One read of Claude Developer Platformapi-20261028T203725Z
116 pages moved out of 821 read.
Pages moved
116
significant first
Pages read
821
in this capture
Captured
20:37 UTC
Corpus hash
82e28663d5c2
corpus-hash
What this read moved
101-116 of 116, page 5 of 5This capture is too large to show at once. Changes 101-116 of 116 are below, significant first; the rest are on the following screens.
managed-agents/webhooks Changed · +61 / -0 lines
## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling
from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
1135---
1236
1337Sessions are long-running interactions. Although most real-time interactions occur through the [SSE event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming), webhooks notify you of major state changes.
from line 464
440464 * Deliveries to the endpoint fail continuously for a sustained period, with the reason `auto-disabled after sustained delivery failures`. The trigger is how long the endpoint has been failing without interruption, not a delivery count. A single `2xx` resets the window, so one event that fails intermittently can’t disable the endpoint.
441465
442466 All three are reversible: re-enable the endpoint in Console after you resolve the issue. Events emitted while the endpoint was disabled aren’t replayed.
467
468## Availability
469
470Webhooks are in beta on every model.
471
472### API support
473
474#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
475
476* Availability: Available
477
478| Status | Cloud platforms |
479| ------ | ------------------------------------------------------------------------------------------------------------------ |
480| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
481
482### Required beta headers
483
484[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
485
486Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
487
488* `managed-agents-2026-04-01`
489
490### Data handling
491
492[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
493
494| Item | Zero data retention | HIPAA |
495| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
496| Status | Not eligible | Not eligible |
497| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
498
499Applicable endpoints:
500
501* `/v1/agents`
502* `/v1/sessions`
503* `/v1/environments`
443504
managed-agents/workflow-runs Changed · +58 / -1 lines
## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling
from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232
1333A **workflow** is a program that an agent writes to run many agents and combine what they return. A **workflow run** is the execution of one workflow. **[Dynamic workflows](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#dynamic-workflows)** is the feature that lets an agent write workflows and start runs. You turn it on or off with the `workflows` (csharp, go: `Workflows`) setting in the agent’s `multiagent` (csharp, go: `Multiagent`) block.
from line 837
817837* If it’s `exhausted`, the thread has failed. If the workflow lets that failure end the run, the run ends with `program_error`, which doesn’t name the cause. Read the failed threads’ events to find it.
818838
819839The server also limits how much all of your organization’s sessions do each minute. A thread that meets this limit stops, with a `session.error` on its own stream whose message names a rate limit. Wait a minute before you ask the agent to continue.
840
841## Availability
842
843Dynamic workflows are available on every model.
844
845### API support
846
847#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
848
849* Availability: Available
850
851| Status | Cloud platforms |
852| --------- | ----------------------- |
853| Available | All supported platforms |
854
855### Required beta headers
856
857[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
858
859Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
860
861* `managed-agents-2026-04-01`
862
863### Data handling
864
865[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
866
867| Item | Zero data retention | HIPAA |
868| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
869| Status | Not eligible | Not eligible |
870| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
871
872Applicable endpoints:
873
874* `/v1/agents`
875* `/v1/sessions`
876* `/v1/environments`
820877
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals Changed · +55 / -0 lines
## Availability ### API support #### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
from line 2
22title: Handle streaming refusals
33url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
44description: Detect and handle refusal stop reasons in streaming responses, and retry refused requests on a fallback model.
5featureMetadata:
6 supportedModels:
7 - claude-fable-5-1
8 - claude-mythos-5-1
9 - claude-fable-5
10 - claude-mythos-5
11 - claude-mythos-preview
12 - claude-opus-5-5
13 - claude-opus-5
14 - claude-sonnet-5-5
15 - claude-sonnet-5
16 - claude-haiku-5-5
17 - claude-haiku-4-5-20251001
18 - claude-opus-4-8
19 - claude-opus-4-7
20 - claude-opus-4-6
21 - claude-sonnet-4-6
22 - claude-opus-4-5-20251101
23 - claude-sonnet-4-5-20250929
24 supportedPlatforms:
25 Claude API: ga
26 Claude Platform on AWS: ga
27 Amazon Bedrock: ga
28 Amazon Bedrock (InvokeModel): ga
29 Claude Models on Google Cloud (Google managed): ga
30 Microsoft Foundry: ga
531---
632
33**API support**: Usage differs by product.
34
35* **Messages API**: Always on. The stream ends with `stop_reason` `"refusal"`, and `stop_details` (`category` and `explanation`) arrives on the `message_delta` event.
36* **Managed Agents**: Always on. A refused turn ends, and the session goes idle with `stop_reason.type` `"refusal"`.
37
738Starting with Claude 4 models, streaming responses from Claude’s API return **`stop_reason`: `"refusal"`** when streaming classifiers intervene to handle potential policy violations. This safety feature helps maintain content compliance during real-time streaming.
