api-20261007T190728Z / page 3 of 4 / documentation capture

about-claude/model-deprecations Changed · +1 / -0 lines

from line 87

agents-and-tools/agent-skills/claude-api-skill Changed · +2 / -2 lines

from line 26

2626* **Streaming patterns:** Implementation details for building chat UIs and handling incremental display

2727* **Batch processing:** Offline batch processing at 50% cost

2828* **Prompt caching:** Prefix-stability design, breakpoint placement, and silent-invalidator audit

29* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), and [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide))

29* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide), and [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide))

3030* **Preserved thinking migration:** Finding, measuring, and fixing the history edits that invalidate `thinking` blocks, available through the `/claude-api preserved-thinking-migration` subcommand

3131* **Current model information:** Model IDs, context window sizes, and pricing

3232* **Common pitfalls:** Detailed guidance on avoiding frequent mistakes when integrating with the API

from line 129

129129

130130As it edits, the skill explains each change and its motivation inline. On completion, it produces a checklist of items that require manual verification (typically integration tests, length-control prompt tuning, and cost/rate-limit re-baselining).

131131

132For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Migrating to Claude Opus 5.5 from Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), [Migrating to Claude Sonnet 5.5 from Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), and [Claude Fable 5.1 and Claude Mythos 5.1 migration guide](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide).

132For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Migrating to Claude Opus 5.5 from Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), [Migrating to Claude Sonnet 5.5 from Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), [Claude Haiku 5.5 migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide), and [Claude Fable 5.1 and Claude Mythos 5.1 migration guide](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide).

133133

134134## Checking an integration for preserved thinking

135135

agents-and-tools/tool-use/code-execution-tool Changed · +3 / -0 lines

from line 20

2020 - claude-sonnet-5

2121 - claude-sonnet-4-6

2222 - claude-sonnet-4-5-20250929

23 - claude-haiku-5-5

2324 - claude-haiku-4-5-20251001

2425 supportedPlatforms:

2526 Claude API: ga

from line 58

5758The examples on this page use `code_execution_20250825`, which covers the Bash and file operations they demonstrate and behaves the same way on every supported model; use `code_execution_20260120` or later when you need programmatic tool calling or REPL state persistence. The current [web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) and [web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool) tools (`web_search_20260209`, `web_fetch_20260209`, and later) require `code_execution_20260120` or later as their code execution version.

5859

5960Older tool versions aren't guaranteed to stay compatible with newer models. When you adopt a new model, check [Tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#tool-versions) and [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compatibility), and prefer the newest tool version your integration supports.

61

62To check whether a model accepts the code execution tool before you send a request, read its `capabilities.server_tools.code_execution.supported` value from the Models API. Don't use the top-level `capabilities.code_execution` value for this. It reports whether code running in this tool can call your request's other tools, as in programmatic tool calling. [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api) describes both fields.

6063

6164<Note>

6265 If you're still using the legacy `code_execution_20250522` (Python only), see [Upgrade to latest tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#upgrade-to-latest-tool-version) to migrate from it.

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

from line 560

560560

561561| Model or setting | Restriction | What to use instead |

562562| --------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

563| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported and result in an error | `auto` or `none`. [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) itself doesn't block forced tool use (Claude Opus 5 supports it with thinking on); the models in the next row reject forced tool use regardless of thinking settings |

563| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported and result in an error | `auto` or `none`. [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) itself doesn't block forced tool use (Claude Opus 5 and Claude Haiku 5.5 support it with thinking on); the models in the next row reject forced tool use regardless of thinking settings |

564564| Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) | `any` and `tool` return a [400 error](https://platform.claude.com/docs/en/api/errors#forced-tool-use-not-supported) | `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) to guarantee schema-valid tool inputs, or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) when you need a response in a fixed JSON shape. Prompting still influences which tool `auto` picks. `none` is also supported |

565565

566566On models that support it, the highlighted lines are the only difference from a standard tool use request:

from line 856

856856This diagram illustrates how each option works:

857857

858858<Frame>

859 ![Diagram showing the four tool\_choice options: auto, any, tool, and none](https://platform.claude.com/docs/images/tool_choice.png)

859 ![Diagram of three tool\_choice options: auto (a tool or a plain response), any (one of the tools), and tool (the named tool)](https://platform.claude.com/docs/images/tool_choice.svg)

860860</Frame>

861861

862862Note that when you have `tool_choice` as `any` or `tool`, the API prefills the assistant message to force a tool to be used. This means that the models will not emit a natural language response or explanation before `tool_use` content blocks, even if explicitly asked to do so.

