One read of Claude Developer Platformapi-20261103T020719Z
32 pages moved out of 846 read.
Pages moved
32
significant first
Pages read
846
in this capture
Captured
02:07 UTC
Corpus hash
97a7207641e2
corpus-hash
What this read moved
1-25 of 32, page 1 of 2This capture is too large to show at once. Changes 1-25 of 32 are below, significant first; the rest are on the following screens.
agents-and-tools/tool-use/browser-use-sdk Changed · +9 / -7 lines
from line 18
1818 - claude-opus-4-8
1919 supportedPlatforms:
2020 Claude API: beta
21 Claude Platform on AWS: beta
22 Amazon Bedrock: beta
2123 Claude Models on Google Cloud (Google managed): beta
24 Microsoft Foundry: beta
2225---
2326
2427With the browser and computer toolsets in the Python and TypeScript SDKs, you can build an agent that works in a web browser or on a desktop. It can use applications with no programmatic interface. Through the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), Claude navigates, reads, and interacts with webpages. Through the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), Claude receives screenshots of a desktop and uses the mouse and keyboard.
from line 85
8285
8386Pass the driver instance itself as the `tools` entry. The runner never closes the toolset, so one instance can serve several runs. Close it when you’re done.
8487
88The example’s client calls the Claude API. For another platform listed under [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk#availability-feature-support), create that platform’s SDK client instead. Each platform’s page shows its client.
89
8590To write your own driver, see [Implement a driver](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk#implement-a-driver).
8691
8792## Partner integrations
from line 600
595600
596601The SDK applies steps 1, 4, and 5 through the policies and the callable you pass. Steps 2, 3, and 6 are up to your driver and your deployment. The precautions under [Security considerations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#security-considerations) apply as well.
597602
598<Note>
599 Anthropic’s prompt-injection classifiers, described under [Security considerations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#security-considerations), don’t currently run on browser toolset requests sent through Amazon Bedrock.
600</Note>
601
602603### Write a URL policy
603604
604605<Warning>
from line 1387
13861387
13871388* Availability: Available
13881389
1389| Status | Cloud platforms | Models |
1390| ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1391| Beta | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1390| Status | Cloud platforms | Models |
1391| ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1392| Beta | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1393| Beta | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
13921394
13931395#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
13941396
agents-and-tools/tool-use/browser-use-tool Changed · +8 / -5 lines
from line 21
2121 - claude-opus-4-8
2222 supportedPlatforms:
2323 Claude API: stable
24 Claude Platform on AWS: stable
25 Amazon Bedrock: stable
2426 Claude Models on Google Cloud (Google managed): stable
27 Microsoft Foundry: stable
2528---
2629
2730<Note>
from line 41
3841
3942## Quick start
4043
41The browser use tool is available on the Claude API and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed): add one entry of type `browser_toolset_20260801`, with no `name`, to the `tools` array of a [Messages API](https://platform.claude.com/docs/en/api/messages/create) request.
44To use the browser use tool, add one entry of type `browser_toolset_20260801`, with no `name`, to the `tools` array of a [Messages API](https://platform.claude.com/docs/en/api/messages/create) request. See [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#availability-feature-support) for the supported models and platforms.
4245
4346<CodeGroup>
4447 ```bash cURL
from line 1565
15621565
15631566## Limitations
15641567
1565* **Platform availability:** Browser use is available on the Claude API and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed).
15661568* **Whole-input streaming only:** When you stream, each member’s `input` arrives as one complete `input_json_delta` ([Client toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference#client-toolsets)).
15671569* **Element references are best-effort:** Highly dynamic pages (virtualized lists, canvas-rendered interfaces, pages that re-render on scroll) might not expose stable references, and Claude falls back to screenshots and coordinate clicks there.
15681570* **`read_console` and `read_network` depend on your browser automation:** They report only what it can capture, and only from the moment it attached to a tab.
from line 1617
16151617
16161618* Availability: Available
16171619
1618| Status | Cloud platforms | Models |
1619| --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1620| Available | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1620| Status | Cloud platforms | Models |
1621| --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1622| Available | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1623| Available | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
16211624
16221625#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
16231626
agents-and-tools/tool-use/computer-use-tool Changed · +17 / -21 lines
from line 27
2727 - claude-sonnet-4-5-20250929
2828 supportedPlatforms:
2929 Claude API: stable
30 Claude Platform on AWS: beta
31 Amazon Bedrock: beta
30 Claude Platform on AWS: stable
31 Amazon Bedrock: stable
3232 Amazon Bedrock (InvokeModel): beta
3333 Claude Models on Google Cloud (Google managed): stable
34 Microsoft Foundry: beta
34 Microsoft Foundry: stable
3535 details:
36 - On the Claude API and Claude Models on Google Cloud (Google managed), Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier `computer_20251124` and `computer_20250124` tool versions. To move an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). To move from `computer_20250124`, see [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) in the Claude Haiku 5.5 migration guide.
37 - On Amazon Bedrock, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 accept the earlier `computer_20251124` tool version as Claude Opus 5 and Claude Sonnet 5 do.
36 - Claude 5.5 and later models support computer use through the `computer_toolset_20260801` toolset. They return a 400 error for any computer use tool version they don't accept, such as `computer_20251124` on the Claude API. To move a `computer_20251124` integration to the toolset, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). To move from `computer_20250124`, see [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) in the Claude Haiku 5.5 migration guide.
3837 - Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 support computer use only through the earlier `computer_20251124` tool version, which requires a beta header; see [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
3938---
4039
from line 47
4847
4948For tasks that stay inside webpages, the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) is the closer fit: its member tools read and act on the page itself, and it doesn’t need a full desktop environment.
5049
51<Note>
52 Computer use is available on the Claude API and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) as the `computer_toolset_20260801` toolset; see [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support) for the supported models.
50See [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support) for the models and platforms that support the toolset. [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) lists each earlier version’s beta header and the models to use it with.
5351
54 Existing `computer_20251124` integrations keep working on the models listed for it under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions), and earlier tool versions remain available in beta for models and platforms that don’t support the toolset. See [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124) to upgrade, or [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) for the beta headers.
55</Note>
56
5752## Security considerations
5853
5954Computer use has unique risks distinct from standard API features. These risks are heightened when interacting with the internet.
from line 2115
21202115
21212116## Migrate from `computer_20251124`
21222117
2123Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) keep accepting it with its beta header, so an existing integration keeps working until you change it. Claude 5.5 and later models are the exception on the Claude API and Claude Models on Google Cloud (Google managed): there they accept only the toolset. Upgrade an integration before you move it to one of them. On Amazon Bedrock, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 accept `computer_20251124`. To upgrade, make the following changes together:
2118A `computer_20251124` integration works without changes on the models listed for that version under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions). Upgrade the integration before you move it to a model that doesn’t accept `computer_20251124`, such as a Claude 5.5 model on the Claude API.
21242119
2120To upgrade, make the following changes together:
2121
212521221. **Remove the beta header.** Drop `anthropic-beta: computer-use-2025-11-24` from your requests. With the SDK, remove `betas` (csharp, go: `Betas`; java: `.addBeta()`) and call the Messages API through the standard client rather than the beta namespace.
212621232. **Change the `tools` entry.** Set `type` to `computer_toolset_20260801` and delete `name`, `display_width_px`, `display_height_px`, `display_number`, and `enable_zoom`. The toolset rejects each of these fields.
212721243. **Choose whether to keep zoom enabled.** Zoom is enabled by default on the toolset, whereas `enable_zoom` defaults to `false`. If your environment doesn’t implement zoom, add `"configs": {"zoom": {"enabled": false}}` to keep the previous behavior; otherwise implement it (see [Available actions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#available-actions)).
from line 2175
21782175
21792176## Earlier tool versions
21802177
2181Two earlier versions of the computer use tool remain available in beta for existing integrations, for models that don’t support the toolset, and on platforms where the toolset isn’t currently available. On Claude Platform on AWS, Amazon Bedrock, and Microsoft Foundry, computer use is available only through these earlier versions. Each requires its [beta header](https://platform.claude.com/docs/en/api/beta-headers) on every request, and their parameters are documented in the [beta Messages API reference](https://platform.claude.com/docs/en/api/beta/messages/create). With the SDK, pass the header through `betas` (csharp, go: `Betas`; java: `.addBeta()`) and use the beta namespace; only the computer use tool needs the header, not the bash or text editor tools in the same request.