839
940<Tip>
from line 369
338369 Serve users across languages with Claude’s cross-lingual capabilities.
339370 </Card>
340371</CardGroup>
372
373## Availability
374
375Streaming refusals are available or in beta, depending on the API.
376
377### API support
378
379#### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages)
380
381* Availability: Always on
382* Usage: The stream ends with `stop_reason` `"refusal"`, and `stop_details` (`category` and `explanation`) arrives on the `message_delta` event.
383
384| Status | Cloud platforms |
385| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
386| Available | 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) |
387
388#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
389
390* Availability: Always on
391* Usage: A refused turn ends, and the session goes idle with `stop_reason.type` `"refusal"` and `stop_details` (`category` and `explanation`) on the `session.status_idle` event.
392
393| Status | Cloud platforms |
394| ------ | ------------------------------------------------------------------------------------------------------------------ |
395| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
341396
about-claude/pricing Changed · +1 / -1 lines
from line 517
517517
518518### How is token usage calculated?
519519
520Tokens are pieces of text that models process. How many tokens the same text produces depends on the model’s tokenizer, the language, and the type of content. Claude 4.7 and later models and Claude Mythos Preview use a newer tokenizer that produces approximately 30 percent more tokens for the same text than earlier models. To see how many tokens a request uses on a specific model, count it with [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) and that model’s ID.
520Tokens are pieces of text that models process. How many tokens the same text produces depends on the model’s tokenizer, the language, and the type of content. Claude 4.7 and later models and Claude Mythos Preview (`claude-mythos-preview`) use a newer tokenizer that produces approximately 30 percent more tokens for the same text than earlier models. To see how many tokens a request uses on a specific model, count it with [Token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) and that model’s ID.
521521
522522### Are there free tiers or trials?
523523
agents-and-tools/agent-skills/quickstart Changed · +1 / -1 lines
from line 339
339339
340340The request includes the following parts:
341341
342* **`model`:** A [model that supports the code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compatibility)
342* **`model`:** A [model that supports the code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#availability-feature-support)
343343* **`container.skills`:** Specifies which Skills Claude can use
344344* **`type: "anthropic"`:** Indicates this is an Anthropic-managed Skill
345345* **`skill_id: "pptx"`:** The PowerPoint Skill identifier
build-with-claude/skills-guide Changed · +1 / -1 lines
from line 60
60601. **Claude API key** from the [Claude Console](https://platform.claude.com/settings/keys)
61612. **[Code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool)** enabled in your requests
6262
63Skills require the code execution tool, so use a model from its [model compatibility list](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compatibility).
63Skills require the code execution tool, so use a model listed in its [API support section](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#availability-feature-support).
6464
6565***
6666
manage-claude/access-transparency Changed · +1 / -0 lines
from line 94
9494| `workspace_id` | string or null | The workspace the content belongs to |
9595| `workspace_uuid` | string | The workspace the content belongs to. UUID format. Present when the access was scoped to a workspace, and absent otherwise. Not one of the transparency log’s [leaf fields](https://platform.claude.com/docs/en/manage-claude/access-transparency-log#how-an-event-becomes-a-leaf), so an inclusion proof does not cover it |
9696| `transparency_log_leaf_index` | integer | The event’s zero-based position in your organization’s transparency log (beta). Present whenever the event has a leaf, and absent otherwise. See [Verify Access Transparency events with the transparency log](https://platform.claude.com/docs/en/manage-claude/access-transparency-log) |
97| `user_profile_id` | string | The [user profile](https://platform.claude.com/docs/en/manage-claude/user-profiles) the accessed or preserved content was created under. Tagged ID format (`uprof_...`). Present only when the content was created under a user profile |
9798
9899Example JSON message:
99100
manage-claude/cmek-coverage-claude-enterprise Changed · +1 / -1 lines
from line 32
3232| Artifacts | Changed. Artifacts, including Claude Design, Claude Slides, and Claude Docs in conversations and the **Artifacts** tab, cannot be turned on in organizations that also use ZDR. In organizations with HIPAA readiness, an Owner must first accept the terms for using them. |
3333| Artifact publishing and sharing | Changed. Claude Code cannot [publish artifacts](https://code.claude.com/docs/en/artifacts#availability). However, artifacts made in chat or Cowork can be shared within your organization, but not publicly. |
3434| Standalone Claude Design app | Not supported. See [Encrypted with Anthropic’s key](https://platform.claude.com/docs/en/manage-claude/cmek-coverage-claude-enterprise#encrypted-with-anthropics-key). |
35| Analytics: smart reports and contribution metrics | Off. Certain analytics are disabled, regardless of admin settings: Claude smart reports (beta, under claude.ai/analytics/insights) and Claude Code contribution metrics from GitHub (beta, under claude.ai/analytics/claude-code). |
35| Analytics: smart reports and contribution metrics | Off. Certain analytics are disabled, regardless of admin settings: Claude smart reports (under claude.ai/analytics/insights) and Claude Code contribution metrics from GitHub (beta, under claude.ai/analytics/claude-code). |
3636| Analytics: skills and connectors | Changed. Admin analytics for skills and connectors, in the claude.ai analytics dashboard and through the [Claude Enterprise Analytics API](https://platform.claude.com/docs/en/manage-claude/analytics-api), don’t include usage in chat, and hide the names of custom skills, plugins, and connectors. |
3737| Response ratings (thumbs up and thumbs down) | Off. Members can’t rate Claude’s responses. |
3838| [Skill and plugin security scanning](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/enterprise#skill-content-scanning) | Off. The setting can’t be turned on, and skills and plugins are installed without a scan. |
manage-claude/inference-hooks Changed · +1 / -1 lines
from line 97
9797
9898* **Claude Security scans (beta).** [Claude Security](https://claude.com/product/claude-security) runs hosted scans on your connected repositories. A session a user opens to fix a finding, and the Claude Security plugin in Claude Code, are governed.