agents-and-tools/tool-use/overview Changed · +1 / -0 lines

from line 879

879879| Claude Sonnet 4.6 | 497 tokens | 589 tokens |

880880| Claude Sonnet 4.5 | 496 tokens | 588 tokens |

881881| Claude Sonnet 4 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 313 tokens | 315 tokens |

882| Claude Haiku 5.5 | 286 tokens | 406 tokens |

882883| Claude Haiku 4.5 | 496 tokens | 588 tokens |

883884| Claude Haiku 3.5 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 264 tokens | 355 tokens |

884885

agents-and-tools/tool-use/programmatic-tool-calling Changed · +2 / -1 lines

from line 20

2020 - claude-sonnet-5

2121 - claude-sonnet-4-6

2222 - claude-sonnet-4-5-20250929

23 - claude-haiku-5-5

2324 supportedPlatforms:

2425 Claude API: ga

2526 Claude Platform on AWS: ga

from line 42

4142 For a deeper look at the inference and context costs that programmatic tool calling addresses, see [Advanced tool use](https://www.anthropic.com/engineering/advanced-tool-use).

4243</Tip>

4344

44Programmatic tool calling requires the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) with tool version `code_execution_20260120` or later.

45Programmatic tool calling requires the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) with tool version `code_execution_20260120` or later. To check whether a model supports programmatic tool calling before you send a request, read its `capabilities.code_execution.supported` value from the Models API. [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api) describes the field.

4546

4647## Quick start

4748

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

from line 24

2424| [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) | `computer_toolset_20260801` `computer_20251124` `computer_20250124` | Client | None `computer-use-2025-11-24` `computer-use-2025-01-24` |

2626

27For model compatibility, see each tool's page. Supported models vary by tool and by tool version.

27For model compatibility, see each tool's page. Supported models vary by tool and by tool version. To check from your code whether a model accepts web search or code execution, see [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api).

2828

2929<Note>

3030 The tool search `type` values also accept undated aliases: `tool_search_tool_regex` and `tool_search_tool_bm25`. These resolve to the latest dated version.

agents-and-tools/tool-use/tool-search-tool Changed · +1 / -0 lines

from line 48

4848| Claude Opus 5.5 (claude-opus-5-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

4949| Claude Opus 5 (claude-opus-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

5050| Claude Sonnet 5.5 (claude-sonnet-5-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

51| Claude Haiku 5.5 (claude-haiku-5-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

5152| Claude Opus 4.8 (claude-opus-4-8) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

5253| Claude Opus 4.7 (claude-opus-4-7) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

5354| Claude Opus 4.6 (claude-opus-4-6) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |

agents-and-tools/tool-use/web-search-tool Changed · +2 / -0 lines

from line 28

2828

2929For model support, see the [Tool reference](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference).

3030

31To check whether a model accepts web search before you send a request, read its `capabilities.server_tools.web_search.supported` value from the Models API. [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api) describes the field.

32

3133## How web search works

3234

3335When you add the web search tool to your API request:

api/rate-limits Changed · +3 / -0 lines

from line 145

145145 | Claude Sonnet 5.5 | 1,000 | 2,000,000 | 400,000 |

146146 | Claude Sonnet 5 | 1,000 | 2,000,000 | 400,000 |

147147 | Claude Sonnet 4.x3 | 1,000 | 2,000,000 | 400,000 |

148 | Claude Haiku 5.5 | 1,000 | 2,000,000 | 400,000 |

148149 | Claude Haiku 4.5 | 1,000 | 2,000,000 | 400,000 |

149150 | Claude Haiku 3.5 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 1,000 | 100,0004 | 20,000 |

150151 </Tab>

from line 160

159160 | Claude Sonnet 5.5 | 5,000 | 5,000,000 | 1,000,000 |

160161 | Claude Sonnet 5 | 5,000 | 5,000,000 | 1,000,000 |

161162 | Claude Sonnet 4.x3 | 5,000 | 5,000,000 | 1,000,000 |

163 | Claude Haiku 5.5 | 5,000 | 5,000,000 | 1,000,000 |

162164 | Claude Haiku 4.5 | 5,000 | 5,000,000 | 1,000,000 |

163165 | Claude Haiku 3.5 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 2,000 | 200,0004 | 40,000 |

164166 </Tab>

from line 175

173175 | Claude Sonnet 5.5 | 10,000 | 10,000,000 | 2,000,000 |

174176 | Claude Sonnet 5 | 10,000 | 10,000,000 | 2,000,000 |

175177 | Claude Sonnet 4.x3 | 10,000 | 10,000,000 | 2,000,000 |

178 | Claude Haiku 5.5 | 10,000 | 10,000,000 | 2,000,000 |

176179 | Claude Haiku 4.5 | 10,000 | 10,000,000 | 2,000,000 |

177180 | Claude Haiku 3.5 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 4,000 | 400,0004 | 80,000 |

178181 </Tab>

api/service-tiers Changed · +1 / -1 lines

from line 227

227227

228228### Supported models

229229

230Priority Tier is supported on all available Claude models except Claude Fable 5.1, Claude Mythos 5.1, Claude Mythos 5, [Claude Mythos Preview](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Sonnet 5.