2178Two earlier versions of the computer use tool are available in beta. Each requires its [beta header](https://platform.claude.com/docs/en/api/beta-headers) on every request, and their parameters are documented in the [beta Messages API reference](https://platform.claude.com/docs/en/api/beta/messages/create). With the SDK, pass the header through `betas` (csharp, go: `Betas`; java: `.addBeta()`) and use the beta namespace; only the computer use tool needs the header, not the bash or text editor tools in the same request.
21822179
21832180| Tool version | Beta header | Use with | Parameters |
21842181| ------------------- | ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- |
2185| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5; on Amazon Bedrock, also Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
2182| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
21862183| `computer_20250124` | `computer-use-2025-01-24` | Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Haiku 4.5, 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)), 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)), and Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
21872184
2185On Amazon Bedrock, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 also accept the `computer_20251124` tool with the `computer-use-2025-11-24` beta header.
2186
21882187***
21892188
21902189## Limitations
from line 2266
22672266| Status | Cloud platforms | Models |
22682267| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
22692268| Available | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2269| Available | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
22702270| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview) |
2271| Beta | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2272| Beta | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | [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) |
22732271
22742272#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
22752273
from line 2279
22812279
22822280Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
22832281
2284| Header | Cloud platforms | Models |
2285| ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2286| `computer-use-2025-11-24` | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2287| `computer-use-2025-11-24` | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | [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) |
2288| `computer-use-2025-11-24` | All supported platforms | [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview) |
2289| `computer-use-2025-01-24` | All supported platforms | [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview) |
2282| Header | Models |
2283| ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2284| `computer-use-2025-11-24` | [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview) |
2285| `computer-use-2025-01-24` | [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview) |
22902286
22912287### Data handling
22922288
api/errors Changed · +4 / -2 lines
from line 530
530530
531531### Computer use tool version not supported
532532
533On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 support [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) only as the `computer_toolset_20260801` toolset. On those platforms, sending any of these models a `tools` entry of the earlier `computer_20251124` or `computer_20250124` type, with that tool’s beta header, returns a 400 `invalid_request_error`. The message names the rejected type, then lists the tool types the model does accept after `Did you mean one of`. For Claude Opus 5.5, it begins:
533Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 return a 400 error for any [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) tool version they don’t accept. On the Claude API, that includes `computer_20251124` with its beta header. They don’t accept `computer_20250124` on any platform. The Claude API’s `invalid_request_error` message names the rejected type and, after `Did you mean one of`, lists the tool types the model accepts. For Claude Opus 5.5, the message begins:
534534
535535```text wrap
536536'claude-opus-5-5' does not support tool types: computer_20251124.
537537```
538538
539The API returns the same message for any Anthropic-defined tool type that the requested model doesn’t support. Declare `{"type": "computer_toolset_20260801"}` without the beta header and update your agent loop as described in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). To move from `computer_20250124`, see [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) in the Claude Haiku 5.5 migration guide. Earlier models that support the toolset keep accepting `computer_20251124`, as do Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 on Amazon Bedrock.
539The Claude API returns the same message for any Anthropic-defined tool type that the requested model doesn’t support. Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 support computer use through the `computer_toolset_20260801` toolset. Declare `{"type": "computer_toolset_20260801"}` without the beta header and update your agent loop as described in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). To move from `computer_20250124`, see [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) in the Claude Haiku 5.5 migration guide.
540
541On Amazon Bedrock, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 also accept the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) lists the models to use with each earlier version.
540542
541543### Thinking block bound to a different conversation
542544
build-with-claude/cache-diagnostics Changed · +3 / -12 lines
from line 324
324324 IO.println("Comparison still pending.");
325325 } else {
326326 var reason = r2.diagnostics().get().cacheMissReason().get();
327 // CacheMissReason doesn't expose a typed .type() accessor; read it from the raw JSON.
328 @SuppressWarnings("unchecked")
329 var json = (Map<String, JsonValue>) reason._json().orElseThrow().asObject().orElseThrow();
330 IO.println("cache_miss_reason: " + json.get("type").asStringOrThrow());
327 IO.println("cache_miss_reason: " + reason.type().asString());
331328 }
332329 ```
333330
from line 629
632629 IO.println("Comparison still pending.");
633630 } else {
634631 var reason = diagnostics.get().cacheMissReason().get();
635 // CacheMissReason doesn't expose a typed .type() accessor; read it from the raw JSON.
636 @SuppressWarnings("unchecked")
637 var json = (Map<String, JsonValue>) reason._json().orElseThrow().asObject().orElseThrow();
638 IO.println("cache_miss_reason: " + json.get("type").asStringOrThrow());
632 IO.println("cache_miss_reason: " + reason.type().asString());
639633 }
640634 ```
641635
from line 897
903897
904898 if (r.diagnostics().isPresent() && r.diagnostics().get().cacheMissReason().isPresent()) {
905899 var reason = r.diagnostics().get().cacheMissReason().get();
906 // CacheMissReason doesn't expose a typed .type() accessor; read it from the raw JSON.
907 @SuppressWarnings("unchecked")
908 var json = (Map<String, JsonValue>) reason._json().orElseThrow().asObject().orElseThrow();
909 IO.println("Turn " + (turn + 1) + " cache_miss_reason: " + json.get("type").asStringOrThrow());
900 IO.println("Turn " + (turn + 1) + " cache_miss_reason: " + reason.type().asString());
910901 }
911902
912903 messages.add(r.toParam());
build-with-claude/claude-on-amazon-bedrock-legacy Changed · +15 / -1 lines
### Computer use and browser use toolsets on Bedrock
from line 745
745745* Claude Managed Agents
746746* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)
747747* Automatic prompt caching (the [top-level `cache_control` field](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching); use [explicit cache breakpoints](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#explicit-cache-breakpoints) instead)
748* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Amazon Bedrock; the beta computer use tool versions remain available)
748
749### Computer use and browser use toolsets on Bedrock
750
751The [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 are available through the InvokeModel API for these models:
752
753* Claude Fable 5.1
754* Claude Fable 5
755* Claude Opus 5.5
756* Claude Opus 5
757* Claude Opus 4.8
758* Claude Sonnet 5.5
759* Claude Sonnet 5
760* Claude Haiku 5.5
761
762To use one, add an entry of type `computer_toolset_20260801` or `browser_toolset_20260801` to the `tools` array. No beta header is required for either toolset.
749763
750764### PDF support on Bedrock
751765
cli-sdks-libraries/cli/using Changed · +7 / -6 lines
from line 148
148148ant files upload --file ./report.pdf
149149```
150150
151To inline a file’s contents into a string-valued field, prefix the path with `@`:
151To inline a file’s contents into a string-valued field of a stdin document, prefix the path with `@` and wrap it in quotes:
152152
153153```bash
154154ant beta:agents create \
155 --name "Researcher" --model '{id: claude-opus-5-5}' \
156 --system @./prompts/researcher.txt
155 --name "Researcher" --model '{id: claude-opus-5-5}' <<'YAML'
156system: "@./prompts/researcher.txt"
157YAML
157158```
158159
159Inside structured flag values, wrap the path in quotes. To send a PDF to the Messages API:
160Structured flag values work the same way. To send a PDF to the Messages API:
160161
161162```bash
162163ant messages create \
manage-claude/compliance-content-data Changed · +13 / -6 lines
from line 146
146146 "mime_type": "text/csv",
147147 "size_bytes": 2048,
148148 "md5": "89968669461d95416549937168269d6b"
149 },
150 {
151 "id": "claude_file_01Qm7RzKdTgWnYbVx3HcLpE5",
152 "filename": "requirements_tracker.xlsx",
153 "mime_type": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
154 "size_bytes": 18432,
155 "md5": "5ccf4e7dd3bdfa729883d6764631ac60"
149156 }
150157 ],
151158 "artifacts": [
from line 171
164171}
165172```
166173
167`files`, `generated_files`, and `artifacts` can each be `null` on a given message. `files` are the files and text attachments (for example, PDFs, images, spreadsheets, documents, and pasted text) the user attached to the message, as claude.ai stored them. `generated_files` are binary files the assistant created during the conversation through tool use (for example, PDFs, spreadsheets, or slide decks). `artifacts` are versioned documents (for example, code or markdown) the assistant generated or updated in its response; an artifact can be revised across multiple assistant turns in the same chat, and each revision appears as a new `version_id` under the same artifact `id`. Pass each entry’s `id` (or `version_id` for artifacts) to the matching content endpoint in [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-files-and-artifacts) to download it.
