api-20261009T153709Z / page 21 of 22 / documentation capture

api/beta/vaults/credentials/update Changed · +2 / -0 lines

from line 21

2121

2222## Headers

2323

24- `"anthropic-version": optional string`

25

2426- `"anthropic-beta": optional array of AnthropicBeta`

2527

2628 Optional header to specify the beta version(s) you want to use.

api/beta/vaults/delete Changed · +2 / -0 lines

from line 17

1717

1818## Headers

1919

20- `"anthropic-version": optional string`

21

2022- `"anthropic-beta": optional array of AnthropicBeta`

2123

2224 Optional header to specify the beta version(s) you want to use.

api/beta/vaults/list Changed · +2 / -0 lines

from line 27

2727

2828## Headers

2929

30- `"anthropic-version": optional string`

31

3032- `"anthropic-beta": optional array of AnthropicBeta`

3133

3234 Optional header to specify the beta version(s) you want to use.

api/beta/vaults/retrieve Changed · +2 / -0 lines

from line 17

1717

1818## Headers

1919

20- `"anthropic-version": optional string`

21

2022- `"anthropic-beta": optional array of AnthropicBeta`

2123

2224 Optional header to specify the beta version(s) you want to use.

api/beta/vaults/update Changed · +2 / -0 lines

from line 17

1717

1818## Headers

1919

20- `"anthropic-version": optional string`

21

2022- `"anthropic-beta": optional array of AnthropicBeta`

2123

2224 Optional header to specify the beta version(s) you want to use.

build-with-claude/cache-diagnostics Changed · +0 / -4 lines

from line 9

99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).

1010 supportedPlatforms:

1111 Claude API: ga

12 Claude Platform on AWS: not available

13 Amazon Bedrock: not available

14 Google Cloud: not available

15 Microsoft Foundry: not available

1612---

1713

1814[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) cuts latency and cost significantly, but only when the beginning of your prompt is byte-for-byte identical to a recent request. A reordered tool, a timestamp interpolated into your system prompt, or an edit to an earlier message can silently invalidate the cache. Without cache diagnostics, the only signal is `usage.cache_read_input_tokens` dropping to zero, with no indication of what changed.

build-with-claude/claude-in-amazon-bedrock Changed · +1 / -1 lines

from line 348

348348| Claude Haiku 5.5 | `anthropic.claude-haiku-5-5` | [See Access](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#access) |

349349| Claude Haiku 4.5 | `anthropic.claude-haiku-4-5` | Open |

350350

351Use Claude Code 2.1.255 or later with Claude Fable 5.1 on Amazon Bedrock, and 2.1.280 or later with Claude Opus 5.5; run `claude update` to upgrade.

351Use Claude Code 2.1.255 or later with Claude Fable 5.1 on Amazon Bedrock, and 2.1.280 or later with Claude Opus 5.5 and Claude Haiku 5.5; run `claude update` to upgrade.

352352

353353<Tip>

354354 Upgrading to a newer Claude model? In Claude Code, run `/claude-api migrate` to apply model ID swaps and breaking parameter changes across your codebase. The skill detects which cloud platform your code targets and adjusts model ID formats and feature changes for that platform. See [Migrating to a newer Claude model](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model).

build-with-claude/claude-in-microsoft-foundry Changed · +1 / -1 lines

from line 653

653653* Models API

654654* Message Batches API

655655* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)

656* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Microsoft Foundry; the beta computer use tool versions remain available)

656* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Microsoft Foundry; the beta computer use tool versions remain available for the models listed under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions))

657657

658658### Additional features not supported when hosted on Azure

659659

build-with-claude/compaction-background Changed · +0 / -1 lines

from line 23

2323 supportedPlatforms:

2424 Claude API: beta

2525 Claude Platform on AWS: beta

26 Amazon Bedrock: not available

2726 Google Cloud: beta

2827 Microsoft Foundry: beta

2928---

build-with-claude/compaction-keep-recent-turns Changed · +0 / -1 lines

from line 23

2323 supportedPlatforms:

2424 Claude API: beta

2525 Claude Platform on AWS: beta

26 Amazon Bedrock: not available

2726 Google Cloud: beta

2827 Microsoft Foundry: beta

2928---

build-with-claude/compaction-on-demand Changed · +1 / -2 lines

from line 23

2323 supportedPlatforms:

2424 Claude API: beta

2525 Claude Platform on AWS: beta

26 Amazon Bedrock: not available

2726 Google Cloud: beta

2827 Microsoft Foundry: beta

2928---

from line 832

833832

834833* **Threshold compaction and context editing.** You can't send `compaction` and `context_management` on the same request. Threshold compaction (`compact_20260112`) can't run on a request that carries a signed block.

835834* **Prompt caching.** `cache_control` on the block places a breakpoint after the summary.

836* **Mid-conversation system messages and tool changes.** `role: "system"` messages inside the summarized range are summarized too, so their text instructions stop applying once the block replaces them. If an instruction still matters, state it again in a `role: "system"` message. Send that message right after your next new `user` turn, and leave it in your history from then on. For [tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes), and for where that message goes when you keep turns after the block, see [Change the system prompt or tools](https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks#change-the-system-prompt-or-tools).

835* **Mid-conversation system messages and tool changes.** `role: "system"` messages inside the summarized range are summarized too, so their text instructions stop applying once the block replaces them. A [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) level they set isn't carried over either: until a later message sets a level, turns run at the request's top-level `output_config.effort`, or the model's default if you don't set one. If an instruction or effort level still matters, state it again in a `role: "system"` message. Send that message right after your next new `user` turn, and leave it in your history from then on. For [tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes), and for where that message goes when you keep turns after the block, see [Change the system prompt or tools](https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks#change-the-system-prompt-or-tools).

837836* **Task budgets.** Don't send the `remaining` value of a [task budget](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (`output_config.task_budget.remaining`) with `compaction` or on requests that carry the block. Doing so returns a 400 error.

838837* **Token counting.** The [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) endpoint ignores the `compaction` parameter.

839838* **Content the summary can't carry.** Images, documents, `container_upload` blocks, and fetched URLs inside the summarized messages are gone once the block replaces them. Restate or re-upload anything a later turn still needs.

build-with-claude/context-windows Changed · +1 / -1 lines

from line 142

142142For more specialized needs, [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) offers additional strategies:

143143

144144* **Tool result clearing:** Clear old tool results in agentic workflows

145* **Thinking block clearing:** Manage thinking blocks when you use extended thinking

145* **Thinking block clearing:** Manage thinking blocks from earlier turns

146146

147147Cached prompt prefixes still occupy the context window: [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) changes what you pay for those tokens, not whether they count.

148148

build-with-claude/extended-thinking Changed · +1 / -1 lines

from line 384

384384}

385385```

386386

387`effort: "high"` matches the API default; it appears here only to show where the depth control now lives, and omitting it produces identical behavior.

387`effort: "high"` is the default on Claude Sonnet 4.6, so omitting it here produces identical behavior; it appears only to show where the depth control lives in adaptive mode. Claude Opus 5.5 and Claude Haiku 5.5 default to `"medium"`, and other models that support effort default to `"high"` (see [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels)).

388388

389389Expect a behavioral difference, not just a syntax change. With a fixed budget, Claude thinks on every request. With adaptive thinking, Claude determines whether and how much to think on each request, and at lower [effort](https://platform.claude.com/docs/en/build-with-claude/effort) settings it may skip thinking entirely on easy inputs. You can also remove the `interleaved-thinking-2025-05-14` beta header after migrating: adaptive thinking interleaves automatically, and the Claude API ignores the header on these models. Thinking block preservation changes too: Claude Opus 4.5 and models numbered 4.6 and higher keep prior turns' thinking blocks in context and bill them as input, where Claude Sonnet 4.5 (deprecated), Claude Haiku 4.5, and earlier models stripped them; see [thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-block-preservation-by-model).

