Home Docs Claude Developer Platform

One capture · api

One read of Claude Developer Platformapi-20261023T040744Z

34 pages moved out of 812 read.

Pages moved 34 significant first

Pages read 812 in this capture

Captured 23 Oct 2026 04:07 UTC

Corpus hash ce804a19d6fd corpus-hash

What this read moved

1-25 of 34, page 1 of 2

This capture is too large to show at once. Changes 1-25 of 34 are below, significant first; the rest are on the following screens.

about-claude/pricing Changed · +64 / -64 lines

from line 12

1212

1313The following table shows pricing for all Claude models:

1414

16| :----------------------------------------------------------------------------------------------------------------------------------- | :-------------------- | :-------------- | :-------------- | :----------------------- | :--------------------- |

16| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------- | :-------------- | :-------------- | :----------------------- | :--------------------- |

3838

3939*1 Cache hits and refreshes on Claude Fable 5.1 and Claude Mythos 5.1 are priced at 0.025x the base input price.*

4040

from line 185

185185

186186The Batch API allows asynchronous processing of large volumes of requests with a 50 percent discount on both input and output tokens.

187187

188| Model | Batch input | Batch output |

189| :----------------------------------------------------------------------------------------------------------------------------------- | :----------- | :------------ |

190| Claude Fable 5.1 | $5 / MTok | $25 / MTok |

191| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

192| Claude Fable 5 | $5 / MTok | $25 / MTok |

193| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

194| Claude Opus 5.5 | $2 / MTok | $10 / MTok |

195| Claude Opus 5 | $2.50 / MTok | $12.50 / MTok |

196| Claude Opus 4.8 | $2.50 / MTok | $12.50 / MTok |

197| Claude Opus 4.7 | $2.50 / MTok | $12.50 / MTok |

198| Claude Opus 4.6 | $2.50 / MTok | $12.50 / MTok |

199| Claude Opus 4.5 | $2.50 / MTok | $12.50 / MTok |

200| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

201| Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

202| Claude Sonnet 5.5 | $1 / MTok | $5 / MTok |

203| Claude Sonnet 5 | $1 / MTok | $5 / MTok |

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

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

206| 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 |

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

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

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

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

188| Model | Batch input | Batch output |

189| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------- | :------------ |

190| Claude Fable 5.1 | $5 / MTok | $25 / MTok |

191| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

192| Claude Fable 5 | $5 / MTok | $25 / MTok |

193| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

194| Claude Opus 5.5 | $2 / MTok | $10 / MTok |

195| Claude Opus 5 | $2.50 / MTok | $12.50 / MTok |

196| Claude Opus 4.8 | $2.50 / MTok | $12.50 / MTok |

197| Claude Opus 4.7 | $2.50 / MTok | $12.50 / MTok |

198| Claude Opus 4.6 | $2.50 / MTok | $12.50 / MTok |

199| Claude Opus 4.5 | $2.50 / MTok | $12.50 / MTok |

200| Claude Opus 4.1 ([retired, except on Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

201| Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

202| Claude Sonnet 5.5 | $1 / MTok | $5 / MTok |

203| Claude Sonnet 5 | $1 / MTok | $5 / MTok |

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

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

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

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

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

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

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

211211

212212* **MTok:** Million tokens. $5 / MTok is $5 for every million tokens.

213213* **Limited access:** Available only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). To request access, apply to the program that covers your use case.

from line 239

239239

240240When you use `tools`, the API also automatically includes a special system prompt for the model that enables tool use. The number of tool use tokens required for each model is listed in the following table (excluding the additional tokens listed earlier). Note that the table assumes at least 1 tool is provided. If no `tools` are provided, then a tool choice of `none` uses 0 additional system prompt tokens.

241241

242| Model | Tool use system prompt tokens: auto, none | Tool use system prompt tokens: any, tool |

243| :----------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------- | :--------------------------------------- |

244| Claude Opus 5.5 | 286 tokens | |

245| Claude Opus 5 | 286 tokens | 406 tokens |

246| Claude Opus 4.8 | 290 tokens | 410 tokens |

247| Claude Opus 4.7 | 675 tokens | 804 tokens |

248| Claude Opus 4.6 | 497 tokens | 589 tokens |

249| Claude Opus 4.5 | 496 tokens | 588 tokens |

250| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 313 tokens | 315 tokens |

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

252| Claude Sonnet 5.5 | 286 tokens | |

253| Claude Sonnet 5 | 354 tokens | 474 tokens |

254| Claude Sonnet 4.6 | 497 tokens | 589 tokens |

255| Claude Sonnet 4.5 | 496 tokens | 588 tokens |

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

257| Claude Haiku 5.5 | 286 tokens | 406 tokens |

258| Claude Haiku 4.5 | 496 tokens | 588 tokens |

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

242| Model | Tool use system prompt tokens: auto, none | Tool use system prompt tokens: any, tool |

243| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------- | :--------------------------------------- |

244| Claude Opus 5.5 | 286 tokens | |

245| Claude Opus 5 | 286 tokens | 406 tokens |

246| Claude Opus 4.8 | 290 tokens | 410 tokens |

247| Claude Opus 4.7 | 675 tokens | 804 tokens |

248| Claude Opus 4.6 | 497 tokens | 589 tokens |

249| Claude Opus 4.5 | 496 tokens | 588 tokens |

250| Claude Opus 4.1 ([retired, except on Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 313 tokens | 315 tokens |

251| Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 313 tokens | 315 tokens |

252| Claude Sonnet 5.5 | 286 tokens | |

253| Claude Sonnet 5 | 354 tokens | 474 tokens |

254| Claude Sonnet 4.6 | 497 tokens | 589 tokens |

255| Claude Sonnet 4.5 | 496 tokens | 588 tokens |

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

257| Claude Haiku 5.5 | 286 tokens | 406 tokens |

258| Claude Haiku 4.5 | 496 tokens | 588 tokens |

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

260260

261261* **auto, none:** The count when tool\_choice is auto or none.

262262* **any, tool:** The count when tool\_choice is any or tool.

about-claude/use-case-guides/legal-summarization Changed · +6 / -6 lines

from line 831

831831 ```

832832</CodeGroup>

833833

834This code implements a `summarize_document` (typescript, go, java: `summarizeDocument`; php: `$summarizeDocument`; csharp: `SummarizeDocument`) function that uses Claude to summarize the contents of a sublease agreement. The function accepts a text string and a list of details to extract as inputs. In this example, the code calls the function with the `document_text` (typescript, go, java, csharp: `documentText`; php: `$documentText`) and `details_to_extract` (typescript, go, java, csharp: `detailsToExtract`; php: `$detailsToExtract`) variables that were defined in the previous code snippets.

834This code implements a `summarize_document()` (typescript, go, java: `summarizeDocument()`; php: `$summarizeDocument()`; csharp: `SummarizeDocument()`) function that uses Claude to summarize the contents of a sublease agreement. The function accepts a text string and a list of details to extract as inputs. In this example, the code calls the function with the `document_text` (typescript, go, java, csharp: `documentText`; php: `$documentText`) and `details_to_extract` (typescript, go, java, csharp: `detailsToExtract`; php: `$detailsToExtract`) variables that were defined in the previous code snippets.

835835

836836Within the function, a prompt is generated for Claude, including the document to be summarized, the details to extract, and specific instructions for summarizing the document. The prompt instructs Claude to respond with a summary of each detail to extract nested within XML headers.

837837

from line 1323

13231323 ```

13241324</CodeGroup>

13251325

1326The `summarize_long_document` (typescript, go, java: `summarizeLongDocument`; php: `$summarizeLongDocument`; csharp: `SummarizeLongDocument`) function builds upon the earlier `summarize_document` (typescript, go, java: `summarizeDocument`; php: `$summarizeDocument`; csharp: `SummarizeDocument`) function by splitting the document into smaller chunks and summarizing each chunk individually.

1326The `summarize_long_document()` (typescript, go, java: `summarizeLongDocument()`; php: `$summarizeLongDocument()`; csharp: `SummarizeLongDocument()`) function builds upon the earlier `summarize_document()` (typescript, go, java: `summarizeDocument()`; php: `$summarizeDocument()`; csharp: `SummarizeDocument()`) function by splitting the document into smaller chunks and summarizing each chunk individually.