174`files`, `generated_files`, and `artifacts` can each be `null` on a given message. `files` are the files and text attachments (for example, PDFs, images, spreadsheets, documents, and pasted text) the user attached to the message, as claude.ai stored them. `generated_files` are binary files the assistant created during the conversation through tool use (for example, PDFs, spreadsheets, or slide decks). `artifacts` are versioned documents (for example, code or markdown) the assistant generated or updated in its response; an artifact can be revised across multiple assistant turns in the same chat, and each revision appears as a new `version_id` under the same artifact `id`. Pass each entry’s `id` (or `version_id` for artifacts) to the matching content endpoint in [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-files-and-artifacts) to download it. An `id` in `generated_files` starts with either `claude_gen_file_` or `claude_file_`. Choose the endpoint by the prefix, not by the array the entry came from.
168175
169176## Retrieve files and artifacts
170177
171Files and artifacts are downloaded by ID. Except for Claude Docs documents (see the end of this section), they aren’t listed independently. The IDs come from the chat messages endpoint in [Retrieve chats and messages](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-chats-and-messages) (the `files`, `generated_files`, and `artifacts` arrays on each message) or, for project-level uploads, from the [project attachments endpoint](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-projects-and-attachments).
178Files and artifacts are downloaded by ID. They aren’t listed independently, except for the artifacts returned by [List code artifacts](https://platform.claude.com/docs/en/api/compliance/apps/code/artifacts/list), such as Claude Docs documents (see the end of this section). All other IDs come from the chat messages endpoint in [Retrieve chats and messages](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-chats-and-messages) (the `files`, `generated_files`, and `artifacts` arrays on each message) or, for project-level uploads, from the [project attachments endpoint](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-projects-and-attachments).
172179
173Pick the endpoint that matches your ID type and the data you need. The same file content endpoint serves both chat files and project files.
180Pick the endpoint that matches your ID’s prefix and the data you need. The same file content endpoint serves chat files, project files, and the `generated_files` entries whose IDs start with `claude_file_`. The file endpoints and the generated-file endpoints each reject the other’s IDs with a 400 error; see [Invalid file ID](https://platform.claude.com/docs/en/manage-claude/compliance-errors#invalid-file-id).
174181
175182| You have | You want | Use this endpoint |
176183| ------------------------------ | --------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
from line 194
187194
188195The response carries these headers:
189196
190* `Content-Disposition: attachment; filename*=utf-8''<percent-encoded filename>` carries the original upload file name in RFC 5987 extended form. The extended form is used for every file name, not only non-ASCII ones.
197* `Content-Disposition: attachment; filename*=utf-8''<percent-encoded filename>` carries the file name in RFC 5987 extended form. The extended form is used for every file name, not only non-ASCII ones.
191198* `Content-Type` carries the MIME type recorded for the stored content, which for a document stored as extracted text can still name the original document format.
192199* `Content-MD5` carries the MD5 digest of the served bytes, base64-encoded as specified in RFC 1864.
193200* `Transfer-Encoding: chunked` is always set.
from line 207
200207 --output "dashboard_mockup_v1.pdf"
201208```
202209
203In curl, the `--remote-header-name` (`-J`) option, which normally saves a download under the `Content-Disposition` file name, does not read the `filename*` form, so name the saved file yourself with `--output`. In a script, take the name from the file’s `filename` field in the chat messages or [Get file metadata](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/retrieve) response, or decode `filename*`. Either way, it is the name the user gave the upload, so treat it as untrusted before using it as an output path:
210In curl, the `--remote-header-name` (`-J`) option, which normally saves a download under the `Content-Disposition` file name, does not read the `filename*` form, so name the saved file yourself with `--output`. In a script, take the name from the file’s `filename` field in the chat messages or [Get file metadata](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/retrieve) response, or decode `filename*`. Either way, treat it as untrusted before using it as an output path:
204211
205212* Keep only the base name.
206213* Allow only characters that are safe on your filesystem.
manage-claude/compliance-errors Changed · +16 / -0 lines
### Invalid file ID
from line 132
132132
133133For the first body, resend the unmodified `next_page` value from the previous response to the endpoint and session that issued it. For an expired cursor, restart without a `page` parameter; the new walk reflects the retention boundary in effect when it starts, so messages that aged out of the retention period in the meantime are no longer returned (see [Retrieve a local session transcript](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-a-local-session-transcript)).
134134
135### Invalid file ID
136
137**Type:** `invalid_request_error`
138
139```text wrap
140Invalid claude_gen_file_id format: 'claude_file_01Qm7RzKdTgWnYbVx3HcLpE5'
141```
142
143```text wrap
144Invalid claude_file_id format: 'claude_gen_file_01TbR8wAcCeFhJkLnPqStUvX'
145```
146
147**Cause:** The ID in the path is not in the form the endpoint accepts. The generated-file endpoints (`/v1/compliance/apps/chats/generated-files/*`) accept only `claude_gen_file_...` IDs and return the first body for any other value. The file endpoints (`/v1/compliance/apps/chats/files/*`) accept only `claude_file_...` IDs and return the second body. The `generated_files` array on a chat message can hold both kinds of ID.
148
149**Fix:** Choose the endpoint by the ID’s prefix, not by the array the ID came from; see [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-files-and-artifacts). If the prefix already matches the endpoint, the ID was truncated or altered; copy it again from the response that returned it.
150
135151### Transcript page too large
136152
137153**Type:** `invalid_request_error`
manage-claude/compliance-faq Changed · +3 / -3 lines
from line 72
7272 <Accordion title="Do sessions in Cowork, Claude Code, and other Claude apps and add-ins appear in the Compliance API?">
7373 Yes. Cowork sessions in Claude Desktop that run on users’ machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Science desktop app, Claude for Microsoft 365 sessions (in Excel, PowerPoint, Word, and Outlook), sessions in the Claude add-ins for Google Docs, Google Sheets, and Google Slides, and chats in the Claude in Chrome browser extension are captured while users are signed in with their Claude Enterprise account and are available through the [local session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions). Cowork sessions started on claude.ai web or mobile, which run in the cloud in Anthropic-managed environments, are available through the [remote session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-remote-sessions). Each family has a list endpoint that returns session metadata and a messages endpoint that returns the session transcript (user prompts, assistant responses, and tool calls and results). The local family adds a third endpoint that retrieves one session’s metadata. All of these endpoints use your existing Compliance Access Key with `read:compliance_user_data`; no new key or scope is needed.
7474
75 Local sessions are captured as their requests reach the Claude API, so nothing is installed on the device, and on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and [Claude Code cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web), which run on cloud infrastructure instead of the user’s machine, are not captured. These cloud sessions are not remote sessions, even though both run in the cloud; the remote session endpoints return Cowork sessions only. Each run of a Cowork scheduled task in the cloud is a remote session: the remote session list endpoint returns it as an [agent-owned session](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-remote-sessions) (`agent_id` is set, and `started_by_user` identifies the human who initiated the run), and the messages endpoint returns its transcript, but neither returns the task’s name or schedule. Claude Code routines that run in the cloud are Claude Code cloud sessions, so the session endpoints do not return them. Organizations with [HIPAA readiness](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#hipaa-readiness) enabled get local session data for Cowork and Claude Code only, stored for 30 days, and sessions for which [zero data retention (ZDR)](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) is in effect are excluded.
75 Local sessions are captured as their requests reach the Claude API, so nothing is installed on the device, and on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and [Claude Code cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web), which run on cloud infrastructure instead of the user’s machine, are not captured. These cloud sessions are not remote sessions, even though both run in the cloud; the remote session endpoints return Cowork sessions only. Each run of a Cowork scheduled task in the cloud is a remote session: the remote session list endpoint returns it as an [agent-owned session](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-remote-sessions) (`agent_id` is set, and `started_by_user` identifies the human who initiated the run), and the messages endpoint returns its transcript, but neither returns the task’s name or schedule. Each run of a Claude Code cloud scheduled task (formerly a routine) is a Claude Code cloud session, so the session endpoints do not return it. Organizations with [HIPAA readiness](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#hipaa-readiness) enabled get local session data for Cowork and Claude Code only, stored for 30 days, and sessions for which [zero data retention (ZDR)](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) is in effect are excluded.
7676
7777 The local and remote session endpoints are stable for Cowork, Claude Code, and Claude for Microsoft 365 sessions. Coverage of sessions in Claude Science, the Claude add-ins for Google Docs, Google Sheets, and Google Slides, and Claude in Chrome is in beta.