390390

build-with-claude/files Changed · +0 / -2 lines

from line 8

88 supportedPlatforms:

99 Claude API: ga

1010 Claude Platform on AWS: ga

11 Amazon Bedrock: not available

12 Google Cloud: not available

1311 Microsoft Foundry:

1412 availability: ga

1513 note: On [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), the Files API requires a [Hosted on Anthropic deployment](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#additional-features-not-supported-when-hosted-on-azure).

build-with-claude/handling-stop-reasons Changed · +1 / -1 lines

from line 1946

19461946

19471947On a refusal, the `stop_details` object identifies the policy category that triggered it. The categories and the full refusal response shape are covered on [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). `stop_details` is `null` for all stop reasons other than `refusal`.

19481948

1949A refused request on Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, or Claude Haiku 5.5 can usually be served by retrying on another Claude model. [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) shows how to set up that retry, server-side or in your client. If you build the retry yourself from Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) covers how to avoid paying the prompt-cache cost twice.

1949A refused request on Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, or Claude Haiku 5.5 can usually be served by retrying on another Claude model. [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) shows how to set up that retry, server-side or in your client. Claude Haiku 5.5 has no server-side fallback, so set up its retry [in your client](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback). If you build the retry yourself from Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) covers how to avoid paying the prompt-cache cost twice.

19501950

19511951### model\_context\_window\_exceeded

19521952

build-with-claude/prompt-engineering/claude-prompting-best-practices Changed · +2 / -2 lines

from line 774

774774 ```

775775</CodeGroup>

776776

777If you are not using extended thinking, no changes are required. On Claude Opus 4.6 through Claude Opus 4.8 and Claude Sonnet 4.6, thinking is off when you omit the `thinking` parameter. On Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Haiku 5.5, thinking is on by default when you omit the `thinking` parameter. On Claude Opus 5 and Claude Haiku 5.5, you can disable it only at effort `high` or lower. On Claude Sonnet 5.5, the lowest thinking setting is `between_tools`, accepted at effort `high` or lower. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on, regardless of whether you set the `thinking` parameter.

777If you are not using extended thinking, you don't need to add a `thinking` parameter. On Claude Opus 4.6 through Claude Opus 4.8 and Claude Sonnet 4.6, thinking is off when you omit the `thinking` parameter. On Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Haiku 5.5, thinking is on by default when you omit the `thinking` parameter, so a response can begin with `thinking` blocks. Select content blocks by `type` rather than by position, and leave room in `max_tokens` for thinking. On Claude Opus 5 and Claude Haiku 5.5, you can disable it only at effort `high` or lower. On Claude Sonnet 5.5, the lowest thinking setting is `between_tools`, accepted at effort `high` or lower. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on, regardless of whether you set the `thinking` parameter.

778778

779779* **Prefer general instructions over prescriptive steps.** A prompt like "think thoroughly" often produces better reasoning than a hand-written step-by-step plan. Claude's reasoning frequently exceeds what a human would prescribe.

780780* **Multishot examples work with thinking.** Worked examples in your prompt shape how Claude approaches similar problems in its own thinking blocks. Present each example as a problem, the method to apply, and the expected answer.

from line 1077

10771077

107810783. **Request specific features explicitly:** Animations and interactive elements should be requested explicitly when desired.

10791079

10804. **Update thinking configuration:** Claude 4.6 models use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`) instead of manual thinking with `budget_tokens`. Use the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) to control thinking depth.

10804. **Update thinking configuration:** Claude 4.6 and later models use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`) instead of manual thinking with `budget_tokens`. On Claude 4.7 and later models, setting `budget_tokens` returns a 400 error. Use the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) to control thinking depth.

10811081

108210825. **Migrate away from prefilled responses:** Prefilled responses on the last assistant turn are no longer supported starting with Claude 4.6 models and Claude Mythos Preview. See [Migrating away from prefilled responses](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#migrating-away-from-prefilled-responses) for detailed guidance on alternatives.