13271327

1328The code achieves this by applying the `summarize_document` (typescript, go, java: `summarizeDocument`; php: `$summarizeDocument`; csharp: `SummarizeDocument`) function to each chunk of 20,000 characters within the original document. The individual summaries are then combined, and a final summary is created from these chunk summaries.

1328The code achieves this by applying the `summarize_document()` (typescript, go, java: `summarizeDocument()`; php: `$summarizeDocument()`; csharp: `SummarizeDocument()`) function to each chunk of 20,000 characters within the original document. The individual summaries are then combined, and a final summary is created from these chunk summaries.

13291329

1330Note that the `summarize_long_document` (typescript, go, java: `summarizeLongDocument`; php: `$summarizeLongDocument`; csharp: `SummarizeLongDocument`) function isn't strictly necessary for the example PDF, as the entire document fits within Claude's context window. However, it becomes essential for documents exceeding Claude's context window or when summarizing multiple related documents together. Regardless, this meta-summarization technique often captures additional important details in the final summary that were missed in the earlier single-summary approach.

1330Note that the `summarize_long_document()` (typescript, go, java: `summarizeLongDocument()`; php: `$summarizeLongDocument()`; csharp: `SummarizeLongDocument()`) function isn't strictly necessary for the example PDF, as the entire document fits within Claude's context window. However, it becomes essential for documents exceeding Claude's context window or when summarizing multiple related documents together. Regardless, this meta-summarization technique often captures additional important details in the final summary that were missed in the earlier single-summary approach.

13311331

13321332### Use summary indexed documents to explore a large collection of documents

13331333

agents-and-tools/tool-use/browser-use-sdk Changed · +5 / -5 lines

from line 702

702702 ```

703703</CodeGroup>

704704

705A request hook like this one doesn't see WebSocket handshakes, service-worker requests, or redirect hops. Block service workers. Check WebSocket handshakes and redirect hops with a hook that sees them. The example policy refuses `ws://` and `wss://` URLs, so change `ws://` to `http://` and `wss://` to `https://` before you pass a WebSocket URL to `is_allowed` (typescript: `isAllowed`).

706706

707707### Put egress policy on the container

708708

from line 770

770770

771771Return `True` (typescript: `true`) to run the call, or `False` (typescript: `false`) to refuse it. When your callable asks a person, show them the member, the page's URL, and the call's input. First, escape every character outside printable ASCII in the URL and the input, because both can carry text from the page.

772772

773This example asks about the two gated members through your own `ask_user` (typescript: `askUser`) function, and approves the rest:

773This example asks about the two gated members through your own `ask_user()` (typescript: `askUser()`) function, and approves the rest:

774774

775775<CodeGroup exclude="shell:cURL, shell:CLI, csharp, go, java, php, ruby">

776776 ```python Python

from line 920

920920

921921### Write a desktop driver

922922

923This driver implements five of the 17 tools listed under [Available actions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#available-actions). A tool you don't implement is sent to the API as disabled, as [Implement a driver](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk#implement-a-driver) explains. In the example, `display` stands for your own wrapper around whatever controls the desktop, such as a VNC client or `xdotool`, and `ask_user` (typescript: `askUser`) stands for your own function that asks a person.

923This driver implements five of the 17 tools listed under [Available actions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#available-actions). A tool you don't implement is sent to the API as disabled, as [Implement a driver](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk#implement-a-driver) explains. In the example, `display` stands for your own wrapper around whatever controls the desktop, such as a VNC client or `xdotool`, and `ask_user()` (typescript: `askUser()`) stands for your own function that asks a person.

924924

925925<CodeGroup exclude="shell:cURL, shell:CLI, csharp, go, java, php, ruby">

926926 ```python Python

from line 1157

11571157 ```

11581158</CodeGroup>

11591159

1160Call `to_display` (typescript: `toDisplay`) on each `coordinate` and `start_coordinate` before you act on it, and `to_screenshot` (typescript: `toScreenshot`) on the position that `cursor_position` reports. A click or scroll with no `coordinate` acts at the cursor, so it has nothing to convert. Scale a `zoom` `region` by the same factor. A `zoom` image doesn't change this: the next points Claude sends are still pixel positions in the full screenshot.

1160Call `to_display()` (typescript: `toDisplay()`) on each `coordinate` and `start_coordinate` before you act on it, and `to_screenshot()` (typescript: `toScreenshot()`) on the position that `cursor_position` reports. A click or scroll with no `coordinate` acts at the cursor, so it has nothing to convert. Scale a `zoom` `region` by the same factor. A `zoom` image doesn't change this: the next points Claude sends are still pixel positions in the full screenshot.

11611161

11621162The SDK never reads or resizes an image. The API rejects an image over the model's limits, which ends the run. Scale each screenshot and `zoom` image in the driver. See [Size screenshots to fit image limits](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#handle-coordinate-scaling-for-higher-resolutions). On a long run, one request can hold more than 20 images, and the API then holds each one to a stricter limit. See [Manage screenshot history](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#manage-screenshot-history).

11631163

from line 1193

11931193

11941194The SDK applies step 2 through the callable you pass. The other steps are up to your driver and your deployment. The precautions under [Security considerations for the computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#security-considerations) apply as well.

11951195

1196The following `confirm` asks a person before any keyboard input, through your own `ask_user` (typescript: `askUser`) function, and approves every other call. `context.member` (typescript: `ctx.member`) is the tool's name. To have a person approve clicks too, set `ASK_FIRST` to `KEYBOARD | CLICKS` (typescript: `new Set([...KEYBOARD, ...CLICKS])`).

1196The following `confirm` asks a person before any keyboard input, through your own `ask_user()` (typescript: `askUser()`) function, and approves every other call. `context.member` (typescript: `ctx.member`) is the tool's name. To have a person approve clicks too, set `ASK_FIRST` to `KEYBOARD | CLICKS` (typescript: `new Set([...KEYBOARD, ...CLICKS])`).

11971197

11981198<CodeGroup exclude="shell:cURL, shell:CLI, csharp, go, java, php, ruby">

11991199 ```python Python

agents-and-tools/tool-use/overview Changed · +18 / -18 lines

from line 762

762762

763763When you use `tools`, the API also automatically includes a special system prompt for the model that enables tool use. The number of tool use tokens required for each model is listed in the following table (excluding the additional tokens listed earlier). Note that the table assumes at least 1 tool is provided. If no `tools` are provided, then a tool choice of `none` uses 0 additional system prompt tokens.

764764

765| Model | Tool use system prompt tokens: auto, none | Tool use system prompt tokens: any, tool |

766| :----------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------- | :--------------------------------------- |

767| Claude Opus 5.5 | 286 tokens | |

768| Claude Opus 5 | 286 tokens | 406 tokens |

769| Claude Opus 4.8 | 290 tokens | 410 tokens |

770| Claude Opus 4.7 | 675 tokens | 804 tokens |

771| Claude Opus 4.6 | 497 tokens | 589 tokens |

772| Claude Opus 4.5 | 496 tokens | 588 tokens |

773| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 313 tokens | 315 tokens |

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

775| Claude Sonnet 5.5 | 286 tokens | |

776| Claude Sonnet 5 | 354 tokens | 474 tokens |

777| Claude Sonnet 4.6 | 497 tokens | 589 tokens |

778| Claude Sonnet 4.5 | 496 tokens | 588 tokens |

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

780| Claude Haiku 5.5 | 286 tokens | 406 tokens |

781| Claude Haiku 4.5 | 496 tokens | 588 tokens |

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

765| Model | Tool use system prompt tokens: auto, none | Tool use system prompt tokens: any, tool |

766| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------- | :--------------------------------------- |

767| Claude Opus 5.5 | 286 tokens | |

768| Claude Opus 5 | 286 tokens | 406 tokens |

769| Claude Opus 4.8 | 290 tokens | 410 tokens |

770| Claude Opus 4.7 | 675 tokens | 804 tokens |

771| Claude Opus 4.6 | 497 tokens | 589 tokens |

772| Claude Opus 4.5 | 496 tokens | 588 tokens |

773| Claude Opus 4.1 ([retired, except on Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 313 tokens | 315 tokens |

774| Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | 313 tokens | 315 tokens |

775| Claude Sonnet 5.5 | 286 tokens | |

776| Claude Sonnet 5 | 354 tokens | 474 tokens |

777| Claude Sonnet 4.6 | 497 tokens | 589 tokens |

778| Claude Sonnet 4.5 | 496 tokens | 588 tokens |

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

780| Claude Haiku 5.5 | 286 tokens | 406 tokens |

781| Claude Haiku 4.5 | 496 tokens | 588 tokens |

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

783783

784784* **auto, none:** The count when tool\_choice is auto or none.

