One read of Claude Developer Platformapi-20261007T150733Z

This capture is too large to show at once. Changes 26-49 of 49 are below, significant first; the rest are on the following screens.

agents-and-tools/tool-use/define-tools Changed · +2 / -2 lines

from line 75

7575 * What the tool does

7676 * When it should be used (and when it shouldn't)

7777 * What each parameter means and how it affects the tool's behavior

78 * Any important caveats or limitations, such as what information the tool does not return if the tool name is unclear. The more context you can give Claude about your tools, the better it will be at deciding when and how to use them. Aim for at least 3–4 sentences for each tool description, more if the tool is complex.

78 * Any important caveats or limitations, such as what information the tool does not return if the tool name is unclear. The more context you can give Claude about your tools, the better it will be at determining when and how to use them. Aim for at least 3–4 sentences for each tool description, more if the tool is complex.

7979 

8080* **Prioritize descriptions, but consider using `input_examples` for complex tools.** Clear descriptions are most important, but for tools with complex inputs, nested objects, or format-sensitive parameters, you can use the `input_examples` field to provide schema-validated examples. See [Providing tool use examples](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#providing-tool-use-examples) for details.

8181 

from line 844

844844 

845845When working with the `tool_choice` parameter, there are four possible options:

846846 

847* `auto` allows Claude to decide whether to call any provided tools or not. This is the default value when `tools` are provided.

847* `auto` allows Claude to determine whether to call any provided tools or not. This is the default value when `tools` are provided.

848848* `any` tells Claude that it must use one of the provided tools, but doesn't force a particular tool.

849849* `tool` forces Claude to always use a particular tool.

850850* `none` prevents Claude from using any tools. This is the default value when no `tools` are provided.

agents-and-tools/tool-use/server-tools Changed · +1 / -1 lines

from line 1073

10731073 

10741074[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) uses the same `allowed_domains` and `blocked_domains` fields on the `web_search` and `web_fetch` entries of the agent toolset. On Managed Agents, each list holds at most 64 entries, domains listed for `web_fetch` cannot include a path, and fields specific to the Messages API tools, such as `max_uses`, `citations`, and `cache_control`, are not available. See [Domain list rules](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions#domain-list-rules) for the full rules.

10751075 

1076Organization-level web search and web fetch settings in the Claude Console apply to Messages API requests only; they do not apply to Managed Agents sessions, which use only the per-tool lists on the agent toolset.

1076Organization-level web search and web fetch settings in the Claude Console apply to Messages API requests only. They do not apply to Managed Agents sessions, which use the per-tool lists on the agent toolset instead. For a session in a cloud environment with `limited` networking, the environment's `allowed_hosts` also applies to `web_search` and `web_fetch`; see [Networking](https://platform.claude.com/docs/en/managed-agents/environments#networking). The per-tool lists restrict these tools further, within the hosts that `allowed_hosts` allows.

10771077 

10781078## Dynamic filtering with code execution

10791079 

agents-and-tools/tool-use/web-search-tool Changed · +1 / -1 lines

from line 237

237237 Web search is enabled for your organization unless an administrator has disabled it in the [Claude Console](https://platform.claude.com/settings/capabilities), where they can also restrict which domains it searches. If it's disabled, a request that includes the tool fails with a 400 `invalid_request_error` that says web search is not enabled, rather than an [error code](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool#errors) inside a search result.

238238</Note>

239239 

240These organization-level settings in the Claude Console apply to Messages API requests only. [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) sessions use only the per-tool `allowed_domains` and `blocked_domains` lists on the agent toolset; see [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).

240These organization-level settings in the Claude Console apply to Messages API requests only. [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) sessions use the per-tool `allowed_domains` and `blocked_domains` lists on the agent toolset instead; see [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions). For a session in a cloud environment with `limited` networking, the environment's `allowed_hosts` also applies to `web_search` and `web_fetch`; see [Networking](https://platform.claude.com/docs/en/managed-agents/environments#networking). The per-tool lists restrict these tools further, within the hosts that `allowed_hosts` allows.