7878 </Accordion>
from line 109
109109 <Accordion title="What does the Compliance API not capture?">
110110 The Compliance API has known coverage boundaries: the Activity Feed records resource events but not prompt or response text, Claude Console and Claude API workloads authenticated with an API key expose no message content at all, and content removed by your retention policy, deleted by a user in claude.ai, or hard-deleted through the Compliance API is not recoverable. For the full coverage boundaries and delivery contract, see [Delivery guarantees and completeness](https://platform.claude.com/docs/en/manage-claude/compliance-integration-patterns#delivery-guarantees-and-completeness).
111111
112 Session transcripts have boundaries of their own. Local sessions are captured only as their requests reach the Claude API, so on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and [Claude Code cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web) (including Claude Code routines that run in the cloud), which run on cloud infrastructure instead of the user’s machine, are not captured either; organizations with HIPAA readiness enabled get local session data for Cowork and Claude Code only, stored for 30 days; and sessions for which zero data retention is in effect are excluded. No session transcript, local or remote, includes thinking blocks or tool definitions. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) receive local session transcripts as usual. While the key cannot be used, the messages endpoint returns [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable) instead of transcript content, and session metadata is still listed.
112 Session transcripts have boundaries of their own. Local sessions are captured only as their requests reach the Claude API, so on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and [Claude Code cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web) (including Claude Code cloud scheduled tasks, formerly routines), which run on cloud infrastructure instead of the user’s machine, are not captured either; organizations with HIPAA readiness enabled get local session data for Cowork and Claude Code only, stored for 30 days; and sessions for which zero data retention is in effect are excluded. No session transcript, local or remote, includes thinking blocks or tool definitions. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) receive local session transcripts as usual. While the key cannot be used, the messages endpoint returns [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable) instead of transcript content, and session metadata is still listed.
113113
114 No Compliance API endpoint lists an organization’s Cowork scheduled tasks or Claude Code routines.
114 No Compliance API endpoint lists an organization’s Cowork scheduled tasks or Claude Code cloud scheduled tasks.
115115 </Accordion>
116116</AccordionGroup>
117117
managed-agents/events-and-streaming Changed · +6 / -18 lines
from line 223
223223 break events;
224224 }
225225 case SESSION_ERROR -> {
226 // The `message` field spans all error variants; read it from the raw JSON.
227 var errorMessage =
228 event.asSessionError().error()._json().orElse(null) instanceof JsonObject json
229 ? json.values().get("message").asStringOrThrow()
230 : "unknown";
231 IO.println("\n[Error: " + errorMessage + "]");
226 IO.println("\n[Error: " + event.asSessionError().error().message() + "]");
232227 break events;
233228 }
234229 }
from line 444
449444 ```java Java
450445 try (var stream = client.beta().sessions().events().streamStreaming(session.id())) {
451446 // Stream is open and buffering. List history before tailing live.
452 // Every event variant carries `id`; read it from the raw JSON to dedup across variants.
453447 var seenEventIds = new HashSet<String>();
454448 for (var pastEvent : client.beta().sessions().events().list(session.id()).autoPager()) {
455 if (pastEvent._json().orElseThrow() instanceof JsonObject json) {
456 seenEventIds.add(json.values().get("id").asStringOrThrow());
457 }
449 seenEventIds.add(pastEvent.id());
458450 }
459451
460452 // Tail live events; Set.add returns false for already-seen IDs, skipping the replay.
461453 stream.stream()
462 .filter(event -> event._json().orElseThrow() instanceof JsonObject json
463 && seenEventIds.add(json.values().get("id").asStringOrThrow()))
454 .filter(event -> event.id().map(seenEventIds::add).orElse(true))
464455 .takeWhile(event -> !event.isSessionStatusIdle())
465456 .filter(BetaManagedAgentsStreamSessionEvents::isAgentMessage)
466457 .forEach(event -> event.asAgentMessage().content()
from line 1472
14811472 var events = await client.Beta.Sessions.Events.List(session.ID);
14821473 foreach (var sessionEvent in events.Items)
14831474 {
1484 Console.WriteLine($"[{sessionEvent.Json.GetProperty("type").GetString()}] {sessionEvent.ProcessedAt}");
1475 Console.WriteLine($"[{sessionEvent.Type.Raw()}] {sessionEvent.ProcessedAt}");
14851476 }
14861477 ```
14871478
from line 1489
14981489 ```java Java
14991490 var events = client.beta().sessions().events().list(session.id());
15001491 for (var event : events.data()) {
1501 var eventJson = event._json().orElseThrow().convert(JsonNode.class);
1502 var processedAt = eventJson.path("processed_at");
1503 IO.println("[" + eventJson.get("type").asText() + "] "
1504 + (processedAt.isTextual() ? processedAt.asText() : "null"));
1492 IO.println("[" + event.type().asString() + "] " + event.processedAt().orElse(null));
15051493 }
15061494 ```
15071495
from line 1548
15601548 });
15611549 foreach (var sessionEvent in events.Items)
15621550 {
1563 Console.WriteLine($"[{sessionEvent.Json.GetProperty("type").GetString()}] {sessionEvent.ProcessedAt}");
1551 Console.WriteLine($"[{sessionEvent.Type.Raw()}] {sessionEvent.ProcessedAt}");
15641552 }
15651553 ```
15661554
managed-agents/scheduled-deployments Changed · +5 / -8 lines
from line 452
452452 );
453453 await foreach (var run in runs.Paginate())
454454 {
455 // The Error union exposes .Message directly; the discriminator is read
456 // from .Json until a common .Type accessor is added.
457 var outcome = run.SessionID ?? run.Error!.Json.GetProperty("type").GetString();
455 var outcome = run.SessionID ?? run.Error!.Type.Raw();
458456 Console.WriteLine($"{run.CreatedAt} {outcome}");
459457 }
460458 ```
from line 479
481479 DeploymentRunListParams.builder()
482480 .deploymentId(deployment.id())
483481 .build()).autoPager()) {
484 // The Error union does not yet expose common .type()/.message()
485 // accessors; .toString() includes both.
486482 IO.println(run.createdAt() + " "
487 + run.sessionId().orElseGet(() -> run.error().orElseThrow().toString()));
483 + run.sessionId().orElseGet(() -> run.error().orElseThrow().type().asString()));
488484 }
489485 ```
490486
from line 540
544540 await foreach (var failedRun in failedRuns.Paginate())
545541 {
546542 var error = failedRun.Error!;
547 var errorType = error.Json.GetProperty("type").GetString();
543 var errorType = error.Type.Raw();
548544 Console.WriteLine($"{failedRun.CreatedAt} {errorType} {error.Message}");
549545 }
550546 ```
from line 565
569565 .deploymentId(deployment.id())
570566 .hasError(true)
571567 .build()).autoPager()) {
572 IO.println(run.createdAt() + " " + run.error().orElseThrow());
568 var error = run.error().orElseThrow();
569 IO.println(run.createdAt() + " " + error.type().asString() + " " + error.message());
573570 }
574571 ```
575572
managed-agents/session-threads Changed · +3 / -6 lines
from line 79
7979 ```csharp C#
8080 await foreach (var sessionThread in (await client.Beta.Sessions.Threads.List(session.ID)).Paginate())
8181 {
82 var label = sessionThread.Agent.Name ?? sessionThread.Agent.Json.GetProperty("type").GetString();
82 var label = sessionThread.Agent.Name ?? sessionThread.Agent.Type.Raw();
8383 Console.WriteLine($"[{label}] {sessionThread.Status.Raw()}");
8484 }
8585 ```
from line 616
616616 var page = await client.Beta.Sessions.Threads.Events.List(thread.ID, new() { SessionID = session.ID });
617617 await foreach (var evt in page.Paginate())
618618 {
619 Console.WriteLine($"[{evt.Json.GetProperty("type").GetString()}] {evt.ProcessedAt}");
619 Console.WriteLine($"[{evt.Type.Raw()}] {evt.ProcessedAt}");
620620 }
621621 ```
622622
from line 640
640640 .sessionId(session.id())
641641 .build()
642642 ).autoPager()) {
643 var type = event._json().orElseThrow() instanceof JsonObject json
644 ? json.values().get("type").asStringOrThrow()
645 : "unknown";
646643 var processedAt = event.processedAt().map(OffsetDateTime::toString).orElse("pending");
647 IO.println("[" + type + "] " + processedAt);
644 IO.println("[" + event.type().asString() + "] " + processedAt);
648645 }
649646 ```
650647
models/haiku-5-5/migration-guide Changed · +6 / -4 lines
from line 28
28284. If your code reads the first content block as the answer, select blocks by `type` instead. See [Configure thinking](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking).