785785* **any, tool:** The count when tool\_choice is any or tool.

build-with-claude/batch-processing Changed · +23 / -23 lines

from line 82

8282

8383The Batches API offers significant cost savings. All usage is charged at 50 percent of the standard API prices.

8484

85| Model | Batch input | Batch output |

86| :----------------------------------------------------------------------------------------------------------------------------------- | :----------- | :------------ |

87| Claude Fable 5.1 | $5 / MTok | $25 / MTok |

88| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

89| Claude Fable 5 | $5 / MTok | $25 / MTok |

90| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

91| Claude Opus 5.5 | $2 / MTok | $10 / MTok |

92| Claude Opus 5 | $2.50 / MTok | $12.50 / MTok |

93| Claude Opus 4.8 | $2.50 / MTok | $12.50 / MTok |

94| Claude Opus 4.7 | $2.50 / MTok | $12.50 / MTok |

95| Claude Opus 4.6 | $2.50 / MTok | $12.50 / MTok |

96| Claude Opus 4.5 | $2.50 / MTok | $12.50 / MTok |

97| Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

98| Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

99| Claude Sonnet 5.5 | $1 / MTok | $5 / MTok |

100| Claude Sonnet 5 | $1 / MTok | $5 / MTok |

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

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

103| 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 |

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

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

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

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

85| Model | Batch input | Batch output |

86| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------- | :------------ |

87| Claude Fable 5.1 | $5 / MTok | $25 / MTok |

88| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

89| Claude Fable 5 | $5 / MTok | $25 / MTok |

90| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |

91| Claude Opus 5.5 | $2 / MTok | $10 / MTok |

92| Claude Opus 5 | $2.50 / MTok | $12.50 / MTok |

93| Claude Opus 4.8 | $2.50 / MTok | $12.50 / MTok |

94| Claude Opus 4.7 | $2.50 / MTok | $12.50 / MTok |

95| Claude Opus 4.6 | $2.50 / MTok | $12.50 / MTok |

96| Claude Opus 4.5 | $2.50 / MTok | $12.50 / MTok |

97| Claude Opus 4.1 ([retired, except on Bedrock and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

98| Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $7.50 / MTok | $37.50 / MTok |

99| Claude Sonnet 5.5 | $1 / MTok | $5 / MTok |

100| Claude Sonnet 5 | $1 / MTok | $5 / MTok |

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

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

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

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

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

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

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

108108

109109* **MTok:** Million tokens. $5 / MTok is $5 for every million tokens.

110110* **Limited access:** Available only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). To request access, apply to the program that covers your use case.

build-with-claude/claude-models-on-google-cloud/overview Changed · +7 / -7 lines

from line 52

5252

5353The following table lists values that identify Claude Models on Google Cloud (Anthropic managed) and Claude Models on Google Cloud (Google managed). Find a value you already have. For example, look for the host in your request URLs or the SDK client in your code. The heading of that value's column is your offering.

5454

55| What to check | [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) |

56| ----------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

57| **Where your requests go** | `claude.googleapis.com` The URL includes your workspace ID. It ends in a Claude API path, such as `.../invoke/v1/messages`. | One of these Agent Platform hosts: `aiplatform.googleapis.com` `aiplatform.us.rep.googleapis.com` `aiplatform.eu.rep.googleapis.com` `{region}-aiplatform.googleapis.com` The URL path contains `.../publishers/anthropic/models/{model}`. It ends in `:rawPredict` or `:streamRawPredict`. |

58| **SDK client in your code** | `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`) In every SDK, the client name contains `GoogleCloud` (all lowercase in Go). | `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`) In every SDK, the client name contains `Vertex` (all lowercase in Go). |

59| **IAM roles that grant access** | `roles/claude.admin` `roles/claude.user` `roles/claude.viewer` | Agent Platform IAM roles |

60| **Management console** | The Claude Console, at `platform.claude.com` You open it from the Google Cloud console. | The Google Cloud console |

61| **Where each offering appears in the Google Cloud console** | The option labeled **Anthropic managed** See [Set up your account](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#set-up-your-account). | Claude models in [Model Garden](https://cloud.google.com/model-garden) |

56| ----------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

58| **SDK client in your code** | `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient()`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`) In every SDK, the client name contains `GoogleCloud` (all lowercase in Go). | `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth()`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`) In every SDK, the client name contains `Vertex` (all lowercase in Go). |

59| **IAM roles that grant access** | `roles/claude.admin` `roles/claude.user` `roles/claude.viewer` | Agent Platform IAM roles |

60| **Management console** | The Claude Console, at `platform.claude.com` You open it from the Google Cloud console. | The Google Cloud console |

6262

6363If you call `api.anthropic.com` with an API key, you use neither offering. To move those calls to Claude Models on Google Cloud (Anthropic managed), see [Moving from an existing Anthropic organization](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#moving-from-an-existing-anthropic-organization).

6464

build-with-claude/claude-platform-on-aws Changed · +17 / -17 lines

from line 22

2222

2323Both offerings let you use Claude through AWS, but they differ in architecture, API surface, and feature availability.

2424

25| Aspect | Claude Platform on AWS | [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | [Amazon Bedrock (Opus 4.6 and earlier)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) |

26| ---------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |

27| **Who operates the stack** | Anthropic | AWS | AWS |

28| **API surface** | Claude API (`/v1/{endpoint}`) | Messages API at `/anthropic/v1/messages` | Bedrock Converse / InvokeModel |

29| **Feature availability** | Typically same-day as Claude API (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-not-supported)) | Follows the Amazon Bedrock release schedule | Follows the Amazon Bedrock release schedule |

31| **Beta features** | Pass through with `anthropic-beta` headers (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-not-supported)) | The beta features Amazon Bedrock supports, through the `anthropic-beta` header | The beta features Amazon Bedrock supports, through the `anthropic_beta` field of the InvokeModel request body |

34| **Base URL** | `aws-external-anthropic.{region}.api.aws` | `bedrock-mantle.{region}.api.aws` | `bedrock-runtime.{region}.amazonaws.com` |

35| **SDK client** | `AnthropicAWS` (typescript: `AnthropicAws`; csharp: `AnthropicAwsClient`; go: `anthropicaws.NewClient`; java: `AwsBackend`; php: `Anthropic\Aws\Client`; ruby: `Anthropic::AWSClient`), in beta | `AnthropicBedrockMantle` | `AnthropicBedrock` / Bedrock SDK |

38| **Inference data processor** | Anthropic | AWS | AWS |

26| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |

27| **Who operates the stack** | Anthropic | AWS | AWS |

28| **API surface** | Claude API (`/v1/{endpoint}`) | Messages API at `/anthropic/v1/messages` | Bedrock Converse / InvokeModel |

34| **Base URL** | `aws-external-anthropic.{region}.api.aws` | `bedrock-mantle.{region}.api.aws` | `bedrock-runtime.{region}.amazonaws.com` |

35| **SDK client** | `AnthropicAWS` (typescript: `AnthropicAws`; csharp: `AnthropicAwsClient`; go: `anthropicaws.NewClient()`; java: `AwsBackend`; php: `Anthropic\Aws\Client`; ruby: `Anthropic::AWSClient`), in beta | `AnthropicBedrockMantle` | `AnthropicBedrock` / Bedrock SDK |

38| **Inference data processor** | Anthropic | AWS | AWS |

3939

4040If you need AWS-operated Claude, see [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock). Claude Platform on AWS uses a separate capacity pool from both the first-party Claude API and Amazon Bedrock. You can run workloads on more than one platform and fail over between them.