241241 

242242Provide the web search tool in your API request:

243243 

api/rate-limits Changed · +1 / -1 lines

from line 186

186186 

187187*2 Opus rate limit is a total limit that applies to combined traffic across Claude Opus 4.8, Opus 4.7, Opus 4.6, and Opus 4.5. Claude Opus 5.5 and Claude Opus 5 each have a separate rate limit and are not part of this combined bucket.*

188188 

189*3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across Sonnet 4.6 and Sonnet 4.5. Claude Sonnet 5.5 and Claude Sonnet 5 each have a separate rate limit and are not part of this combined bucket.*

189*3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across Sonnet 4.6 and Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)). Claude Sonnet 5.5 and Claude Sonnet 5 each have a separate rate limit and are not part of this combined bucket.*

190190 

191191*4 Limit counts `cache_read_input_tokens` toward ITPM usage.*

192192 

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

from line 642

642642 

643643### Context window

644644 

645Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Microsoft Foundry. Other Claude models, including Claude Sonnet 4.5, have a 200k-token context window.

645Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Microsoft Foundry. Other Claude models, including Claude Sonnet 4.5 (deprecated), have a 200k-token context window.

646646 

647647### Claude features not supported for Claude in Microsoft Foundry

648648 

build-with-claude/claude-on-vertex-ai Changed · +2 / -2 lines

from line 369

369369 

370370### Context window

371371 

372Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Agent Platform. Other Claude models, including Sonnet 4.5 and Sonnet 4 (deprecated), have a 200k-token context window.

372Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) on Agent Platform. Other Claude models, including Sonnet 4.5 (deprecated) and Sonnet 4 (deprecated), have a 200k-token context window.

373373 

374374Agent Platform limits request payloads to 30 MB. When sending large documents or many images, you might reach this limit before the token limit.

375375 

from line 384

384384Regional and multi-region endpoints include a 10% pricing premium over global endpoints.

385385 

386386<Note>

387 This applies to Claude Sonnet 4.5 and future models only. Older models (Claude Sonnet 4 (deprecated), Opus 4 (deprecated), and earlier) maintain their existing pricing structures.

387 This applies to Claude Sonnet 4.5 (deprecated) and future models only. Older models (Claude Sonnet 4 (deprecated), Opus 4 (deprecated), and earlier) maintain their existing pricing structures.

388388</Note>

389389 

390390### When to use each option

build-with-claude/handling-stop-reasons Changed · +2 / -2 lines

from line 1941

19411941</CodeGroup>

19421942 

19431943<Tip>

1944 If you encounter `refusal` stop reasons frequently while using Claude Sonnet 4.5 or Claude Opus 4.1 (the latter [retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), you can try updating your API calls to use Haiku 4.5 (`claude-haiku-4-5-20251001`), which has different usage restrictions. Learn more about [understanding Sonnet 4.5's API safety filters](https://support.claude.com/en/articles/12449294-understanding-sonnet-4-5-s-api-safety-filters).

1944 If you encounter `refusal` stop reasons frequently while using Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) or Claude Opus 4.1 (the latter [retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), you can try updating your API calls to use Haiku 4.5 (`claude-haiku-4-5-20251001`), which has different usage restrictions. Learn more about [understanding Sonnet 4.5's API safety filters](https://support.claude.com/en/articles/12449294-understanding-sonnet-4-5-s-api-safety-filters).

19451945</Tip>

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`.

from line 1953

19531953Claude stopped because it reached the model's context window limit. This lets you request the maximum possible tokens without knowing the exact input size.