29295. Remove `temperature`, `top_p`, and `top_k` from your requests. See [Remove sampling parameters](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters).
30306. If your requests end `messages` with an assistant turn for the model to continue, end them with a user turn instead. See [Replace assistant prefill](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replace-assistant-prefill).
317. If you use computer use, replace `computer_20250124`: on the Claude API and Claude Models on Google Cloud (Google managed), with the `computer_toolset_20260801` toolset; on Amazon Bedrock, with `computer_20251124` and the `computer-use-2025-11-24` beta header. See [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset).
317. If you use computer use, replace `computer_20250124` with the `computer_toolset_20260801` toolset. On Amazon Bedrock, `computer_20251124` also works. See [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset).
32328. If you replay stored conversations through a different account, replay each one through the account that produced it. See [Replay thinking blocks through the account that produced them](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replay-thinking-blocks-through-the-producing-account).
33339. If your code changes `system`, `tools`, or earlier `messages` between requests in a conversation and sends thinking blocks back, keep the conversation append-only. See [Keep earlier turns unchanged](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#keep-earlier-turns-unchanged).
343410. Handle `stop_reason: "refusal"`. Claude Haiku 5.5 runs safety classifiers that can decline a request, and it has no server-side fallback. See [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5#safeguard-refusals).
from line 126
126126
127127## Move computer use to the toolset
128128
129Claude Haiku 4.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_20250124` tool, with the `computer-use-2025-01-24` beta header. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 supports computer use only through the `computer_toolset_20260801` toolset, and a request that declares `computer_20250124` returns a 400 error. On Amazon Bedrock, Claude Haiku 5.5 doesn’t accept `computer_20250124` either; use the `computer_20251124` tool version with the `computer-use-2025-11-24` beta header.
129Claude Haiku 4.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_20250124` tool, with the `computer-use-2025-01-24` beta header. Claude Haiku 5.5 supports computer use through the `computer_toolset_20260801` toolset. A request to Claude Haiku 5.5 that declares `computer_20250124` returns a 400 error.
130130
131To move an integration to the toolset, drop the `computer-use-2025-01-24` beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then make the other request and agent-loop changes in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124): dispatch on each member `tool_use` block’s `name` and `toolset_name` rather than on `input.action`, handle every such block in a turn, and echo `toolset_name` on results. Zoom is on by default in the toolset; if your environment doesn’t implement it, add `"configs": {"zoom": {"enabled": false}}`. If you send the `fine-grained-tool-streaming-2025-05-14` beta header, remove it. Alongside a toolset entry, it returns a 400 error. For other platforms, see the computer use tool’s [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support) section.
131To move an integration to the toolset, drop the `computer-use-2025-01-24` beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then make the other request and agent-loop changes in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). Dispatch on each member `tool_use` block’s `name` and `toolset_name` rather than on `input.action`. Handle every such block in a turn and echo `toolset_name` on results. Zoom is on by default in the toolset; if your environment doesn’t implement it, add `"configs": {"zoom": {"enabled": false}}`. If you send the `fine-grained-tool-streaming-2025-05-14` beta header, remove it. Alongside a toolset entry, it returns a 400 error.
132132
133On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. Claude Haiku 4.5 doesn’t support it.
133On Amazon Bedrock, Claude Haiku 5.5 also accepts the `computer_20251124` tool with the `computer-use-2025-11-24` beta header.
134
135Claude Haiku 5.5 supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. Claude Haiku 4.5 doesn’t support it.
134136
135137## Replay thinking blocks through the account that produced them
136138
models/haiku-5-5/whats-new-haiku-5-5 Changed · +18 / -18 lines
from line 12
1212
1313Each row names one change, whether it is new, changed, or breaking, and what your code has to do.
1414
15| Change | Type | Action needed |
16| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
17| [Adaptive thinking and effort](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#adaptive-thinking-and-effort) | New | Optional: set `effort` to trade response quality against speed and cost. |
18| [Larger context window and output](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#larger-context-window-and-output) | New | None. Existing `max_tokens` values stay valid, but thinking tokens count toward them. Long prompts are billed at higher prices; see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing). |
19| [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | New | None. Available on the Claude API and Claude Models on Google Cloud (Google managed). |
20| [Safety classifiers can decline a request](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) | New | Handle `stop_reason: "refusal"` in your client. Server-side fallback isn’t available. |
21| [Manual extended thinking returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Breaking | Replace `budget_tokens` with adaptive thinking. |
22| [Sampling parameters can return an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters) | Breaking | Omit `temperature`, `top_p`, and `top_k`. |
23| [Assistant message prefill returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replace-assistant-prefill) | Breaking | End `messages` with a user turn. |
24| [`computer_20250124` returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) on the Claude API, Claude Models on Google Cloud (Google managed), and Amazon Bedrock | Breaking | Replace it with `computer_toolset_20260801` on the Claude API and Claude Models on Google Cloud (Google managed), or with `computer_20251124` on Amazon Bedrock. |
25| [Changing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#keep-earlier-turns-unchanged) | Breaking | Keep conversations append-only if you send thinking blocks back. |
26| [Responses can start with thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#responses-can-begin-with-thinking-blocks) | Changed | Select content blocks by `type`, not by position. |
27| [Thinking text is omitted by default](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Changed | To receive summarized thinking, set `thinking.display` to `"summarized"`. |
28| [Same text counts as more tokens](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#same-text-counts-as-more-tokens) | Changed | Recount prompts and revisit `max_tokens` and cost estimates. |
29| [Replaying thinking blocks across accounts](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#replaying-thinking-blocks-across-accounts) | Changed | If you replay stored conversations through a different account, replay each through the account that produced it. |
30| [Earlier thinking blocks stay in context](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#earlier-thinking-blocks-stay-in-context) | Changed | Expect more input tokens in multi-turn conversations. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). |
31| [Shorter prompts can be cached](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations) | Changed | None. The minimum cacheable prompt length is 512 tokens, down from 4,096 on Claude Haiku 4.5, so a prompt in between that sets `cache_control` is cached on Claude Haiku 5.5. |
32| [Context awareness tags aren’t injected](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness) | Changed | To give the model an explicit budget for an agentic loop, use [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta). |
15| Change | Type | Action needed |
16| --------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
17| [Adaptive thinking and effort](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#adaptive-thinking-and-effort) | New | Optional: set `effort` to trade response quality against speed and cost. |
18| [Larger context window and output](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#larger-context-window-and-output) | New | None. Existing `max_tokens` values stay valid, but thinking tokens count toward them. Long prompts are billed at higher prices; see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing). |
19| [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | New | None. |
20| [Safety classifiers can decline a request](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) | New | Handle `stop_reason: "refusal"` in your client. Server-side fallback isn’t available. |
21| [Manual extended thinking returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Breaking | Replace `budget_tokens` with adaptive thinking. |
22| [Sampling parameters can return an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters) | Breaking | Omit `temperature`, `top_p`, and `top_k`. |
23| [Assistant message prefill returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#replace-assistant-prefill) | Breaking | End `messages` with a user turn. |
24| [`computer_20250124` returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) | Breaking | Replace it with `computer_toolset_20260801`. On Amazon Bedrock, `computer_20251124` also works. |
25| [Changing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#keep-earlier-turns-unchanged) | Breaking | Keep conversations append-only if you send thinking blocks back. |
26| [Responses can start with thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#responses-can-begin-with-thinking-blocks) | Changed | Select content blocks by `type`, not by position. |
27| [Thinking text is omitted by default](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Changed | To receive summarized thinking, set `thinking.display` to `"summarized"`. |
28| [Same text counts as more tokens](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#same-text-counts-as-more-tokens) | Changed | Recount prompts and revisit `max_tokens` and cost estimates. |
29| [Replaying thinking blocks across accounts](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#replaying-thinking-blocks-across-accounts) | Changed | If you replay stored conversations through a different account, replay each through the account that produced it. |
30| [Earlier thinking blocks stay in context](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#earlier-thinking-blocks-stay-in-context) | Changed | Expect more input tokens in multi-turn conversations. To remove older blocks, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing). |
31| [Shorter prompts can be cached](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations) | Changed | None. The minimum cacheable prompt length is 512 tokens, down from 4,096 on Claude Haiku 4.5, so a prompt in between that sets `cache_control` is cached on Claude Haiku 5.5. |
32| [Context awareness tags aren’t injected](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-awareness) | Changed | To give the model an explicit budget for an agentic loop, use [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets) (beta). |
3333
3434## New capabilities
3535
models/opus-5-5/migration-guide Changed · +11 / -9 lines
#### Some computer use tool versions are not supported #### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
from line 28
2828* **Tool choice:** Use `tool_choice` `{"type": "auto"}` (the default) or `{"type": "none"}`. Forcing a tool call with `{"type": "any"}` or `{"type": "tool", "name": "..."}` is rejected. See the [before and after for tool choice](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#forced-tool-use).