4141

from line 271

271271

272272### Region resolution

273273

274The client reads `AWS_REGION` from the environment if you don't set `aws_region` (typescript, php: `awsRegion`; go: `AWSRegion`; java: `.region()`; csharp: `AwsClientOptions.AwsRegion`), falling back to `AWS_DEFAULT_REGION` for compatibility with the standard AWS SDKs. Region is required and there is no default: `AnthropicAWS` (typescript: `AnthropicAws`; csharp: `AnthropicAwsClient`; go: `anthropicaws.NewClient`; java: `AwsBackend`; php: `Anthropic\Aws\Client`; ruby: `Anthropic::AWSClient`) raises an error if neither the constructor argument nor an environment variable is set.

274The client reads `AWS_REGION` from the environment if you don't set `aws_region` (typescript, php: `awsRegion`; go: `AWSRegion`; java: `.region()`; csharp: `AwsClientOptions.AwsRegion`), falling back to `AWS_DEFAULT_REGION` for compatibility with the standard AWS SDKs. Region is required and there is no default: `AnthropicAWS` (typescript: `AnthropicAws`; csharp: `AnthropicAwsClient`; go: `anthropicaws.NewClient()`; java: `AwsBackend`; php: `Anthropic\Aws\Client`; ruby: `Anthropic::AWSClient`) raises an error if neither the constructor argument nor an environment variable is set.

275275

276276## Install an SDK

277277

278Anthropic's [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) support Claude Platform on AWS. Your SDK provides `AnthropicAWS` (typescript: `AnthropicAws`; csharp: `AnthropicAwsClient`; go: `anthropicaws.NewClient`; java: `AwsBackend`; php: `Anthropic\Aws\Client`; ruby: `Anthropic::AWSClient`), which handles SigV4 signing, region-based base URL construction, and the `anthropic-workspace-id` header.

278Anthropic's [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) support Claude Platform on AWS. Your SDK provides `AnthropicAWS` (typescript: `AnthropicAws`; csharp: `AnthropicAwsClient`; go: `anthropicaws.NewClient()`; java: `AwsBackend`; php: `Anthropic\Aws\Client`; ruby: `Anthropic::AWSClient`), which handles SigV4 signing, region-based base URL construction, and the `anthropic-workspace-id` header.

279279

280280<Tabs>

281281 <Tab title="Python">

from line 1094

10941094| -------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

10951095| **Base URL** | `bedrock-mantle.{region}.api.aws` | `bedrock-runtime.{region}.amazonaws.com` | `aws-external-anthropic.{region}.api.aws` |

10961096| **API format** | Messages API at `/anthropic/v1/messages` | Bedrock Converse / InvokeModel | Claude API (`/v1/{endpoint}`) |

10981098| **SDK client** | `AnthropicBedrockMantle` | `AnthropicBedrock` / Bedrock SDK | Platform-specific client (see [Install an SDK](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#install-an-sdk)), in beta |

10991099| **SDK package** | `anthropic[bedrock]` (typescript: `@anthropic-ai/bedrock-sdk`; csharp: `Anthropic.Bedrock`; go: `github.com/anthropics/anthropic-sdk-go/v2/bedrock`; java: `com.anthropic:anthropic-java-bedrock`; php: `anthropic-ai/sdk`; ruby: `anthropic`) | `anthropic[bedrock]` (typescript: `@anthropic-ai/bedrock-sdk`; csharp: `Anthropic.Bedrock`; go: `github.com/anthropics/anthropic-sdk-go/v2/bedrock`; java: `com.anthropic:anthropic-java-bedrock`; php: `anthropic-ai/sdk`; ruby: `anthropic`), or the AWS SDK | `anthropic[aws]` (typescript: `@anthropic-ai/aws-sdk`; csharp: `Anthropic.Aws`; go: `github.com/anthropics/anthropic-sdk-go/v2/aws`; java: `com.anthropic:anthropic-java-aws`; php: `anthropic-ai/sdk`; ruby: `anthropic`) (see [Install an SDK](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#install-an-sdk)) |

build-with-claude/fast-mode Changed · +3 / -3 lines

from line 395

395395

396396### Automatic retries

397397

398The SDK automatically retries fast mode `429` errors up to 2 times by default (configurable with `max_retries` (typescript, java, php: `maxRetries`; csharp: `MaxRetries`; go: `option.WithMaxRetries`)), waiting for the delay in the `retry-after` header before each retry. Because fast mode uses continuous token replenishment, the `retry-after` delay is typically short and requests succeed once capacity is available.

398The SDK automatically retries fast mode `429` errors up to 2 times by default (configurable with `max_retries` (typescript, php: `maxRetries`; java: `.maxRetries()`; csharp: `MaxRetries`; go: `option.WithMaxRetries()`)), waiting for the delay in the `retry-after` header before each retry. Because fast mode uses continuous token replenishment, the `retry-after` delay is typically short and requests succeed once capacity is available.

399399

400400### Falling back to standard speed

401401

402If you'd prefer to fall back to standard speed rather than wait for fast mode capacity, catch the rate limit error and retry without `speed: "fast"`. Set `max_retries` (typescript, java, php: `maxRetries`; csharp: `MaxRetries`; go: `option.WithMaxRetries`) to `0` on the initial fast request to skip automatic retries and fail immediately on rate limit errors.

402If you'd prefer to fall back to standard speed rather than wait for fast mode capacity, catch the rate limit error and retry without `speed: "fast"`. Set `max_retries` (typescript, php: `maxRetries`; java: `.maxRetries()`; csharp: `MaxRetries`; go: `option.WithMaxRetries()`) to `0` on the initial fast request to skip automatic retries and fail immediately on rate limit errors.

403403

404404<Note>

405405 Falling back from fast to standard speed results in a [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) miss. Requests at different speeds do not share cached prefixes.

406406</Note>

407407

408Because setting `max_retries` (typescript, java, php: `maxRetries`; csharp: `MaxRetries`; go: `option.WithMaxRetries`) to `0` also disables retries for other transient errors (overloaded, internal server errors), the following examples reissue the original request with default retries for those cases.

408Because setting `max_retries` (typescript, php: `maxRetries`; java: `.maxRetries()`; csharp: `MaxRetries`; go: `option.WithMaxRetries()`) to `0` also disables retries for other transient errors (overloaded, internal server errors), the following examples reissue the original request with default retries for those cases.

409409

410410<CodeGroup exclude="shell:cURL, shell:CLI">

411411 ```python Python

build-with-claude/prompt-caching Changed · +23 / -23 lines

from line 228

228228

229229Prompt caching introduces a new pricing structure. The following table shows the price per million tokens for each supported model:

230230

232| :----------------------------------------------------------------------------------------------------------------------------------- | :---------------- | :-------------- | :-------------- | :----------------------- | :------------ |

232| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------- | :-------------- | :-------------- | :----------------------- | :------------ |

254254

255255*1 Cache hits and refreshes on Claude Fable 5.1 and Claude Mythos 5.1 are priced at 0.025x the base input price.*

256256

manage-claude/wif-providers/azure Changed · +4 / -4 lines

from line 141

141141

142142### Acquire and use the token

143143

144At runtime your workload fetches its Entra token, exchanges it at `POST /v1/oauth/token`, and uses the returned bearer token to call Claude. The Claude SDK handles the exchange and refresh loop when you supply `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider`; java: `IdentityTokenConfig`), as shown in the following examples. Except in Java (see the comment in that example), that option takes a token provider, and the SDK calls it again for each refresh. The cURL tab shows the raw flow.

144At runtime your workload fetches its Entra token, exchanges it at `POST /v1/oauth/token`, and uses the returned bearer token to call Claude. The Claude SDK handles the exchange and refresh loop when you supply `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider()`; java: `IdentityTokenConfig`), as shown in the following examples. Except in Java (see the comment in that example), that option takes a token provider, and the SDK calls it again for each refresh. The cURL tab shows the raw flow.

145145

146146The samples fetch the managed identity token from the platform's token endpoint: IMDS on VMs and VM Scale Sets, or the `IDENTITY_ENDPOINT` service on App Service, Functions, and Container Apps. Replace `<APP_ID>` in the `api://<APP_ID>` resource value with the audience app registration's client ID from [Register the token audience](https://platform.claude.com/docs/en/manage-claude/wif-providers/azure#register-the-token-audience).