230Priority Tier is supported on all available Claude models except Claude Fable 5.1, Claude Haiku 5.5, Claude Mythos 5.1, Claude Mythos 5, [Claude Mythos Preview](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Sonnet 5.

231231

232232Check the [Models overview](https://platform.claude.com/docs/en/models/overview) for more details on available models.

233233

build-with-claude/batch-processing Changed · +3 / -1 lines

from line 100

100100| Claude Sonnet 4.6 | $1.50 / MTok | $7.50 / MTok |

101101| Claude Sonnet 4.5 | $1.50 / MTok | $7.50 / MTok |

102102| Claude Sonnet 4 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $1.50 / MTok | $7.50 / MTok |

103| Claude Haiku 5.5 (for prompts up to 100,000 tokens) | $0.05 / MTok | $0.25 / MTok |

104| Claude Haiku 5.5 (for prompts over 100,000 tokens) | $0.25 / MTok | $1.25 / MTok |

103105| Claude Haiku 4.5 | $0.50 / MTok | $2.50 / MTok |

104106| Claude Haiku 3.5 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $0.40 / MTok | $2 / MTok |

105107

from line 1572

15701572

15711573### Extended output (beta)

15721574

1573The `output-300k-2026-03-24` beta header raises the `max_tokens` cap to 300,000 for batch requests using 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, or Claude Sonnet 4.6. Include the header to generate outputs far longer than the standard 128k `max_tokens` limit in a single turn.

1575The `output-300k-2026-03-24` beta header raises the `max_tokens` cap to 300,000 for batch requests using 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, Claude Sonnet 4.6, or Claude Haiku 5.5. Include the header to generate outputs far longer than the standard 128k `max_tokens` limit in a single turn.

15741576

15751577<Note>

15761578 Extended output is available on the Message Batches API only, not the synchronous Messages API. It is supported on the Claude API and Claude Platform on AWS, and is not currently available on Amazon Bedrock, Google Cloud, or Microsoft Foundry.

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

from line 19

1919 - claude-sonnet-5-5

2020 - claude-sonnet-5

2121 - claude-sonnet-4-6

22 - claude-haiku-5-5

2223 supportedPlatforms:

2324 Claude API: beta

2425 Claude Platform on AWS: beta

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

from line 19

1919 - claude-sonnet-5-5

2020 - claude-sonnet-5

2121 - claude-sonnet-4-6

22 - claude-haiku-5-5

2223 supportedPlatforms:

2324 Claude API: beta

2425 Claude Platform on AWS: beta

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

from line 19

1919 - claude-sonnet-5-5

2020 - claude-sonnet-5

2121 - claude-sonnet-4-6

22 - claude-haiku-5-5

2223 supportedPlatforms:

2324 Claude API: beta

2425 Claude Platform on AWS: beta

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

from line 19

1919 - claude-sonnet-5-5

2020 - claude-sonnet-5

2121 - claude-sonnet-4-6

22 - claude-haiku-5-5

2223 supportedPlatforms:

2324 Claude API: beta

2425 Claude Platform on AWS: beta

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

from line 354

354354You need to migrate off `type: "enabled"` if:

355355

356356* You use Claude Opus 4.6 or Claude Sonnet 4.6, where `budget_tokens` is deprecated.

357* You use Claude 4.7 or a later model, such as Claude Opus 5.5, Claude Sonnet 5, Claude Sonnet 5.5, or Claude Fable 5.1, where `type: "enabled"` returns a 400 error.

357* You use Claude 4.7 or a later model, such as Claude Opus 5.5, Claude Sonnet 5, Claude Sonnet 5.5, Claude Fable 5.1, or Claude Haiku 5.5, where `type: "enabled"` returns a 400 error.

358358

359359The mapping is small: remove `budget_tokens`, set `thinking: {type: "adaptive"}`, and control reasoning depth with `output_config: {effort: ...}` instead of a token budget.