19541954 

19551955<Note>

1956 This stop reason is currently typed only in the SDK's `beta` (csharp, go: `Beta`; java: `beta()`) namespace, so the following examples call `client.beta.messages` (csharp, go: `client.Beta.Messages`; java: `client.beta().messages()`; php: `$client->beta->messages`) and use the `Beta`-prefixed types. On Sonnet 4.5 and newer models the API returns this value without a beta header. For earlier models, add the `model-context-window-exceeded-2025-08-26` beta header to enable it.

1956 This stop reason is currently typed only in the SDK's `beta` (csharp, go: `Beta`; java: `beta()`) namespace, so the following examples call `client.beta.messages` (csharp, go: `client.Beta.Messages`; java: `client.beta().messages()`; php: `$client->beta->messages`) and use the `Beta`-prefixed types. On Sonnet 4.5 (deprecated) and newer models the API returns this value without a beta header. For earlier models, add the `model-context-window-exceeded-2025-08-26` beta header to enable it.

19571957</Note>

19581958 

19591959<CodeGroup>

build-with-claude/mid-conversation-system-messages Changed · +2 / -2 lines

from line 1642

16421642 

16431643You can still set the top-level `system` field for instructions that should apply to the entire conversation. Reserve mid-conversation system messages for instructions that only become relevant later, or that you want to add without invalidating the cached prefix.

16441644 

1645A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level from the next `user` turn on. This is in beta on Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5 on the Claude API and Google Cloud, and requires the `mid-conversation-output-config-2026-07-01` beta header. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).

1645A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level partway through a conversation. This is in beta on Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5 on the Claude API and Google Cloud, and requires the `mid-conversation-output-config-2026-07-01` beta header. On Amazon Bedrock, it's in beta on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5.5, with the same beta value. Claude Opus 5 doesn't support it on Amazon Bedrock. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).

16461646 

16471647<CodeGroup>

16481648 ```bash cURL

from line 2096

20962096messages.3.content.0: cache_control is not permitted on a turn-scoped system message (clear_at: 'next_user_message')

20972097```

20982098 

2099The first is the error returned without the beta header. On Amazon Bedrock and Google Cloud, pass the beta value as described in [Beta headers](https://platform.claude.com/docs/en/api/beta-headers).

2099The first is the error returned without the beta header. On Google Cloud and [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), send the beta value in the `anthropic-beta` header, as on the Claude API (see [Beta headers](https://platform.claude.com/docs/en/api/beta-headers)). With the Amazon Bedrock [InvokeModel API](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), put it in the `anthropic_beta` array of the request body instead.

21002100 

21012101Through the SDK, set `clear_at` (csharp, go: `ClearAt`; java: `.clearAt()`; php: `clearAt`) on the `role: "system"` entry in `messages` and send the beta header. The following example appends a turn-scoped reminder after the user turn; on the next request, once a later user message exists, the reminder stays in the array but no longer renders:

21022102 

build-with-claude/overview Changed · +1 / -1 lines

from line 41

4141| Feature | Description | Zero Data Retention (ZDR) | Availability |

4242| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- |

4343| [Context windows](https://platform.claude.com/docs/en/build-with-claude/context-windows) | Up to 1M tokens for processing large documents, extensive code bases, and long conversations. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

44| [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) | Let Claude dynamically decide when and how much to think. The only thinking mode on Claude 4.7 and later models. Use the effort parameter to control thinking depth. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

44| [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) | Let Claude dynamically determine when and how much to think. The only thinking mode on Claude 4.7 and later models. Use the effort parameter to control thinking depth. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

4545| [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) | Process large volumes of requests asynchronously for cost savings. Send batches with a large number of queries per batch. Batch API calls cost 50% less than standard API calls. | Not ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws /> |

4646| [Citations](https://platform.claude.com/docs/en/build-with-claude/citations) | Ground Claude's responses in source documents. With Citations, Claude can provide detailed references to the exact sentences and passages it uses to generate responses, leading to more verifiable, trustworthy outputs. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

