking …utput, steer thinking depth with effort, and use thinking with tools, caching, and streaming." --- <Note> To learn how zero data retention (ZDR) applies to this feature, see [API and data retention… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …s how Claude determines when to think, how to steer thinking, and the caching, cost, and pricing mechanics that follow from it. ## How Claude determines when to think Thinking is optional for the mo… thinking-tool-workflows Claude Developer Platform · in the page build-with-claude/thinking-tool-workflows …ing on, read thinking output, and review the full rules for tool use, caching, and streaming. </Card> <Card title="Steering thinking" icon="compass" href="https://platform.claude.com/docs/en/buil… thinking-troubleshooting Claude Developer Platform · in the page build-with-claude/thinking-troubleshooting …lent to omitting it and does not invalidate. See [Thinking and prompt caching](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-prompt-caching). ## Setting effort does not… token-counting Claude Developer Platform · in the page build-with-claude/token-counting …<AccordionGroup> <Accordion title="Does token counting use prompt caching?"> No, token counting provides an estimate without using caching logic. Although you may provide `cache_control` block… working-with-messages Claude Developer Platform · in the page build-with-claude/working-with-messages …ges) for the complete guide, including how to combine it with [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching). ## Prefilling Claude's response You can prefill… apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …n Apple's protocol are not available through it, including: * Prompt caching controls (the package applies prompt caching automatically; cache TTL and breakpoint placement are not configurable) * Sto… openai-sdk Claude Developer Platform · in the page cli-sdks-libraries/libraries/openai-sdk …/platform.claude.com/docs/en/build-with-claude/thinking), and [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching)), use the native [Claude API](https://platform.clau… home Claude Developer Platform · in the page home …g" href="https://platform.claude.com/docs/en/build-with-claude/prompt-caching"> Prompt caching </HomeJourneyLink> <HomeJourneyLink icon="wifi-high" href="https://platf… access-transparency-log Claude Developer Platform · in the page manage-claude/access-transparency-log …| ### Caching Responses are cacheable only by the requesting client. `Cache-Control` always includes `private`, and responses carry `Va… api-and-data-retention Claude Developer Platform · in the page manage-claude/api-and-data-retention …| | [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) | `/v1/messages… data-residency Claude Developer Platform · in the page manage-claude/data-residency …ed TPM, consistent with how other pricing multipliers (such as prompt caching) affect burndown rates. </Note> ## Batch API support The `inference_geo` parameter is supported on the [Batch API](https… First request Claude Developer Platform · in the page manage-claude/usage-cost-api …en/api/rate-limits) optimization:** Optimize features such as [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) or specific prompts to use your allocated capacity… okta Claude Developer Platform · in the page manage-claude/wif-providers/okta …our Okta fetcher should return a fresh token on each call rather than caching one indefinitely. The `ant` CLI re-reads `ANTHROPIC_IDENTITY_TOKEN_FILE` on each exchange, so refresh that file on a timer… wif-reference Claude Developer Platform · in the page manage-claude/wif-reference …if the issuer recently rotated its signing key, see [Key rotation and caching](https://platform.claude.com/docs/en/manage-claude/wif-reference#key-rotation-and-caching). | | 401 | `authentication_e… workspaces Claude Developer Platform · in the page manage-claude/workspaces …caches](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) are also isolated by workspace on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …(csharp, go: `Advisor`) setting has no `max_uses`, `max_tokens`, or `caching` fields, and advice arrives through thread events rather than `advisor_tool_result` blocks. ### How consultations work E… overview Claude Developer Platform · in the page managed-agents/overview …the web, and run code securely. The harness supports built-in prompt caching, compaction, and other performance optimizations for high-quality, efficient agent outputs. To build your own agent loop w… Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: Claude Developer Platform · in the page models/fable-5-1/migration-guide …t cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) hits: <CodeGroup> ```bash cURL curl -sS https://api.anthropic.com/v1/messages \ -H "content-type: ap… overview Claude Developer Platform · in the page models/fable-5-1/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… whats-new-fable-5-1 Claude Developer Platform · in the page models/fable-5-1/whats-new-fable-5-1 …t cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) warm. To find out whether your integration edits history, run a session with `prefix_mismatch_behavior: "drop_block"` and… overview Claude Developer Platform · in the page models/fable-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/haiku-4-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/haiku-5-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… whats-new-haiku-5-5 Claude Developer Platform · in the page models/haiku-5-5/whats-new-haiku-5-5 …cached](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations) | Chang… overview Claude Developer Platform · in the page models/mythos-5-1/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/mythos-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/opus-4-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/opus-4-6/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/opus-4-7/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/opus-4-8/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …summarized"` to receive readable summaries. * Review prompts near the caching minimum: prompts of 512 tokens or more can create cache entries. * If your organization has a [Priority Tier](https://plat… overview Claude Developer Platform · in the page models/opus-5-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …/platform.claude.com/docs/en/build-with-claude/task-budgets), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch p… overview Claude Developer Platform · in the page models/opus-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… Models overview Claude Developer Platform · in the page models/overview …/pricing"> Complete pricing, including batch discounts and prompt caching rates. </Card> <Card title="Model deprecations" icon="clock" href="https://platform.claude.com/docs/en/about-claude/m… overview Claude Developer Platform · in the page models/sonnet-4-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page models/sonnet-4-6/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …safeguards-on-claude-opus-and-sonnet). ### Other changes * **Prompt caching:** The minimum cacheable prompt is 512 tokens, down from 1,024 on Claude Sonnet 5, Claude Sonnet 4.6, and Claude Sonnet 4.… overview Claude Developer Platform · in the page models/sonnet-5-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …sation-system-messages#mid-conversation-tool-changes) (beta), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch p… overview Claude Developer Platform · in the page models/sonnet-5/overview …base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude S… overview Claude Developer Platform · in the page release-notes/overview …of 0.1x. Cache writes and all other prices are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching). * We've launched **Claude Haiku 5.5** (… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …ge-and-billing) in the Claude API documentation. ## Impact on prompt caching Enabling or disabling the advisor mid-session does not invalidate your main model's [prompt cache](/docs/en/prompt-cachin… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …cached](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), which reduces cost and latency for repeated prefixes. For how a custom system prompt or `append` text affects cache reus… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …s rates. For more information, see [Switching models](/docs/en/prompt-caching.md#switching-models). ## Configure specific features The table below maps each option to the feature it configures. For…