360360

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, or Claude Sonnet 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. 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/structured-outputs Changed · +1 / -0 lines

from line 23

2323 - claude-sonnet-4-6

2424 - claude-sonnet-4-5-20250929

2525 - claude-opus-4-5-20251101

26 - claude-haiku-5-5

2627 - claude-haiku-4-5-20251001

2728 supportedPlatforms:

2829 Claude API: ga

build-with-claude/task-budgets Changed · +2 / -0 lines

from line 15

1515 - claude-opus-4-8

1616 - claude-opus-4-7

1717 - claude-sonnet-5-5

18 - claude-haiku-5-5

1819---

1920

2021Task budgets let you tell Claude how many tokens it has for a full agentic loop, including thinking, tool calls, tool results, and output. The model sees a running countdown and uses it to prioritize work and finish gracefully as the budget is consumed.

from line 654

653654| Claude Mythos 5 | Beta (set `task-budgets-2026-03-13` header) |

654655| Claude Sonnet 5.5 | Beta (set `task-budgets-2026-03-13` header) |

655656| Claude Sonnet 5 | Not supported |

657| Claude Haiku 5.5 | Beta (set `task-budgets-2026-03-13` header) |

656658| Claude Opus 4.8 | Beta (set `task-budgets-2026-03-13` header) |

657659| Claude Opus 4.7 | Beta (set `task-budgets-2026-03-13` header) |

658660| Claude Opus 4.6 | Not supported |

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, and Claude Sonnet 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 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

claude_api_primer Changed · +3 / -1 lines

from line 16

1616Previous Opus model: Claude Opus 5: claude-opus-5

1717Smart model: Claude Sonnet 5.5: claude-sonnet-5-5

1818Previous Sonnet model: Claude Sonnet 5: claude-sonnet-5

19For fast, cost-effective tasks: Claude Haiku 4.5: claude-haiku-4-5-20251001

19For fast, cost-effective tasks: Claude Haiku 5.5: claude-haiku-5-5

20Previous Haiku model: Claude Haiku 4.5: claude-haiku-4-5-20251001

2021```

2122

2223## Calling the API

from line 247

246247

247248* Claude Opus 5.5 (`claude-opus-5-5`, adaptive thinking only, always on)

248249* Claude Sonnet 5.5 (`claude-sonnet-5-5`, adaptive thinking only, on by default)

250* Claude Haiku 5.5 (`claude-haiku-5-5`, adaptive thinking only, on by default)

249251* Claude Opus 5 (claude-opus-5, adaptive thinking only, on by default)

250252* Claude Sonnet 5 (`claude-sonnet-5`, adaptive thinking only, on by default)

251253* Claude Opus 4.8 (claude-opus-4-8, adaptive thinking only)

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

from line 32

3232 For Linux environments, download the release binary directly.

3333

3434 ```bash

35 VERSION=1.38.0

35 VERSION=1.39.0

3636 OS=$(uname -s | tr '[:upper:]' '[:lower:]')

3737 case $(uname -m) in

3838 x86_64) ARCH=amd64 ;;

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

from line 15

1515<Tabs>

1616 <Tab title="Gradle">

1717 ```kotlin

18 implementation("com.anthropic:anthropic-java:2.68.0")

18 implementation("com.anthropic:anthropic-java:2.69.0")

1919 ```

2020 </Tab>

2121

from line 24

2424 <dependency>

2525 <groupId>com.anthropic</groupId>

2626 <artifactId>anthropic-java</artifactId>

27 <version>2.68.0</version>

27 <version>2.69.0</version>

2828 </dependency>

2929 ```

3030 </Tab>

cli-sdks-libraries/sdks/python Changed · +2 / -0 lines

from line 272

272272

273273On every iteration, an API request is made. If the response includes a call to one of the given tools, the tool is automatically called, and the result is returned directly to the model in the next iteration.

274274

275To run the browser use tool or the computer use tool with this SDK, see [Browser and computer use with the SDK toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk).

276

275277## Message batches

276278

277279This SDK provides support for [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) under `client.messages.batches`.

One read of Claude Developer Platformapi-20261007T190728Z

What this read moved

about-claude/model-deprecations Changed · +1 / -0 lines

agents-and-tools/agent-skills/claude-api-skill Changed · +2 / -2 lines

agents-and-tools/tool-use/code-execution-tool Changed · +3 / -0 lines

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

agents-and-tools/tool-use/overview Changed · +1 / -0 lines

agents-and-tools/tool-use/programmatic-tool-calling Changed · +2 / -1 lines

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

agents-and-tools/tool-use/tool-search-tool Changed · +1 / -0 lines

agents-and-tools/tool-use/web-search-tool Changed · +2 / -0 lines

api/rate-limits Changed · +3 / -0 lines

api/service-tiers Changed · +1 / -1 lines

build-with-claude/batch-processing Changed · +3 / -1 lines

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

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

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

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

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

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

build-with-claude/structured-outputs Changed · +1 / -0 lines

build-with-claude/task-budgets Changed · +2 / -0 lines

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

claude_api_primer Changed · +3 / -1 lines

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

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

cli-sdks-libraries/sdks/python Changed · +2 / -0 lines