4747| [Data residency](https://platform.claude.com/docs/en/manage-claude/data-residency) | Control where model inference runs using geographic controls. Specify `"global"` or `"us"` routing per request through the `inference_geo` parameter. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws /> |

build-with-claude/prompt-caching Changed · +2 / -2 lines

from line 606

606606* 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, and [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview)

607607* 2,048 tokens for [Claude Mythos Preview](https://anthropic.com/glasswing) and Claude Opus 4.7

608608* 4,096 tokens for Claude Opus 4.6 and Claude Opus 4.5

609* 1,024 tokens for Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Sonnet 4 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations))

609* 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 Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Sonnet 4 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations))

610610* 4,096 tokens for Claude Haiku 4.5

611611* 2,048 tokens for Claude Haiku 3.5 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations))

612612 

from line 747

747747User: [tool_result_1, cache=True],

748748Assistant: [thinking_block_2] + [text block 2],

749749User: [Text response, cache=True]

750# On earlier Opus/Sonnet and all Haiku models, non-tool-result user block causes prior thinking blocks to be stripped; on Opus 4.5+/Sonnet 4.6+ they are kept

750# Depending on the model, this non-tool-result user block either keeps prior thinking blocks or strips them (see the next paragraph)

751751```

752752 

753753On earlier Opus/Sonnet models and all Haiku models, all previous thinking blocks are removed from context at this point. On Opus 4.5+ and Sonnet 4.6+, prior thinking blocks are kept by default and remain part of the cached prefix.

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

from line 544

544544 

545545Claude's latest models offer thinking capabilities that can be especially helpful for tasks involving reflection after tool use or complex multistep reasoning. You can guide its initial or interleaved thinking for better results.

546546 

547Claude 4.6 and later models and Claude Mythos Preview use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`), where Claude dynamically decides when and how much to think. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on and adaptive thinking is the only mode. Claude calibrates its thinking based on two factors: the `effort` parameter and query complexity. Higher effort elicits more thinking, and more complex queries do the same. On easier queries that don't require thinking, the model responds directly. In internal evaluations, adaptive thinking reliably drives better performance than extended thinking. Consider moving to adaptive thinking.

547Claude 4.6 and later models and Claude Mythos Preview use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`), where Claude dynamically determines when and how much to think. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5, thinking is always on and adaptive thinking is the only mode. Claude calibrates its thinking based on two factors: the `effort` parameter and query complexity. Higher effort elicits more thinking, and more complex queries do the same. On easier queries that don't require thinking, the model responds directly. In internal evaluations, adaptive thinking reliably drives better performance than extended thinking. Consider moving to adaptive thinking.

548548 

549549Use adaptive thinking for workloads that require agentic behavior such as multistep tool use, complex coding tasks, and long-horizon agent loops. Older models use manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) with `budget_tokens`; see the [per-model configuration table](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#supported-models) for which configuration each model accepts.

550550 

from line 796

796796 

797797#### Context awareness and multiwindow workflows

798798 

799Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5 feature [context awareness](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness), enabling the model to track its remaining context window (that is, its "token budget") throughout a conversation. This enables Claude to execute tasks and manage context more effectively by understanding how much space it has to work.

799Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5 (deprecated), and Claude Haiku 4.5 feature [context awareness](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness), enabling the model to track its remaining context window (that is, its "token budget") throughout a conversation. This enables Claude to execute tasks and manage context more effectively by understanding how much space it has to work.

800800 

801801**Managing context limits:**

802802 

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

from line 122

122122 

123123## Thinking instructions in chat system prompts

124124 

125In chat applications, if your system prompt contains instructions that tell Claude to think carefully before answering, consider removing them for Claude Opus 5.5. The model decides for itself how much to think, and [effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#calibrate-effort) is the main control. In Anthropic's testing in a chat product, removing such a line made replies start sooner, with no clear decline in the quality of the reply.