147147

148148<Tip>

149 If your workload already uses the Azure Identity client library, get the Entra token from it (`DefaultAzureCredential` with the scope `api://<APP_ID>/.default`) instead of calling the token endpoints directly. Supply it to `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider`; java: `IdentityTokenConfig`) the way the examples do. The library selects the correct endpoint on every Azure platform, including AKS with Entra Workload Identity.

149 If your workload already uses the Azure Identity client library, get the Entra token from it (`DefaultAzureCredential` with the scope `api://<APP_ID>/.default`) instead of calling the token endpoints directly. Supply it to `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider()`; java: `IdentityTokenConfig`) the way the examples do. The library selects the correct endpoint on every Azure platform, including AKS with Entra Workload Identity.

150150</Tip>

151151

152152<CodeGroup>

from line 789

789789

790790### Acquire and use the token

791791

792At runtime the pod performs the two-hop exchange: it sends the Kubernetes-projected token (the file at `AZURE_FEDERATED_TOKEN_FILE`) to Entra's token endpoint as a federated `client_credentials` assertion, then exchanges the resulting Entra access token at `POST /v1/oauth/token`. The Claude SDK handles the second exchange and the refresh loop when you supply `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider`; java: `IdentityTokenConfig`), as shown in the following examples. Except in Java (see the comment in that example), that option takes your Entra fetch as a token provider, and the SDK calls it again for each refresh. The cURL tab shows the raw flow.

792At runtime the pod performs the two-hop exchange: it sends the Kubernetes-projected token (the file at `AZURE_FEDERATED_TOKEN_FILE`) to Entra's token endpoint as a federated `client_credentials` assertion, then exchanges the resulting Entra access token at `POST /v1/oauth/token`. The Claude SDK handles the second exchange and the refresh loop when you supply `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider()`; java: `IdentityTokenConfig`), as shown in the following examples. Except in Java (see the comment in that example), that option takes your Entra fetch as a token provider, and the SDK calls it again for each refresh. The cURL tab shows the raw flow.

793793

794794Two different client IDs appear in the samples. `<APP_ID>` is the audience app registration's client ID from [Register the token audience](https://platform.claude.com/docs/en/manage-claude/wif-providers/azure#register-the-token-audience); the scope `api://<APP_ID>/.default` asks Entra for a token addressed to that audience. `$AZURE_CLIENT_ID` is the managed identity's client ID, injected by the webhook, and identifies the caller. Do not substitute one for the other.

795795

796796<Tip>

797 If your workload already uses the Azure Identity client library, get the Entra token from it (`DefaultAzureCredential` with the scope `api://<APP_ID>/.default`) instead of performing the two-hop exchange yourself. Supply it to `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider`; java: `IdentityTokenConfig`) the way the examples do. The library reads the same `AZURE_FEDERATED_TOKEN_FILE`, `AZURE_CLIENT_ID`, and `AZURE_TENANT_ID` environment variables and handles the Entra exchange.

797 If your workload already uses the Azure Identity client library, get the Entra token from it (`DefaultAzureCredential` with the scope `api://<APP_ID>/.default`) instead of performing the two-hop exchange yourself. Supply it to `identity_token_provider` (typescript: `identityTokenProvider`; php: `identityProvider`; csharp: `IdentityTokenProvider`; go: `option.WithFederationTokenProvider()`; java: `IdentityTokenConfig`) the way the examples do. The library reads the same `AZURE_FEDERATED_TOKEN_FILE`, `AZURE_CLIENT_ID`, and `AZURE_TENANT_ID` environment variables and handles the Entra exchange.

798798</Tip>

799799

800800<CodeGroup>

models/overview Changed · +20 / -19 lines

from line 24

2424

2525If you're unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still fall short. All current models support text and image input, text output, multilingual capabilities, vision, and tool use. Each model's page lists the platforms it's available on.

2626

28| :------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :---------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------- |

29| Description | For demanding reasoning and long-horizon agentic work | For long-running agentic coding and knowledge work | The best combination of speed and intelligence | For high-volume, latency-sensitive tasks such as classification, extraction, and routing |

30| Model page | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) |

38| Reliable knowledge cutoff | Jun 2026 | Jun 2026 | Jun 2026 | Jun 2026 |

39| Training data cutoff | Jun 2026 | Jun 2026 | Jun 2026 | Jun 2026 |

28| :------------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :---------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------- |

38| Reliable knowledge cutoff | Jun 2026 | Jun 2026 | Jun 2026 | Jun 2026 |

39| Training data cutoff | Jun 2026 | Jun 2026 | Jun 2026 | Jun 2026 |

4647

4748* **Comparative latency:** Relative to the current lineup. Actual latency depends on prompt length, output length, and thinking effort.

4849* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for cache writes, long-context, and per-platform pricing.

release-notes/overview Changed · +9 / -9 lines

from line 58

5858### October 7, 2026

5959

6060* We've lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching).

61* We've launched **Claude Haiku 5.5** (`claude-haiku-5-5`), our most capable model tuned for high-volume and latency-sensitive work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort). It's available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5).

61* We've launched **Claude Haiku 5.5** (`claude-haiku-5-5`), our most capable model tuned for high-volume and latency-sensitive work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort). It's available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5).

6262* Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (`budget_tokens`), the sampling parameters `temperature`, `top_p`, and `top_k`, and assistant message prefill can each return a 400 error. `computer_20250124` also returns a 400 error: use the `computer_toolset_20260801` toolset on the Claude API and Google Cloud, or `computer_20251124` on Amazon Bedrock. A request that sends thinking blocks back after a change to `system`, `tools`, or earlier turns can also return a 400 error. Adaptive thinking is on by default, so a response can begin with `thinking` blocks, and their text is omitted unless you set `thinking.display` to `"summarized"`. The same text also counts as more tokens. See the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide) for each change. For model-specific prompting patterns, see [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5).

6363* The Python and TypeScript SDKs now include classes, in beta, for the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) and the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool). You subclass one and write one method per tool against your own browser or desktop automation. The SDK runs the tool loop, the URL and file policies you set for the browser, and your approval callback. See [Browser and computer use with the SDK toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk).

6464* Claude Max and Team plans now include monthly API credits. To learn how to claim them, see [API credits for Max and Team plans](https://platform.claude.com/docs/en/about-claude/api-credits-for-subscribers).

from line 86

8686

8787### September 28, 2026

8888

89* We've launched **Claude Sonnet 5.5** (`claude-sonnet-5-5`). It's available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). For its context window, output limits, and prices, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview).

89* We've launched **Claude Sonnet 5.5** (`claude-sonnet-5-5`). It's available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). For its context window, output limits, and prices, see the [Claude Sonnet 5.5 model page](https://platform.claude.com/docs/en/models/sonnet-5-5/overview).

9090* Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways. To turn off up-front thinking, send `thinking: {"type": "between_tools"}` instead of `"disabled"`, at `high` effort or below. Forced tool use (`tool_choice` types `any` and `tool`) returns a 400 error. Thinking blocks are tied to the model and the conversation. On the Claude API and Google Cloud, the earlier `computer_20251124` computer use tool isn't accepted. The advisor tool rejects Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors. See [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5) for each change and the [migration guide](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide) for before-and-after requests. For model-specific prompting patterns, see [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).

9191* Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model sees it, and the request succeeds. Blocks from earlier models aren't affected. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).

9292

from line 102

102102

103103### September 22, 2026

104104

105* We've launched **Claude Opus 5.5** (`claude-opus-5-5`), a model for long-running agentic coding and knowledge work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $4 / $20 USD per MTok (Claude Opus 5 is $5 / $25). Claude Opus 5.5 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5) for capabilities, API changes, and migration guidance.

105* We've launched **Claude Opus 5.5** (`claude-opus-5-5`), a model for long-running agentic coding and knowledge work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $4 / $20 USD per MTok (Claude Opus 5 is $5 / $25). Claude Opus 5.5 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5) for capabilities, API changes, and migration guidance.