10831083

build-with-claude/prompt-engineering/prompting-claude-opus-5-5 Changed · +1 / -1 lines

from line 43

4343* Reserve `xhigh` and `max` for work where you've measured a quality gain.

4444* To get less thinking, lower the effort level first. Lowering effort reduces thinking, and with it cost and latency, more reliably than prompt instructions do.

4545

46Changing the top-level `effort` value between requests invalidates the prompt cache. To run individual turns at a different level, use a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta) instead, which keeps the cache.

46Changing the top-level `effort` value between requests invalidates the prompt cache. To change the level partway through a conversation, use a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta) instead, which keeps the cache. A change holds for every later turn until another one replaces it.

4747

4848## Prompts written for thinking disabled

4949

build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 Changed · +1 / -1 lines

from line 36

3636* Reserve `xhigh` and `max` for work where you've measured a quality gain, because thinking and replies get much longer there. At those levels, `between_tools` isn't accepted, so up-front thinking can't be turned off.

3737* To get less thinking, lower the effort level. From `medium` up, the model thinks briefly before almost every reply, even a greeting, which adds to the time before the first visible token. Asking it in the system prompt to think less doesn't reliably reduce its thinking. At `low`, it skips thinking on most simple requests.

3838

39Changing the top-level `effort` value between requests invalidates the prompt cache. To run individual turns at a different level, use a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta) instead, which keeps the cache. For example, run an interactive session at `low` and raise effort to `high` when the user submits a hard problem. Per-message effort changes need adaptive thinking. With `between_tools`, they return a 400 error, as [Running without up-front thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#running-without-up-front-thinking) explains.

39Changing the top-level `effort` value between requests invalidates the prompt cache. To change the level partway through a conversation, use a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta) instead, which keeps the cache. A change holds for every later turn until another one replaces it. For example, in an interactive session at `low`, add a change to `high` before the user's hard problem, and a change back to `low` after Claude answers it. Per-message effort changes need adaptive thinking. With `between_tools`, they return a 400 error, as [Running without up-front thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#running-without-up-front-thinking) explains.

4040

4141## Steer initiative and scope

4242

build-with-claude/streaming Changed · +2 / -2 lines

from line 1

11---

22title: Streaming messages

33url: https://platform.claude.com/docs/en/build-with-claude/streaming

4description: Stream Messages API responses incrementally with server-sent events, including text, tool use, and extended thinking deltas.

4description: Stream Messages API responses incrementally with server-sent events, including text, tool use, and thinking deltas.

55---

66

77When creating a Message, you can set `"stream": true` to incrementally stream the response using [server-sent events](https://developer.mozilla.org/en-US/Web/API/Server-sent%5Fevents/Using%5Fserver-sent%5Fevents) (SSE).

from line 1507

15071507### Error recovery best practices

15081508

150915091. **Use SDK features:** Leverage the SDK's built-in message accumulation and error handling capabilities.

15102. **Handle content types:** Be aware that messages can contain multiple content blocks (`text`, `tool_use`, `thinking`). Tool use and extended thinking blocks cannot be partially recovered. You can resume streaming from the most recent text block.

15102. **Handle content types:** Be aware that messages can contain multiple content blocks (`text`, `tool_use`, `thinking`). Tool use and thinking blocks cannot be partially recovered. You can resume streaming from the most recent text block.

15111511

15121512## Next steps

15131513

build-with-claude/thinking-tool-workflows Changed · +1 / -1 lines

from line 14

1414

1515Each link leads to the full statement on the Thinking page:

1616

17* [Limit tool choice to `auto` or `none` in manual mode](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use): `tool_choice` options that force tool use return an error with manual extended thinking (`thinking: {type: "enabled"}`); adaptive thinking supports forced tool use.