125In chat applications, if your system prompt contains instructions that tell Claude to think carefully before answering, consider removing them for Claude Opus 5.5. The model determines how much to think, and [effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#calibrate-effort) is the main control. In Anthropic's testing in a chat product, removing such a line made replies start sooner, with no clear decline in the quality of the reply.

126126 

127127In multi-turn chat, Claude Opus 5.5 sometimes goes back over an earlier answer while it thinks about a new message, even a short follow-up, which adds thinking and latency on later turns. If you would rather the model treat earlier answers as settled, add two sentences at the end of the system prompt:

128128 

build-with-claude/task-budgets Changed · +1 / -1 lines

from line 669

669669 </Card>

670670 

671671 <Card title="Adaptive thinking" icon="brain" href="https://platform.claude.com/docs/en/build-with-claude/thinking">

672 Let Claude decide when and how much to use extended thinking.

672 Let Claude determine when and how much to use extended thinking.

673673 </Card>

674674 

675675 <Card title="Compaction" icon="arrows-clockwise" href="https://platform.claude.com/docs/en/build-with-claude/compaction">

cli-sdks-libraries/libraries/openai-sdk Changed · +1 / -1 lines

from line 203

203203 

204204### Thinking support

205205 

206You can enable [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) by adding the `thinking` parameter. On current models thinking is adaptive, with Claude deciding when and how deeply to think, and on Claude 5 models it is on by default; manually configured extended thinking is a legacy mode. Although thinking improves Claude's reasoning for complex tasks, the OpenAI SDK doesn't return Claude's thinking. For full thinking features, including [summarized thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#summarized-thinking), use the native Claude API.

206You can enable [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) by adding the `thinking` parameter. On current models thinking is adaptive, with Claude determining when and how deeply to think, and on Claude 5 models it is on by default; manually configured extended thinking is a legacy mode. Although thinking improves Claude's reasoning for complex tasks, the OpenAI SDK doesn't return Claude's thinking. For full thinking features, including [summarized thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#summarized-thinking), use the native Claude API.

207207 

208208<CodeGroup exclude="shell">

209209 ```python Python

get-api-key Changed · +1 / -1 lines

from line 48

4848 

4949## API keys and the Admin API

5050 

51The [Admin API](https://platform.claude.com/docs/en/api/beta/organization) includes endpoints for managing your organization's API keys programmatically, such as [Retrieve API Key](https://platform.claude.com/docs/en/api/beta/organization/api_keys/retrieve) and [List API Keys](https://platform.claude.com/docs/en/api/beta/organization/api_keys/list). These endpoints are for organization admins automating key management. They accept an [Admin API key](https://platform.claude.com/docs/en/manage-claude/admin-api-keys), an OAuth token with the `org:admin` scope, or a personal or service account key that isn't scoped to a specific workspace; workspace keys don't work there. They never return a key's secret value, only a partially redacted hint.

51The [Admin API](https://platform.claude.com/docs/en/api/organization) includes endpoints for managing your organization's API keys programmatically, such as [Retrieve API Key](https://platform.claude.com/docs/en/api/organization/api_keys/retrieve) and [List API Keys](https://platform.claude.com/docs/en/api/organization/api_keys/list). These endpoints are for organization admins automating key management. They accept an [Admin API key](https://platform.claude.com/docs/en/manage-claude/admin-api-keys), an OAuth token with the `org:admin` scope, or a personal or service account key that isn't scoped to a specific workspace; workspace keys don't work there. They never return a key's secret value, only a partially redacted hint.

5252 

5353<Note>

5454 The Admin API can't recover a lost key or give you a key to call the Claude API with. To get a usable API key, create one in [Settings → API keys](https://platform.claude.com/settings/keys) in the Claude Console.

manage-claude/data-residency Changed · +1 / -1 lines

from line 223

223223 

224224### Model availability

225225 

226The `inference_geo` parameter is supported on Claude 4.6 and later models. Requests with `inference_geo` on Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, or earlier models return a 400 error.