106106* On Claude Opus 5.5, thinking can't be disabled: `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}` return a 400 error. Omit the `thinking` field and control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort). `tool_choice` types `any` and `tool` also return a 400 error, as on Claude Fable 5.1; use `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use). On the Claude API and Google Cloud, [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) on this model requires the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool returns a 400 error; on Amazon Bedrock, `computer_20251124` keeps working. See the [migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5).

107107* [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) (research preview) is available for Claude Opus 5.5 on the Claude API.

108108* Tools can now be defined inside a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), in beta on the Claude API with the `inline-tools-2026-09-15` beta header. A `tool_addition` block can carry the tool's full definition (`tool: {"type": "tool_definition", "definition": {...}}`), so you can add a tool, change its schema, or move a server tool to a newer version without editing `tools` or invalidating the prompt cache. The same header covers adding and removing tools by reference. With the MCP connector's `mcp-client-2026-09-15` beta header as well, the definition can be an MCP toolset, and a response records each server's fetched tool list in an `mcp_tool_listing` block, which pins that list when you send it back.

from line 129

129129### September 3, 2026

130130

131131* Version 1.30.0 of the `ant` CLI adds `ant apply`, which creates and updates agents, environments, skills, memory stores, and deployments from files in your repository. Describe each resource in a file, run `ant apply`, and approve the plan it prints. Commit the `claude-lock.json` lockfile it writes so that later runs, on your machine or in CI, update the same resources instead of creating new ones. See [Manage resources as code with ant apply](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply).

132* [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) changes, in beta, are also available on [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) for Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5, with the same `mid-conversation-output-config-2026-07-01` beta header.

132* [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) changes, in beta, are also available on [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) for Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5, with the same `mid-conversation-output-config-2026-07-01` beta header.

133133

134134### September 1, 2026

135135

136* We've launched **Claude Fable 5.1** (`claude-fable-5-1`), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside **Claude Mythos 5.1** (`claude-mythos-5-1`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 per MTok. Claude Fable 5.1 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) for capabilities, API changes, and migration guidance.

136* We've launched **Claude Fable 5.1** (`claude-fable-5-1`), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside **Claude Mythos 5.1** (`claude-mythos-5-1`) for Project Glasswing participants. Both models support a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, 128k max output tokens, and always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), at $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 per MTok. Claude Fable 5.1 is available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) for capabilities, API changes, and migration guidance.

137137* Prompt cache reads on Claude Fable 5.1 and Claude Mythos 5.1 cost $0.25 USD per million tokens: 0.025x the base input price, compared with 0.1x on other models. Cache writes are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching).

138138* On Claude Fable 5.1 and Claude Mythos 5.1, `tool_choice` types `any` and `tool` aren't supported and return a 400 error. `auto` and `none` are unchanged. To guarantee schema-conformant tool inputs, use [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs).

139139* Thinking blocks produced by Claude Fable 5.1 and Claude Mythos 5.1 are preserved only for the model that produced them or a newer one: earlier models can't read them, and the API drops one replayed to an earlier model. Claude Fable 5.1 accepts thinking blocks from Claude Opus 5, Claude Fable 5, Claude Mythos 5, and earlier Claude models. On Claude Fable 5.1, the API also [checks that nothing before a block has changed](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation): for new accounts created on or after August 31, 2026, replaying one after the `system` prompt, `tools`, or an earlier message changed returns a 400 error. With the `thinking-binding-controls-2026-08-01` beta header, dropped blocks are reported in an `input_transformations` response field, and `thinking.block_binding.prefix_mismatch_behavior` chooses between rejecting and dropping blocks whose history changed. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking).

from line 159

159159### August 20, 2026

160160

161161* We've released **v1.0 of the [Python SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/python)**. The SDK's HTTP layer moves from `httpx` to [httpx2](https://httpx2.pydantic.dev), a maintained, API-compatible fork: build custom `http_client`, `Timeout`, and transport objects from `httpx2` (the `DefaultHttpxClient` helpers are unchanged), and call `httpx2.alias_httpx()` at startup if you rely on tracing or mocking libraries that patch `httpx`. v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the `temperature`, `top_p`, and `top_k` parameters on Messages methods, and the tool runner's client-side `compaction_control`. On the async client, `.with_raw_response` results now need `await response.parse()`, and `AnthropicBedrock` now raises an error when no AWS region is configured instead of defaulting to `us-east-1`. See the [v1 migration guide](https://github.com/anthropics/anthropic-sdk-python/blob/main/MIGRATION.md) for every change with before-and-after snippets.

162* The [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 now available on [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8. Requests use the same `tools` entries as on the Claude API.

162* The [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 now available on [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8. Requests use the same `tools` entries as on the Claude API.

163163

164164### August 19, 2026

165165

from line 208

208208

209209### July 24, 2026

210210

211* We've launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It's available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for new features, behavior changes, and migration guidance, and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.

211* We've launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It's available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview) for new features, behavior changes, and migration guidance, and the [models overview](https://platform.claude.com/docs/en/models/overview) for complete specs.

212212* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview).

213213* [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) is the primary control for steering Claude Opus 5: the model supports the full ladder (`low`, `medium`, `high`, `xhigh`, `max`), with `max` for capability-critical work.

214214* Mid-conversation tool changes are now in beta on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5: add or remove tools between turns of a conversation while preserving the prompt cache. Include the `mid-conversation-tool-changes-2026-07-01` beta header in your requests.

from line 230

230230

231231### July 15, 2026

232232

233* [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available on Claude Fable 5, Claude Mythos 5, and Claude Opus 4.8, on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai). No beta header is required. This corrects earlier availability notes.

233* [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available on Claude Fable 5, Claude Mythos 5, and Claude Opus 4.8, on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). No beta header is required. This corrects earlier availability notes.

234234

235235### July 14, 2026

236236

from line 586

586586### August 26, 2025

587587

588588* We've increased rate limits on the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) for Claude Sonnet 4 on the Claude API.

589* The 1M token context window is now available on Vertex AI. For more information, see [Claude on Vertex AI](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai).

589* The 1M token context window is now available on Vertex AI. For more information, see [Claude on Vertex AI](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed).

590590

591591### August 19, 2025

592592

about-claude/use-case-guides/ticket-routing Changed · +2 / -2 lines

from line 1014

10141014This code:

10151015

10161016* Creates a client instance using your API key.

1017* Defines a `classify_support_request` (typescript, go, java, php: `classifySupportRequest`; csharp: `ClassifySupportRequest`) function that takes a `ticket_contents` (typescript, csharp, go, java: `ticketContents`; php: `$ticketContents`) string.

1017* Defines a `classify_support_request()` (typescript, go, java, php: `classifySupportRequest()`; csharp: `ClassifySupportRequest()`) function that takes a `ticket_contents` (typescript, csharp, go, java: `ticketContents`; php: `$ticketContents`) string.

10181018* Sends the `ticket_contents` (typescript, csharp, go, java: `ticketContents`; php: `$ticketContents`) to Claude for classification using the `classification_prompt` (typescript, csharp, go, java: `classificationPrompt`; php: `$classificationPrompt`).

10191019* Returns the model's reasoning and intent extracted from the response.

10201020

from line 1401

14011401

14021402Here is a breakdown of the edits:

14031403

1404* The `classify_support_request` (typescript, go, java, php: `classifySupportRequest`; csharp: `ClassifySupportRequest`) function now takes the `actual_intent` (typescript, csharp, go, java: `actualIntent`; php: `$actualIntent`) from the test cases and compares it against Claude’s intent classification to assess whether they match.

1404* The `classify_support_request()` (typescript, go, java, php: `classifySupportRequest()`; csharp: `ClassifySupportRequest()`) function now takes the `actual_intent` (typescript, csharp, go, java: `actualIntent`; php: `$actualIntent`) from the test cases and compares it against Claude’s intent classification to assess whether they match.

14051405* The function extracts usage statistics for the API call to calculate cost based on input and output tokens used.

14061406

14071407### Run your evaluation

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

from line 587

587587

588588The tool runner is an iterable that yields messages from Claude. On each iteration, the runner checks whether Claude requested a tool use. If so, it runs the tool and sends the result back to Claude automatically, then yields the next message from Claude to continue your loop.