17* [Limit tool choice to `auto` or `none` in manual mode](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use): `tool_choice` options that force tool use return an error with manual extended thinking (`thinking: {type: "enabled"}`). Adaptive thinking supports forced tool use, except on Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1, which return a 400 error. Where forced tool use is accepted, it skips thinking: the response starts with the tool call.

1818* [Keep one thinking configuration per assistant turn](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use): a tool-use loop is one assistant turn, so change the configuration only between turns.

1919* [Pass thinking blocks back complete and unmodified](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks): when you return a tool result, the thinking blocks from the assistant message must come back with it.

2020* [Echo the assistant message exactly as received](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks): rebuilding the message or filtering out `redacted_thinking` blocks triggers a 400 error.

build-with-claude/working-with-messages Changed · +1 / -1 lines

from line 323

323323

324324### System role in messages

325325

326On 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 include messages with `"role": "system"` after a user turn (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)) to add a new system instruction partway through a conversation. A `system` message cannot be the first entry in `messages`. Use the top-level `system` field for instructions that apply from the start.

326On 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 include messages with `"role": "system"` after a user turn (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)) to add a new system instruction partway through a conversation. A `system` message that carries content cannot be the first entry in `messages`. Use the top-level `system` field for instructions that apply from the start.

327327

328328A mid-conversation system message has the same authority as the top-level `system` field, but because it is appended to the end of the message history, it does not invalidate any cached prefix that came before it. Use the top-level `system` field for instructions that should apply from the very first turn, and a mid-conversation system message for instructions that only become relevant later.

329329

cli-sdks-libraries/libraries/apple-foundation-models Changed · +1 / -1 lines

from line 87

8787

8888### Effort

8989

90Pin a Claude [effort level](https://platform.claude.com/docs/en/build-with-claude/effort) for every request with `fixedEffort:`. It takes precedence over the framework's per-request reasoning hints. The framework's named reasoning levels stop at high; to request more effort for a single request instead, pass a custom reasoning level naming the Claude effort (`.custom("xhigh")` or `.custom("max")`), which maps directly. The API defaults to `high` when no effort is sent:

90Pin a Claude [effort level](https://platform.claude.com/docs/en/build-with-claude/effort) for every request with `fixedEffort:`. It takes precedence over the framework's per-request reasoning hints. The framework's named reasoning levels stop at high; to request more effort for a single request instead, pass a custom reasoning level naming the Claude effort (`.custom("xhigh")` or `.custom("max")`), which maps directly. When no effort is sent, the API uses the model's default level, which differs by model (see [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels)):

9191

9292```swift

9393ClaudeLanguageModel(name: .opus5_5, auth: auth, fixedEffort: .xhigh)

cli-sdks-libraries/middleware Changed · +1 / -1 lines

from line 177

177177

178178## Built-in middleware

179179

180The SDK ships a refusal-fallback middleware that automatically retries requests Claude Fable 5 declines on a fallback model. See [Detect and retry on a fallback model](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) for setup and per-language examples.

180The SDK ships a refusal-fallback middleware that automatically retries a request Claude declines (`stop_reason: "refusal"`) on a fallback model. [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) lists the models whose safety classifiers can decline requests, and [Detect and retry on a fallback model](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) covers setup and per-language examples.

181181

cli-sdks-libraries/sdks/java Changed · +2 / -2 lines

from line 690

690690 Consider using [streaming](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/java#streaming) for longer running requests.

691691</Warning>

692692

693Avoid setting a large `maxTokens` value without using streaming. Some networks may drop idle connections after a certain period of time, which can cause the request to fail or [timeout](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/java#timeouts) without receiving a response from Anthropic. The SDK periodically pings the API to keep the connection alive and reduce the impact of these networks.

693Avoid setting a large `maxTokens` value without using streaming. Some networks may drop idle connections after a certain period of time, which can cause the request to fail or [time out](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/java#timeouts) without receiving a response from Anthropic. The SDK periodically pings the API to keep the connection alive and reduce the impact of these networks.