226The `inference_geo` parameter is supported on Claude 4.6 and later models. Requests with `inference_geo` on Claude Opus 4.5, Claude Sonnet 4.5 (deprecated), Claude Haiku 4.5, or earlier models return a 400 error.

227227 

228228<Note>

229229 The `inference_geo` parameter is available on the Claude API (first-party) and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws). On Amazon Bedrock and Google Cloud, the inference region is determined by the endpoint URL or inference profile, so `inference_geo` is not applicable. On [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), `inference_geo` is likewise not applicable: deployments hosted on Azure can instead use the US Data Zone Standard deployment type, which keeps inference within the United States. The `inference_geo` parameter is also not available through the [OpenAI SDK compatibility endpoint](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk).

manage-claude/workload-identity-federation Changed · +1 / -1 lines

from line 79

7979 </Step>

8080</Steps>

8181 

82To manage these resources programmatically, see [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api) for the curl walkthrough, or see the [Service accounts API reference](https://platform.claude.com/docs/en/api/beta/organization/service_accounts), [Federation issuers API reference](https://platform.claude.com/docs/en/api/beta/organization/federation/issuers), and [Federation rules API reference](https://platform.claude.com/docs/en/api/beta/organization/federation/rules) for complete parameter details and response schemas.

82To manage these resources programmatically, see [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api) for the curl walkthrough, or see the [Service accounts API reference](https://platform.claude.com/docs/en/api/organization/service_accounts), [Federation issuers API reference](https://platform.claude.com/docs/en/api/organization/federation/issuers), and [Federation rules API reference](https://platform.claude.com/docs/en/api/organization/federation/rules) for complete parameter details and response schemas.

8383 

8484## Authenticate from your workload

8585 

managed-agents/quickstart Changed · +1 / -1 lines

from line 374

374374 </Step>

375375 

376376 <Step title="Create an environment">

377 An environment defines the sandbox where your agent runs. This one uses `limited` [networking](https://platform.claude.com/docs/en/managed-agents/environments#networking) with package managers allowed, so code running in the sandbox can reach public [package registries and code hosts](https://platform.claude.com/docs/en/managed-agents/environments#package-manager-hosts) and no other sites. Web search and web fetch run outside the sandbox and are not affected.

377 An environment defines the sandbox where your agent runs. This one uses `limited` [networking](https://platform.claude.com/docs/en/managed-agents/environments#networking) with package managers allowed, so code running in the sandbox can reach public [package registries and code hosts](https://platform.claude.com/docs/en/managed-agents/environments#package-manager-hosts). Web search and web fetch run outside the sandbox, and this quickstart does not need them. With `limited` networking, the [`allowed_hosts` list](https://platform.claude.com/docs/en/managed-agents/environments#networking) applies to them too. They return no pages or search results in this environment, because it lists no hosts. For your own agent, list the hosts it needs in `allowed_hosts`.

378378 

379379 <CodeGroup defaultLanguage="CLI">

380380 <CodeGroupItem>

models/fable-5-1/overview Changed · +1 / -1 lines

from line 97

9797 Model-specific prompting guidance for long-horizon and agentic work.

9898 </Card>

9999 

100 <Card title="Migrating to Claude Fable 5.1" icon="arrow-right" href="https://platform.claude.com/docs/en/models/fable-5-1/migration-guide">

100 <Card title="Claude Fable 5.1 migration guide" icon="arrow-right" href="https://platform.claude.com/docs/en/models/fable-5-1/migration-guide">

101101 What changes when you move from Claude Fable 5, Claude Opus 5, or Claude Opus 4.8.

102102 </Card>

103103 

models/fable-5-1/whats-new-fable-5-1 Changed · +1 / -1 lines

from line 65

6565 

6666### Change effort mid-conversation (beta)

6767 

68On Claude Fable 5.1 you can change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level mid-conversation without invalidating the prompt cache. Raise it for a hard step and lower it for routine ones. Per-message effort is in beta: include the `mid-conversation-output-config-2026-07-01` beta header. Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5 support it on the Claude API and Google Cloud.