2929* **Sampling parameters:** Omit `temperature`, `top_p`, and `top_k`. Use prompting to guide the model’s behavior.
3030* **Prefill:** Don’t end `messages` with a prefilled assistant turn: it is rejected. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) or system prompt instructions instead.
31* **Computer use:** On the Claude API and Claude Models on Google Cloud (Google managed), declare computer use as the `computer_toolset_20260801` toolset; the earlier `computer_20251124` tool is rejected there. See the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
31* **Computer use:** Declare computer use as the `computer_toolset_20260801` toolset. On Amazon Bedrock, `computer_20251124` also works. See the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
3232* **Context window:** No context-window beta header is needed. The [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) is the default, and a header sent for older models has no effect.
3333
3434The following request satisfies every item in the list: effort is set, and there is no `thinking` field. Where the example prints text, it finds the text block by its type, because `thinking` blocks come first.
from line 279
279279* Remove `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}`; choose an effort level instead.
280280* Set `effort` explicitly: the default is `medium`, where Claude Opus 5’s is `high`.
281281* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.
282* If you use computer use on the Claude API or Claude Models on Google Cloud (Google managed), declare `computer_toolset_20260801` (no beta header) instead of `computer_20251124` and update your agent loop for the toolset. On Amazon Bedrock, keep `computer_20251124`; check the computer use tool’s [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support) section for other platforms.
282* If you use an earlier computer use tool version, declare `computer_toolset_20260801` (no beta header) instead and update your agent loop for the toolset. On Amazon Bedrock, `computer_20251124` also works.
283283* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5’s thinking blocks (Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them). Claude Opus 5.5 itself reads thinking from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models.
284284* Read content blocks by `type`, and pass `thinking` blocks back unmodified in tool-use loops.
285285* If your interface renders text between tool calls, set `display: "updates"` (beta) or `"summarized"` and render the non-empty `thinking` blocks.
from line 878
878878
879879On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks; no other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them. In the other direction, Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models. Keep the conversation append-only (no edits to the `system` prompt, `tools`, or earlier messages mid-conversation) so the blocks stay valid; Claude Code, claude.ai, Claude Managed Agents, and the Claude Agent SDK already do. On accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms, a request that replays a thinking block after such an edit and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error. There is no code change for append-only integrations. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them) and [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
880880
881#### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
881#### Some computer use tool versions are not supported
882882
883On the Claude API and Claude Models on Google Cloud (Google managed), a `tools` entry of type `computer_20251124` returns a 400 error (`'claude-opus-5-5' does not support tool types: computer_20251124.`, followed by the tool types the model accepts). Declare the `computer_toolset_20260801` toolset instead: drop the beta header and send the entry with no `name` or display dimensions. In your agent loop, handle member `tool_use` blocks (the action is the block’s `name`, not `input.action`), several of them per turn, and echo `toolset_name` on every result. The request change is shown below; the agent-loop changes are listed in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). On Amazon Bedrock, the earlier `computer_20251124` tool continues to work on Claude Opus 5.5 as it does on Claude Opus 5, so no change is needed there; for other platforms, see the computer use tool’s [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support) section. See [The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported).
883Claude Opus 5.5 supports computer use through the `computer_toolset_20260801` toolset. On Amazon Bedrock, Claude Opus 5.5 also accepts the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. Claude Opus 5.5 returns a 400 error for any computer use tool version it doesn’t accept, such as `computer_20251124` on the Claude API. It doesn’t accept `computer_20250124` on any platform. On the Claude API, the error message begins `'claude-opus-5-5' does not support tool types: computer_20251124.` and then lists the tool types the model accepts.
884884
885Before. Claude Opus 5 accepts this request, and on the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 rejects it with a 400 error:
885Integrations that use the toolset need no change. To move a `computer_20251124` integration to the toolset, drop the beta header and send the `computer_toolset_20260801` entry with no `name` or display dimensions. In your agent loop, handle every member `tool_use` block in a turn and echo `toolset_name` on every result. Read the action from each block’s `name`, not from `input.action`. [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124) lists the agent-loop changes.
886886
887Before. Claude Opus 5 accepts this request, and Claude Opus 5.5 rejects it with a 400 error on the Claude API:
888
887889<CodeGroup>
888890 ```bash cURL
889891 curl https://api.anthropic.com/v1/messages \
from line 1200
11981200
119912015. **Fast mode:** Claude Opus 5.5 supports [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) on the Claude API. Fast mode is not available on Claude Opus 4.7, where requests with `speed: "fast"` return an error. Set `speed: "fast"` on your requests. Claude Opus 5.5 doesn’t need a beta header.
12001202
12016. **Computer use toolset and browser use tool:** On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages. Claude Opus 4.7 supports neither. On those platforms Claude Opus 5.5 doesn’t accept the earlier `computer_20251124` tool; see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
12036. **Computer use toolset and browser use tool:** Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages. Claude Opus 4.7 supports neither. To move a `computer_20251124` integration to the toolset, see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
12021204
12031205## Migrating to Claude Opus 5.5 from Claude Opus 4.6 and earlier Opus models
12041206
from line 1633
16311633
16321634 * **Text editor:** Use `text_editor_20250728` and `str_replace_based_edit_tool`. See the [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool) documentation for details.
16331635 * **Code execution:** Upgrade to `code_execution_20260521`. See the [Code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#upgrade-to-latest-tool-version) documentation for migration instructions.
1634 * **Computer use:** On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 accepts computer use only as the `computer_toolset_20260801` toolset: the earlier `computer_20250124` and `computer_20251124` tools are rejected there. See the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
1636 * **Computer use:** Use the `computer_toolset_20260801` toolset in place of `computer_20250124`, which Claude Opus 5.5 doesn’t accept. On Amazon Bedrock, `computer_20251124` also works. See the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
16351637
163616383. **Handle the `refusal` stop reason**
16371639
models/opus-5-5/overview Changed · +8 / -1 lines
from line 16
1616
1717## Overview
1818
19Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes affect code already running on Claude Opus 5: [thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled), [forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported), [thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them), and, on the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported). The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
19Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes can affect code already running on Claude Opus 5:
20
21* [Thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled).
22* [Forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported).
23* [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them).
24* [Some computer use tool versions are not supported](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported).
25
26The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
2027
2128[What’s new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5)
2229
models/opus-5-5/whats-new-opus-5-5 Changed · +13 / -6 lines
### Some computer use tool versions are not supported ### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
from line 4
44description: Overview of breaking changes, feature support, and behavior differences in Claude Opus 5.5.
55---
66
7Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes affect code already running on Claude Opus 5: [thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled), [forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported), [thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them), and, on the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported). The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
7Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes can affect code already running on Claude Opus 5:
88
9* [Thinking can’t be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled).
10* [Forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported).
11* [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them).
12* [Some computer use tool versions are not supported](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported).
13
14The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#text-between-tool-calls) whose text is empty at the default `display` setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a `display` value that returns the text.
15
916## New model
1017
1118| Model | Claude API ID | Description |
from line 55
4855
4956The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. Keep the conversation append-only: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. A request that replays a block after such a change and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error on accounts created on or after August 31, 2026, 00:00 UTC. This applies on the Claude API and on cloud platforms. On accounts created before that date, the request gets the error only when it sets the field to `"error"`. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set the field to `"drop_block"`. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).