589589

590You can end the loop at any iteration with a `break` statement. The runner loops until Claude returns a message without a tool use, or until it reaches `max_iterations` (csharp, java, php: `maxIterations`; go: `MaxIterations`) if you set it.

590You can end the loop at any iteration with a `break` statement. The runner loops until Claude returns a message without a tool use, or until it reaches `max_iterations` (csharp, php: `maxIterations`; java: `.maxIterations()`; go: `MaxIterations`) if you set it.

591591

592592If you don't need intermediate messages, you can get the final message directly:

593593

from line 814

814814

815815You take over by modifying the runner's messages from inside the loop body. The exact method depends on the SDK. See the per-language tabs that follow.

816816

817When you take over for an iteration, the runner does not append the assistant message or tool results from that turn. You become responsible for keeping the conversation valid: append the assistant message and a tool result yourself (if you want the turn to count), modify state conditionally so the loop can still exit when there are no tool calls, and pass `max_iterations` (csharp, java, php: `maxIterations`; go: `MaxIterations`) to bound the loop. The SDK supports `max_iterations` (csharp, java, php: `maxIterations`; go: `MaxIterations`) in all seven languages.

817When you take over for an iteration, the runner does not append the assistant message or tool results from that turn. You become responsible for keeping the conversation valid: append the assistant message and a tool result yourself (if you want the turn to count), modify state conditionally so the loop can still exit when there are no tool calls, and pass `max_iterations` (csharp, php: `maxIterations`; java: `.maxIterations()`; go: `MaxIterations`) to bound the loop. The SDK supports `max_iterations` (csharp, php: `maxIterations`; java: `.maxIterations()`; go: `MaxIterations`) in all seven languages.

818818

819819<Tabs exclude="shell">

820820 <Tab title="Python">

api/errors Changed · +2 / -2 lines

from line 36

3636 In rare cases, if your organization has a sharp increase in usage, you might see 429 errors because of acceleration limits on the API. To avoid hitting acceleration limits, increase your traffic gradually and maintain consistent usage patterns.

3737 </Warning>

3838

39The official SDK automatically retries transient failures (such as connection errors, rate limits, and 5xx server errors) with exponential backoff, twice by default, honoring the `retry-after` header when present. The SDK client accepts `max_retries` (typescript, java, php: `maxRetries`; csharp: `MaxRetries`; go: `option.WithMaxRetries`) to configure or disable this behavior.

39The official SDK automatically retries transient failures (such as connection errors, rate limits, and 5xx server errors) with exponential backoff, twice by default, honoring the `retry-after` header when present. The SDK client accepts `max_retries` (typescript, php: `maxRetries`; java: `.maxRetries()`; csharp: `MaxRetries`; go: `option.WithMaxRetries()`) to configure or disable this behavior.

4040

4141When receiving a [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) response over server-sent events (SSE), an error can occur after the API returns a 200 response. In that case, error handling doesn't follow these standard mechanisms. See [Error events](https://platform.claude.com/docs/en/build-with-claude/streaming#error-events) for the shape of mid-stream errors.

4242

from line 82

8282

8383On [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), responses include two request IDs: the AWS request ID (`x-amzn-requestid`, primary, indexed in CloudTrail) and the Anthropic request ID (`request-id`, secondary). Use the AWS request ID for CloudTrail lookups and the Anthropic request ID for Anthropic support tickets.

8484

85The Python and TypeScript SDKs expose the request ID as a `_request_id` property on top-level response objects. The C#, Go, Java, and PHP SDKs expose it through their raw-response accessors, and the Ruby SDK through [middleware](https://platform.claude.com/docs/en/cli-sdks-libraries/middleware). In every SDK except Ruby, use `with_raw_response` (typescript: `.withResponse()`; java: `.withRawResponse()`; csharp: `WithRawResponse`; go: `option.WithResponseInto`; php: `->raw`) to read any other [response header](https://platform.claude.com/docs/en/api/overview#response-headers), such as `anthropic-organization-id` and [`anthropic-workspace-id`](https://platform.claude.com/docs/en/manage-claude/workspaces#identify-the-workspace-behind-an-api-response). In Ruby, use the same middleware. On Claude Platform on AWS, use the raw-response accessor to read the AWS request ID (`x-amzn-requestid`) as well:

85The Python and TypeScript SDKs expose the request ID as a `_request_id` property on top-level response objects. The C#, Go, Java, and PHP SDKs expose it through their raw-response accessors, and the Ruby SDK through [middleware](https://platform.claude.com/docs/en/cli-sdks-libraries/middleware). In every SDK except Ruby, use `with_raw_response` (typescript: `.withResponse()`; java: `.withRawResponse()`; csharp: `WithRawResponse`; go: `option.WithResponseInto()`; php: `->raw`) to read any other [response header](https://platform.claude.com/docs/en/api/overview#response-headers), such as `anthropic-organization-id` and [`anthropic-workspace-id`](https://platform.claude.com/docs/en/manage-claude/workspaces#identify-the-workspace-behind-an-api-response). In Ruby, use the same middleware. On Claude Platform on AWS, use the raw-response accessor to read the AWS request ID (`x-amzn-requestid`) as well:

8686

8787<CodeGroup>

8888 ```bash cURL

api/overview Changed · +1 / -1 lines

from line 92

9292

9393| Platform | Provider | Documentation |

9494| ------------------------------------------------- | ------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |

95| Agent Platform | Google Cloud | [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) |

95| Claude Models on Google Cloud (Google managed) | Google Cloud | [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) |

9696| Amazon Bedrock | AWS | [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) |

9797| Claude Platform on AWS | AWS (Anthropic-operated) | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |

9898| Claude Models on Google Cloud (Anthropic managed) | Google Cloud (Anthropic-operated) | [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |

api/versioning Changed · +1 / -1 lines

from line 26

2626

2727 * [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21) shows how to upgrade.

2828

29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai). On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available for Claude 4.7 and later models. For other models on Bedrock, see the [migration guide for API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available for Claude 4.7 and later models. For other models on Bedrock, see the [migration guide for API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

3030

3131 * Messages API:

3232

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

from line 325

325325</Tabs>

326326

327327<Tip>

328 You can also create the standard client with `Anthropic` (go: `anthropic.NewClient()`; java: `AnthropicOkHttpClient.builder()`; csharp: `AnthropicClient`; php: `Anthropic\Client`; ruby: `Anthropic::Client`): set `base_url` (typescript: `baseURL`; go: `option.WithBaseURL()`; java: `.baseUrl()`; csharp: `BaseUrl`; php: `baseUrl`) to `https://bedrock-mantle.{region}.api.aws/anthropic` and pass your bearer token as `api_key` (typescript, php: `apiKey`; go: `option.WithAPIKey()`; java: `.apiKey()`; csharp: `ApiKey`). This path supports bearer-token authentication only. SigV4 signing requires `AnthropicBedrockMantle` (csharp: `AnthropicBedrockMantleClient`; go: `bedrock.NewMantleClient`; java: `BedrockMantleBackend`; php: `MantleClient`; ruby: `Anthropic::BedrockMantleClient`).

328 You can also create the standard client with `Anthropic` (go: `anthropic.NewClient()`; java: `AnthropicOkHttpClient.builder()`; csharp: `AnthropicClient`; php: `Anthropic\Client`; ruby: `Anthropic::Client`): set `base_url` (typescript: `baseURL`; go: `option.WithBaseURL()`; java: `.baseUrl()`; csharp: `BaseUrl`; php: `baseUrl`) to `https://bedrock-mantle.{region}.api.aws/anthropic` and pass your bearer token as `api_key` (typescript, php: `apiKey`; go: `option.WithAPIKey()`; java: `.apiKey()`; csharp: `ApiKey`). This path supports bearer-token authentication only. SigV4 signing requires `AnthropicBedrockMantle` (csharp: `AnthropicBedrockMantleClient`; go: `bedrock.NewMantleClient()`; java: `BedrockMantleBackend`; php: `MantleClient`; ruby: `Anthropic::BedrockMantleClient`).

329329</Tip>

330330

331331## Supported models

build-with-claude/claude-models-on-google-cloud/anthropic-managed Changed · +2 / -2 lines

from line 140

140140

141141### Install an SDK

142142

143The [SDK client](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for Claude Models on Google Cloud (Anthropic managed) is `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`). The client resolves your Google credentials. It also builds the base URL from your project, location, and workspace ID.