68On Claude Fable 5.1 you can change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level mid-conversation without invalidating the prompt cache. Raise it for a hard step and lower it for routine ones. Per-message effort is in beta: include the `mid-conversation-output-config-2026-07-01` beta header. Claude Fable 5.1 and Claude Mythos 5.1 support it on the Claude API, Google Cloud, and Amazon Bedrock. To use it with Claude Fable 5.1 through the Amazon Bedrock [InvokeModel API](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), send that value in the `anthropic_beta` array of the request body instead. For the other models that support it and the platforms for each, see [Change effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#changing-effort-mid-conversation).

6969 

7070<CodeGroup>

7171 ```bash cURL

models/haiku-4-5/migration-guide Changed · +2 / -2 lines

from line 1

11---

2title: Migrating to Claude Haiku 4.5

2title: Claude Haiku 4.5 migration guide

33url: https://platform.claude.com/docs/en/models/haiku-4-5/migration-guide

4description: "Migrate to Claude Haiku 4.5 from earlier Haiku models: model IDs, breaking changes, and a migration checklist."

4description: Switch to Claude Haiku 4.5 from earlier Haiku models with this migration guide. The guidance to enable Claude Haiku 4.5 includes model IDs, breaking changes, and a migration checklist.

55---

66 

77<Note>

models/opus-5-5/migration-guide Changed · +2 / -2 lines

from line 1

11---

2title: Migrating to Claude Opus 5.5

2title: Claude Opus 5.5 migration guide

33url: https://platform.claude.com/docs/en/models/opus-5-5/migration-guide

4description: "Migrate to Claude Opus 5.5 from earlier Opus models or Claude Sonnet 5: request settings that return errors, thinking blocks in every response, and a checklist for each starting model."

4description: Switch to Claude Opus 5.5 from earlier Opus models or Claude Sonnet 5 with this migration guide. The guidance to enable Claude Opus 5.5 includes request settings that return errors, thinking blocks in every response, and a checklist for each starting model.

55---

66 

77<Note>

models/overview Changed · +1 / -1 lines

from line 79

7979 

8080* **Performance:** Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. See [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) for general and model-specific prompting guidance.

8181* **Engaging responses:** Claude models are ideal for applications that require rich, human-like interactions. If you prefer more concise responses, adjust your prompts to guide the model toward the desired output length. Refer to the [prompt engineering guides](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering) for details.

82* **Output quality:** When migrating from a previous model generation, you may notice larger improvements in overall performance. If you're on Claude Opus 5 or earlier, see [Migrating to Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide).

82* **Output quality:** When migrating from a previous model generation, you may notice larger improvements in overall performance. If you're on Claude Opus 5 or earlier, see the [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide).

8383 

8484## Get started with Claude

8585 

models/sonnet-5-5/migration-guide Changed · +2 / -2 lines

from line 1

11---

2title: Migrating to Claude Sonnet 5.5

2title: Claude Sonnet 5.5 migration guide

33url: https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide

4description: "Move code to Claude Sonnet 5.5 from Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Sonnet 4, Claude 3.7 Sonnet, or Claude Haiku 4.5: settings that return errors, thinking changes, and a checklist for each starting model."

4description: Switch to Claude Sonnet 5.5 from earlier Sonnet models or Claude Haiku 4.5 with this migration guide. The guidance to enable Claude Sonnet 5.5 includes settings that return errors, thinking changes, and a checklist for each starting model.

55---

66 

77This guide lists the code changes for moving to Claude Sonnet 5.5 from Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Sonnet 4, Claude 3.7 Sonnet, or Claude Haiku 4.5. Read the first two sections, then read down to the section for your current model. The [migration checklist](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migration-checklist) lists every change by starting model.