5057
51### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
58### Some computer use tool versions are not supported
5259
53Claude Opus 5 accepts [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) both as the `computer_toolset_20260801` toolset and, with the `computer-use-2025-11-24` beta header, as the earlier `computer_20251124` tool. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 supports only the toolset: a request that declares a `computer_20251124` tool returns a 400 `invalid_request_error`. The message names the rejected type, then lists the tool types the model does accept (`computer_toolset_20260801` among them) after `Did you mean one of`; it begins:
60Claude Opus 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_toolset_20260801` toolset. On Amazon Bedrock, Claude Opus 5.5 also accepts the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. Claude Opus 5.5 returns a 400 error for any computer use tool version it doesn’t accept, such as `computer_20251124` on the Claude API. The Claude API’s `invalid_request_error` message names the rejected type and, after `Did you mean one of`, lists the tool types the model accepts. The message begins:
5461
5562```text wrap
5663'claude-opus-5-5' does not support tool types: computer_20251124.
5764```
5865
59To move an existing integration on the Claude API or Claude Models on Google Cloud (Google managed), follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124): drop the beta header, replace the `tools` entry with `{"type": "computer_toolset_20260801"}`, and update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. On Amazon Bedrock, the earlier `computer_20251124` tool continues to work on Claude Opus 5.5 as it does on Claude Opus 5, so no change is needed there. For other platforms, see the computer use tool’s [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support) section. Integrations that already use the toolset, and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), need no change. The migration guide shows the request [before and after](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
66Integrations that use the toolset need no change. To move a `computer_20251124` integration to the toolset, follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). Drop the beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. The migration guide shows the request [before and after](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#computer-use-toolset).
6067
6168## Feature support
6269
63Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). On the Claude API and Claude Models on Google Cloud (Google managed), computer use requires the `computer_toolset_20260801` toolset (see the [computer use breaking change](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#computer-20251124-is-not-supported)). See each feature’s page for model availability.
70Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). See each feature’s page for model availability.
6471
6572### Fast mode
6673
from line 151
144151 ```
145152</CodeGroup>
146153
147Then remove any `thinking: {"type": "disabled"}` or `thinking: {"type": "enabled", ...}` settings and choose an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level instead. Replace `tool_choice` types `any` and `tool` with `auto` plus [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use). If you use computer use through `computer_20251124` on the Claude API or Claude Models on Google Cloud (Google managed), [move to the toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). If your interface shows the text between tool calls, also set `thinking.display`; see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls). See the [migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide) for step-by-step instructions from Claude Opus 5 and earlier models, and the full checklist.
154Then remove any `thinking: {"type": "disabled"}` or `thinking: {"type": "enabled", ...}` settings and choose an [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level instead. Replace `tool_choice` types `any` and `tool` with `auto` plus [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use). If you use computer use through `computer_20251124`, [move to the toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). On Amazon Bedrock, `computer_20251124` also works. If your interface shows the text between tool calls, also set `thinking.display`; see [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls). See the [migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide) for step-by-step instructions from Claude Opus 5 and earlier models, and the full checklist.
148155
149156## Next steps
150157
models/sonnet-5-5/migration-guide Changed · +7 / -13 lines
### Some computer use tool versions are not supported ### Computer use needs the toolset on the Claude API and Claude Models on Google Cloud (Google managed)
from line 470
470470* To keep running without up-front thinking, send the [lowest thinking setting](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#turn-off-up-front-thinking) at `high` effort or below.
471471* Replace [forced tool use](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use) with `auto` and strict tools.
472472* Keep conversations [append-only](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-blocks).
473* On the Claude API and Claude Models on Google Cloud (Google managed), move computer use to the [toolset](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset), without the `fine-grained-tool-streaming-2025-05-14` beta header.
473* Move computer use to the [toolset](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset), without the `fine-grained-tool-streaming-2025-05-14` beta header. On Amazon Bedrock, `computer_20251124` also works.
474474* [Pair the advisor tool](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#advisor-tool) with a supported advisor, and expect encrypted advice.
475475* Read [text between tool calls](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#text-between-tool-calls) from `thinking` blocks.
476476* [Handle refusals](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#safety-classifiers-and-fallback), and configure fallback.
from line 488
488488
489489* Replace [assistant prefills](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-sonnet-45).
490490* Parse tool call input with a standard JSON parser.
491* On Amazon Bedrock, move computer use from `computer_20250124` to [`computer_20251124`](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset).
492491* Set `output_config.effort` explicitly.
493492* Remove any context-window beta header.
494493* Remove `interleaved-thinking-2025-05-14`, and replace `fine-grained-tool-streaming-2025-05-14` with `eager_input_streaming`.
from line 842
843842
844843Each Claude Sonnet 5.5 thinking block is also signed over the conversation before it. Keep conversations append-only, and change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages). A request that replays a block after an edit to earlier history and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error on accounts created on or after August 31, 2026, 00:00 UTC. This applies on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed). Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them or in an account linked to it. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
845844
846### Computer use needs the toolset on the Claude API and Claude Models on Google Cloud (Google managed)
845### Some computer use tool versions are not supported
847846
848On the Claude API and Claude Models on Google Cloud (Google managed), Claude Sonnet 5.5 supports computer use only through the `computer_toolset_20260801` toolset. There, `computer_20251124` returns a 400 error. Claude Sonnet 5.5 doesn’t accept `computer_20250124` on any platform. Find the version you send today:
847Claude Sonnet 5.5 supports computer use through the `computer_toolset_20260801` toolset. On Amazon Bedrock, Claude Sonnet 5.5 also accepts the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. Claude Sonnet 5.5 returns a 400 error for any computer use tool version it doesn’t accept, such as `computer_20251124` on the Claude API. It doesn’t accept `computer_20250124` on any platform.
849848
850| Version you send today | Starting models that send it | Send on the Claude API and Claude Models on Google Cloud (Google managed) | Send on Amazon Bedrock |
851| ---------------------- | ---------------------------------------------------- | ------------------------------------------------------------------------- | ---------------------- |
852| `computer_20251124` | Claude Sonnet 5, Claude Sonnet 4.6 | `computer_toolset_20260801` | `computer_20251124` |
853| `computer_20250124` | Claude Sonnet 4.5, Claude Haiku 4.5, Claude Sonnet 4 | `computer_toolset_20260801` | `computer_20251124` |
849Integrations that use the toolset need no change. To move to the toolset, replace `computer_20251124` or `computer_20250124` with `computer_toolset_20260801`, and drop that version’s beta header. [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124) lists the request and agent-loop changes.
854850
855851If you send the `fine-grained-tool-streaming-2025-05-14` beta header, remove it when you move to the toolset. Alongside a toolset entry, it returns a 400 error. Set `eager_input_streaming: true` on each tool that needs it instead.
856852
857Code that already sends the toolset needs no change. [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124) lists the request and agent-loop changes. For other platforms, see [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support).
858
859853### The advisor tool accepts fewer advisors
860854
861855With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), a Claude Sonnet 5.5 executor needs one of these advisors: Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5, Claude Fable 5.1, Claude Mythos 5, or Claude Mythos 5.1. Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 5.5 advisors return a 400 error. The advice comes back encrypted as an `advisor_redacted_result` block, so its text isn’t readable in the response. See [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).
from line 1210
12161210
12171211**Tool input escaping.** Escaping in tool call arguments can differ. Parse `input` with a standard JSON parser.
12181212
1219**Computer use.** Claude Sonnet 5.5 doesn’t accept `computer_20250124`. See the [computer use table](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset).
1213**Computer use.** Claude Sonnet 5.5 doesn’t accept `computer_20250124`. See [Some computer use tool versions are not supported](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#computer-use-toolset).
12201214
12211215**Effort.** Claude Sonnet 4.5 has no effort parameter. Set an effort level explicitly, as [Recommended changes](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#recommended-changes) describes.
12221216
models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +7 / -9 lines
### Some computer use tool versions are not supported ### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
from line 4
44description: "What changes when you move from Claude Sonnet 5 to Claude Sonnet 5.5: breaking changes, feature support, behavior differences, pricing, and availability."
55---
66
7Claude Sonnet 5.5 offers the best combination of speed and intelligence. Five breaking changes affect code already running on Claude Sonnet 5:
7Claude Sonnet 5.5 offers the best combination of speed and intelligence. Five breaking changes can affect code already running on Claude Sonnet 5:
88
99* [Turn off up-front thinking with `between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking).
1010* [Forced tool use returns an error](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#forced-tool-use-is-not-supported).
1111* [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them).
12* On the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#computer-20251124-is-not-supported).
12* [Some computer use tool versions are not supported](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#computer-20251124-is-not-supported).
1313* [The advisor tool rejects four models as advisors](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#advisor-tool-pairings): Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5.
1414
1515One more change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#text-between-tool-calls). An application that streams that text to its users goes quiet between tool calls until it sets a `display` value that returns the text, or turns off up-front thinking with `between_tools`.
from line 56
5656
5757See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-blocks).