694694

695695The SDK throws an error if a non-streaming request is expected to take longer than 10 minutes. Using a [streaming method](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/java#streaming) or [overriding the timeout](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/java#timeouts) at the client or request level disables the error.

696696

from line 1077

10771077

10781078The Java SDK supports the following platforms through separate dependencies that provide platform-specific `Backend` implementations:

10791079

1080* **Agent Platform:** `com.anthropic:anthropic-java-vertex`: Use `VertexBackend.fromEnv()` or `VertexBackend.builder()`.

1080* **Agent Platform:** `com.anthropic:anthropic-java-vertex`: Use `VertexBackend.builder()` or `VertexBackend.fromEnv()`. `fromEnv()` reads `CLOUD_ML_REGION` and `ANTHROPIC_VERTEX_PROJECT_ID` and uses Application Default Credentials.

10811081* **Bedrock:** `com.anthropic:anthropic-java-bedrock`: Use `BedrockMantleBackend.fromEnv()` or `BedrockMantleBackend.builder()` for the Messages-API Bedrock endpoint, or `BedrockBackend.fromEnv()` / `BedrockBackend.builder()` (`bedrock-runtime` path).

10821082* **Claude Platform on AWS:** `com.anthropic:anthropic-java-aws`: Use `AwsBackend.fromEnv()` (reads `ANTHROPIC_AWS_WORKSPACE_ID` and the AWS default region/credential chain) or `AwsBackend.builder()`. Available in beta.

10831083* **Foundry:** `com.anthropic:anthropic-java-foundry`: Use `FoundryBackend.fromEnv()` or `FoundryBackend.builder()`.

intro Changed · +1 / -1 lines

from line 60

6060 </Step>

6161

6262 <Step title="Explore features and tools">

63 Discover what Claude can do: extended thinking, web search, file handling, structured outputs, and more.

63 Discover what Claude can do: thinking, web search, file handling, structured outputs, and more.

6464

6565 [Browse the features overview](https://platform.claude.com/docs/en/build-with-claude/overview)

6666 </Step>

One read of Claude Developer Platformapi-20261009T153709Z

What this read moved

api/beta/vaults/credentials/update Changed · +2 / -0 lines

api/beta/vaults/delete Changed · +2 / -0 lines

api/beta/vaults/list Changed · +2 / -0 lines

api/beta/vaults/retrieve Changed · +2 / -0 lines

api/beta/vaults/update Changed · +2 / -0 lines

build-with-claude/cache-diagnostics Changed · +0 / -4 lines

build-with-claude/claude-in-amazon-bedrock Changed · +1 / -1 lines

build-with-claude/claude-in-microsoft-foundry Changed · +1 / -1 lines

build-with-claude/compaction-background Changed · +0 / -1 lines

build-with-claude/compaction-keep-recent-turns Changed · +0 / -1 lines

build-with-claude/compaction-on-demand Changed · +1 / -2 lines

build-with-claude/context-windows Changed · +1 / -1 lines

build-with-claude/extended-thinking Changed · +1 / -1 lines

build-with-claude/files Changed · +0 / -2 lines

build-with-claude/handling-stop-reasons Changed · +1 / -1 lines

build-with-claude/prompt-engineering/claude-prompting-best-practices Changed · +2 / -2 lines

build-with-claude/prompt-engineering/prompting-claude-opus-5-5 Changed · +1 / -1 lines

build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 Changed · +1 / -1 lines

build-with-claude/streaming Changed · +2 / -2 lines

build-with-claude/thinking-tool-workflows Changed · +1 / -1 lines

build-with-claude/working-with-messages Changed · +1 / -1 lines

cli-sdks-libraries/libraries/apple-foundation-models Changed · +1 / -1 lines

cli-sdks-libraries/middleware Changed · +1 / -1 lines

cli-sdks-libraries/sdks/java Changed · +2 / -2 lines

intro Changed · +1 / -1 lines