9999* **Code Review (research preview).** [Code Review](https://code.claude.com/docs/en/code-review) runs reviews on your GitHub pull requests. A review a user runs locally in Claude Code with `/code-review` is governed.
100* **Smart reports (beta).** Anthropic makes model calls to build your organization’s [smart reports](https://support.claude.com/en/articles/16893491-get-started-with-smart-reports). What a user types or uploads when creating a report is governed.
100* **Smart reports.** Anthropic makes model calls to build your organization’s [smart reports](https://support.claude.com/en/articles/16893491-get-started-with-smart-reports). What a user types or uploads when creating a report is governed.
101101
102102***
103103
models/fable-5-1/migration-guide Changed · +1 / -1 lines
from line 1207
12071207
12081208 Dropping thinking blocks once, at a compaction boundary for example, has little effect. An integration that invalidates prior thinking on every request restarts the prompt cache each time, which can raise cost per task (see [Keep the conversation history append-only](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#keep-the-conversation-history-append-only)).
12091209
12104. **The advisor tool accepts fewer advisors:** With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) (beta), the advisor must be at least as capable as the executor. With a `claude-fable-5-1` executor, a less capable advisor, such as `claude-fable-5` or `claude-opus-5-5`, returns a 400 `invalid_request_error`. Choose an advisor from the executor’s row in the [compatibility table](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility).
12104. **The advisor tool accepts fewer advisors:** With the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) (beta), the advisor must be at least as capable as the executor. With a `claude-fable-5-1` executor, a less capable advisor, such as `claude-fable-5` or `claude-opus-5-5`, returns a 400 `invalid_request_error`. Choose an advisor that [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) lists for the executor.
12111211
12121212### Behavior changes
12131213
models/haiku-5-5/migration-guide Changed · +1 / -1 lines
from line 127
127127
128128Claude 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.
129129
130To 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 [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section.
130To 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.
131131
132132On 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.
133133
models/opus-5-5/migration-guide Changed · +2 / -2 lines
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 [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) section for other platforms.
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.
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 880
880880
881881#### The `computer_20251124` computer use tool is not supported on the Claude API and Claude Models on Google Cloud (Google managed)
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 [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) 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).
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).
884884
885885Before. 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:
886886
models/opus-5-5/whats-new-opus-5-5 Changed · +1 / -1 lines
from line 56
5656'claude-opus-5-5' does not support tool types: computer_20251124.
5757```
5858
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 [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) 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).
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).
6060
6161## Feature support
6262
models/sonnet-5-5/migration-guide Changed · +1 / -1 lines
from line 854
854854
855855If 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.
856856
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 [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility).
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).
858858
859859### The advisor tool accepts fewer advisors
860860
models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +1 / -1 lines
from line 66
6666
6767On Amazon Bedrock, Claude Sonnet 5.5 accepts the earlier `computer_20251124` tool.
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 [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) 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.
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.
7070
7171### Some advisor tool pairings are not supported
7272
release-notes/overview Changed · +1 / -1 lines
from line 284
284284
285285### June 18, 2026
286286
287* The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for `code_execution_20260120`, the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) version that adds REPL state persistence and is the minimum version for [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling). To adopt it, set the tool’s `type` to `code_execution_20260120`; no beta header is required. It’s available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.5 and newer, and Claude Sonnet 4.5 and newer; see the code execution tool’s [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compatibility) section.
287* The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for `code_execution_20260120`, the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) version that adds REPL state persistence and is the minimum version for [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling). To adopt it, set the tool’s `type` to `code_execution_20260120`; no beta header is required. It’s available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.5 and newer, and Claude Sonnet 4.5 and newer; see the code execution tool’s [API support](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#availability-feature-support) section.
288288
289289### June 15, 2026
290290