5858
59### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
59### Some computer use tool versions are not supported
6060
61On the Claude API and Claude Models on Google Cloud (Google managed), Claude Sonnet 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) only through the `computer_toolset_20260801` toolset. A request that declares the earlier `computer_20251124` tool returns a 400 `invalid_request_error`. On the Claude API, the message names the rejected type, then lists the tool types the model does accept. It begins:
61Claude Sonnet 5.5 supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) through the `computer_toolset_20260801` toolset. On Amazon Bedrock, Claude Sonnet 5.5 also accepts the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. Claude Sonnet 5.5 returns a 400 error for any computer use tool version it doesn’t accept, such as `computer_20251124` on the Claude API. The Claude API’s `invalid_request_error` message names the rejected type and, after `Did you mean one of`, lists the tool types the model accepts. The message begins:
6262
6363```text wrap
6464'claude-sonnet-5-5' does not support tool types: computer_20251124.
6565```
6666
67On Amazon Bedrock, Claude Sonnet 5.5 accepts the earlier `computer_20251124` tool.
67Integrations that use the toolset need no change. To move a `computer_20251124` integration to the toolset, follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124), which shows the request before and after. Drop the beta header and replace the `tools` entry with `{"type": "computer_toolset_20260801"}`. Then update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results.
6868
69To move an existing integration on the Claude API or Claude Models on Google Cloud (Google managed), follow [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124), which shows the request before and after. Drop the beta header, replace the `tools` entry with `{"type": "computer_toolset_20260801"}`, and update your agent loop for member `tool_use` blocks, batch actions, and `toolset_name` on results. The toolset is available on both the Claude API and Claude Models on Google Cloud (Google managed). For other platforms, see the computer use tool’s [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#availability-feature-support) section. Integrations that already use the toolset, and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), need no change.
70
7169### Some advisor tool pairings are not supported
7270
7371With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) (beta), a Claude Sonnet 5.5 executor needs Claude Mythos 5.1, Claude Fable 5.1, Claude Mythos 5, Claude Fable 5, Claude Opus 5.5, or Claude Opus 5 as its advisor, or Claude Sonnet 5.5 itself. Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5 advisors work with a Claude Sonnet 5 executor, but with a Claude Sonnet 5.5 executor they return a 400 `invalid_request_error`. Every advisor that Claude Sonnet 5.5 accepts returns its advice encrypted, as an `advisor_redacted_result` block, so your client can’t read the advice text. See the advisor tool’s [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) and [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants).
from line 72
7472
7573## Feature support
7674
77Claude Sonnet 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) (beta), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). Per-message effort, mid-conversation system messages, and mid-conversation tool changes aren’t available on Claude Sonnet 5, whose minimum cacheable prompt is 1,024 tokens. On the Claude API and Claude Models on Google Cloud (Google managed), computer use requires the `computer_toolset_20260801` toolset (see the [computer use breaking change](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#computer-20251124-is-not-supported)). See each feature’s page for model availability.
75Claude Sonnet 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) (beta), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) with a 512-token minimum cacheable prompt, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). Per-message effort, mid-conversation system messages, and mid-conversation tool changes aren’t available on Claude Sonnet 5, whose minimum cacheable prompt is 1,024 tokens. See each feature’s page for model availability.
7876
7977### Compact on demand (beta)
8078
from line 157
1591571. If your code turns thinking off with `disabled`, send `between_tools` instead, at `high` effort or below.
1601582. Replace `tool_choice` types `any` and `tool` with `auto` plus [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use).
1611593. Keep conversations append-only. A request that replays a Claude Sonnet 5.5 thinking block after an edit to earlier history can return a 400 error. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them).
1624. If you use computer use through `computer_20251124` on the Claude API or Claude Models on Google Cloud (Google managed), [move to the toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).
1604. If you use computer use through `computer_20251124`, [move to the toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). On Amazon Bedrock, `computer_20251124` also works.
1631615. If you use the advisor tool with a Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, or Claude Haiku 5.5 advisor, [switch to an advisor that Claude Sonnet 5.5 accepts](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#advisor-tool-pairings).
1641626. If your interface shows the text between tool calls, set `thinking.display` when you use adaptive thinking. With `between_tools`, the text comes back without it. See [Text between tool calls is returned in thinking blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#text-between-tool-calls).
165163
api/ip-addresses Changed · +4 / -0 lines
from line 16
1616
1717`160.79.104.0/23`
1818
19`153.61.224.0/22`
20
1921### IPv6
2022
2123`2607:6bc0::/48`
from line 29
2729### IPv4
2830
2931`160.79.104.0/21`
32
33`153.61.208.0/20`
3034
3135### Phased out IP addresses
3236
build-with-claude/claude-in-amazon-bedrock Changed · +1 / -2 lines
from line 365
365365* [Messages API](https://platform.claude.com/docs/en/api/messages/create) (`/anthropic/v1/messages`)
366366* [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching)
367367* [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking)
368* [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), and [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool)
368* [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), and [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool)
369369* [Citations](https://platform.claude.com/docs/en/build-with-claude/citations)
370370* [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs)
371371
from line 377
377377* API endpoints (Message Batches, Models, Admin, Compliance, Usage and Cost)
378378* Claude Managed Agents
379379* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)
380* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Amazon Bedrock; the beta computer use tool versions remain available)
381380
382381## Regions
383382
build-with-claude/claude-in-microsoft-foundry Changed · +0 / -1 lines
from line 653
653653* Models API
654654* Message Batches API
655655* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)
656* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Microsoft Foundry; the beta computer use tool versions remain available for the models listed under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions))
657656
658657### Additional features not supported when hosted on Azure
659658
build-with-claude/claude-platform-on-aws Changed · +1 / -2 lines
from line 550
550550* **Beta features:** Pass the standard `anthropic-beta` header to access beta features, just as you would with the Claude API.
551551* **Agent Skills:** Use pre-built and custom [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) with the same `container.skills` parameter as the Claude API. All pre-built Skills (PowerPoint, Excel, Word, PDF) work out of the box.
552552* **Code execution:** Run code in Anthropic’s managed sandbox using the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool).
553* **Tool use:** All [tool use capabilities](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) are available except the computer use and browser use toolsets; see [Features not supported](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-not-supported).
553* **Tool use:** All [tool use capabilities](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) are available.
554554* **Thinking:** [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort), and, on the models that support it, [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) work with the same parameters as the Claude API.
555555* **Streaming:** Full SSE streaming support for real-time responses.
556556* **Batch processing:** Submit batch requests for high-throughput workloads.
from line 576
576576The following capabilities are not currently available on Claude Platform on AWS:
577577
578578* **HIPAA readiness:** Anthropic’s HIPAA-ready program is not available. See [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
579* **Computer use and browser use toolsets:** `computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Claude Platform on AWS. The beta computer use tool versions remain available for the models listed under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).
580579
581580- **Admin API:** Workspace endpoints (create, get, list, update, and archive on `/v1/organizations/workspaces`), external key endpoints (register, get, list, update, and delete on `/v1/organizations/external_keys`, for [CMEK](https://platform.claude.com/docs/en/manage-claude/cmek); keys are validated when attached to a workspace rather than through a validate endpoint), the [telemetry destination endpoints](https://platform.claude.com/docs/en/api/claude-platform-on-aws-iam-actions#telemetry-destinations), and the [Usage and Cost Analytics API](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api) endpoints are available. Other Admin API endpoints (organization members, workspace members, invites, API keys, the legacy [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api), and rate limit reports) are not available. AWS IAM manages organization membership.
582581- **Workspace member management:** Adding or removing users from individual workspaces is not available. AWS IAM policies on workspace ARNs control access.
build-with-claude/prompt-engineering/prompting-claude-opus-4-8 Changed · +1 / -1 lines
from line 157
157157
158158## Computer use
159159
160Claude Opus 4.8 supports the earlier `computer_20251124` tool version and, on the Claude API and Claude Models on Google Cloud (Google managed), the `computer_toolset_20260801` toolset. On those two platforms, Claude Opus 4.8 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
160Claude Opus 4.8 supports computer use through the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool version. It also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`) for tasks inside webpages. [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.
161161
162162For particularly cost-sensitive workloads, 720p or 1366×768 are lower-cost options with strong performance. Conduct your own testing to find the ideal settings for your use case; experimenting with effort settings can also help tune the model’s behavior.
163163