143The [SDK client](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for Claude Models on Google Cloud (Anthropic managed) is `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient()`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`). The client resolves your Google credentials. It also builds the base URL from your project, location, and workspace ID.

144144

145145<Note>

146146 The SDK client for Claude Models on Google Cloud (Anthropic managed) is in beta.

from line 631

631631 </Step>

632632

633633 <Step title="Replace the import and the client">

634 Change the code that imports and creates your client. Use `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`) in place of `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`). In a cURL request, change the URL, the headers, and the body. Your current code creates a client for Claude Models on Google Cloud (Google managed). For example, the following code creates that client with the global endpoint:

634 Change the code that imports and creates your client. Use `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient()`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`) in place of `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth()`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`). In a cURL request, change the URL, the headers, and the body. Your current code creates a client for Claude Models on Google Cloud (Google managed). For example, the following code creates that client with the global endpoint:

635635

636636 <CodeGroup exclude="shell:CLI">

637637 ```bash cURL

build-with-claude/claude-models-on-google-cloud/google-managed Changed · +2 / -2 lines

from line 17

1717

1818### Install an SDK

1919

20Anthropic's [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) support Claude Models on Google Cloud (Google managed) through `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`). Install the package that provides it:

20Anthropic's [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) support Claude Models on Google Cloud (Google managed) through `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth()`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`). Install the package that provides it:

2121

2222<Tabs>

2323 <Tab title="Python">

from line 548

548548 </Step>

549549

550550 <Step title="Replace the import and the client">

551 Change the code that imports and creates your client. Use `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`) in place of `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`). A cURL request needs a new URL, new headers, and a new body. The following code creates the client for Claude Models on Google Cloud (Anthropic managed) that you use today:

551 Change the code that imports and creates your client. Use `AnthropicVertex` (csharp: `AnthropicVertexClient`; go: `vertex.WithGoogleAuth()`; java: `VertexBackend`; php: `Anthropic\Vertex\Client`; ruby: `Anthropic::VertexClient`) in place of `AnthropicGoogleCloud` (csharp: `AnthropicGoogleCloudClient`; go: `googlecloud.NewClient()`; java: `GoogleCloudBackend`; php: `Anthropic\GoogleCloud\Client`; ruby: `Anthropic::GoogleCloudClient`). A cURL request needs a new URL, new headers, and a new body. The following code creates the client for Claude Models on Google Cloud (Anthropic managed) that you use today:

552552

553553 <CodeGroup>

554554 ```bash cURL

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

from line 26

2626| **Deprecated** | Feature is still functional but no longer recommended. A migration path and removal timeline are provided. |

2727| **Retired** | Feature is no longer available. |

2828

29**Platform labels:** Claude API (Anthropic first-party) · [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) (AWS-operated) · [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) (Anthropic-operated on AWS) · [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) (Google-operated) · [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) (Anthropic-operated on Azure)

29**Platform labels:** Claude API (Anthropic first-party) · [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) (AWS-operated) · [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) (Anthropic-operated on AWS) · [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) (Google-operated) · [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) (Anthropic-operated on Azure)

3030

3131## Model capabilities

3232

build-with-claude/refusals-and-fallback Changed · +1 / -1 lines

from line 756

756756

757757### Setting it up

758758

759Pass `BetaRefusalFallbackMiddleware` (typescript: `betaRefusalFallbackMiddleware`; go: `betafallback.BetaRefusalFallbackMiddleware`; csharp: `BetaRefusalFallbackHandler`; java: `BetaRefusalFallbackInterceptor`; php: `RefusalFallbackMiddleware`) to the client constructor, and share one `BetaFallbackState` (go: `betafallback.BetaFallbackState`) instance across the requests of a conversation.

759Pass `BetaRefusalFallbackMiddleware` (typescript: `betaRefusalFallbackMiddleware()`; go: `betafallback.BetaRefusalFallbackMiddleware()`; csharp: `BetaRefusalFallbackHandler`; java: `BetaRefusalFallbackInterceptor`; php: `RefusalFallbackMiddleware`) to the client constructor, and share one `BetaFallbackState` (go: `betafallback.BetaFallbackState`) instance across the requests of a conversation.

760760

761761<CodeGroup exclude="shell">

762762 <CodeGroupItem language="cURL">

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

from line 423

423423

424424The C# SDK supports the following platforms through separate NuGet packages:

425425

426* **Agent Platform:** `Anthropic.Vertex`. See [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) for client setup.

426* **Claude Models on Google Cloud (Google managed):** `Anthropic.Vertex`. See [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) for client setup.

427427* **Bedrock:** `Anthropic.Bedrock`. Use `AnthropicBedrockMantleClient` for the Messages-API Bedrock endpoint, or `AnthropicBedrockClient` (`bedrock-runtime` path). `AnthropicBedrockMantleClient` takes an optional `MantleAwsClientOptions` config object; `AnthropicBedrockClient` accepts `AnthropicBedrockCredentialsHelper.FromEnv()` or explicit credentials.

428428* **Claude Platform on AWS:** `Anthropic.Aws`. Use `AnthropicAwsClient`; set `WorkspaceId` on the client or the `ANTHROPIC_AWS_WORKSPACE_ID` environment variable (see [Workspaces](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#workspaces)). Available in beta.

429429* **Foundry:** `Anthropic.Foundry`. Use `AnthropicFoundryClient` with `DefaultAnthropicFoundryCredentials.FromEnv()` or explicit credentials.

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

from line 636

636636

637637The Go SDK supports the following platforms:

638638

639* **Agent Platform:** `import "github.com/anthropics/anthropic-sdk-go/v2/vertex"`. Use `vertex.WithGoogleAuth(ctx, region, projectID)` or `vertex.WithCredentials(ctx, region, projectID, creds)`.

639* **Claude Models on Google Cloud (Google managed):** `import "github.com/anthropics/anthropic-sdk-go/v2/vertex"`. Use `vertex.WithGoogleAuth(ctx, region, projectID)` or `vertex.WithCredentials(ctx, region, projectID, creds)`.

640640* **Bedrock:** `import "github.com/anthropics/anthropic-sdk-go/v2/bedrock"`. Use `bedrock.NewMantleClient` for the Messages-API Bedrock endpoint (streams over SSE), or `bedrock.WithLoadDefaultConfig(ctx)` / `bedrock.WithConfig(cfg)` (`bedrock-runtime` path). Importing the `bedrock` package globally registers a decoder for `application/vnd.amazon.eventstream` with the SDK's streaming layer (through package `init()`). This applies whether you use the `bedrock-runtime` `WithConfig`/`WithLoadDefaultConfig` path or `NewMantleClient`.

641641* **Claude Platform on AWS:** `import anthropicaws "github.com/anthropics/anthropic-sdk-go/v2/aws"`. Use `anthropicaws.NewClient(ctx, cfg)` with an `anthropicaws.ClientConfig` value to construct a client; set `WorkspaceID` on the config or the `ANTHROPIC_AWS_WORKSPACE_ID` environment variable. The `anthropicaws` import alias avoids a name collision with `github.com/aws/aws-sdk-go-v2/aws` when both are imported. Available in beta.

642642* **Foundry:** `import "github.com/anthropics/anthropic-sdk-go/v2/foundry"`. Use `foundry.NewClient(cfg)` with a `foundry.ClientConfig` value to construct a client; set `APIKey` (or `AzureADTokenProvider` for Microsoft Entra ID) and `Resource` on the config, or the `ANTHROPIC_FOUNDRY_API_KEY` and `ANTHROPIC_FOUNDRY_RESOURCE` environment variables.

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

from line 1090

10901090

10911091The Java SDK supports the following platforms through separate dependencies that provide platform-specific `Backend` implementations:

10921092

1093* **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.

1093* **Claude Models on Google Cloud (Google managed):** `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.

10941094* **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).

10951095* **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.

10961096* **Foundry:** `com.anthropic:anthropic-java-foundry`: Use `FoundryBackend.fromEnv()` or `FoundryBackend.builder()`.