migration-guide changedmodels/sonnet-5-5/migration-guide
Nearest release: v2.1.309, published an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+15added
Lines−15removed
From line
475
where the diff opens
First seen
29 Sep 2026
this site's first read of the page
Recorded edits16to this page, all time
### Computer use needs the toolset on the Claude API and Claude Models on Google Cloud (Google managed) ### Computer use needs the toolset on the Claude API and Google Cloud
The whole hunk
from line 475, old and new numbered
/
from line 475
475475* 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.
476476* Replace [forced tool use](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#forced-tool-use) with `auto` and strict tools.
477477* Keep conversations [append-only](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#thinking-blocks).
478* On the Claude API and Google Cloud, 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.
478* 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.
479479* 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.
480480* Read [text between tool calls](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#text-between-tool-calls) from `thinking` blocks.
481481* [Handle refusals](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#safety-classifiers-and-fallback), and configure fallback.
from line 842
842842
843843### Thinking blocks are tied to the model and the conversation
844844
845Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Google Cloud, from Claude Haiku 5.5. It doesn't read blocks from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. The API drops blocks the model can't read. The request still returns 200, and dropped blocks aren't billed. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
845Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5. It doesn't read blocks from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. The API drops blocks the model can't read. The request still returns 200, and dropped blocks aren't billed. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
846846
847Each Claude Sonnet 5.5 thinking block is also signed over the conversation before it. For accounts created on or after August 31, 2026, 00:00 UTC, the API enforces this by default, on the Claude API, Amazon Bedrock, and Google Cloud. On those accounts, a request that replays a block after an edit to earlier history returns a 400 error. 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). 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).
847Each Claude Sonnet 5.5 thinking block is also signed over the conversation before it. For accounts created on or after August 31, 2026, 00:00 UTC, the API enforces this by default, on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed). On those accounts, a request that replays a block after an edit to earlier history returns a 400 error. 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). 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).
848848
849### Computer use needs the toolset on the Claude API and Google Cloud
849### Computer use needs the toolset on the Claude API and Claude Models on Google Cloud (Google managed)
850850
851On the Claude API and Google Cloud, 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:
851On 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:
852852
853| Version you send today | Starting models that send it | Send on the Claude API and Google Cloud | Send on Amazon Bedrock |
854| ---------------------- | ---------------------------------------------------- | --------------------------------------- | ---------------------- |
855| `computer_20251124` | Claude Sonnet 5, Claude Sonnet 4.6 | `computer_toolset_20260801` | `computer_20251124` |
856| `computer_20250124` | Claude Sonnet 4.5, Claude Haiku 4.5, Claude Sonnet 4 | `computer_toolset_20260801` | `computer_20251124` |
853| 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 |
854| ---------------------- | ---------------------------------------------------- | ------------------------------------------------------------------------- | ---------------------- |
855| `computer_20251124` | Claude Sonnet 5, Claude Sonnet 4.6 | `computer_toolset_20260801` | `computer_20251124` |
856| `computer_20250124` | Claude Sonnet 4.5, Claude Haiku 4.5, Claude Sonnet 4 | `computer_toolset_20260801` | `computer_20251124` |
857857
858858If 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.
859859
from line 879
879879* **`"reasoning_extraction"`:** The request asks the model to reproduce its internal reasoning in the response text.
880880* **`"general_harms"`:** The request falls under another usage-policy area. Benign work can also trigger this category.
881881
882[Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`, beta, Claude API only) retries `"cyber"` and `"frontier_llm"` declines on Claude Sonnet 5. It doesn't retry `"bio"`, `"reasoning_extraction"`, or `"general_harms"` declines. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) and [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
882[Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`), in beta on the Claude API and on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), retries `"cyber"` and `"frontier_llm"` declines on Claude Sonnet 5. It doesn't retry `"bio"`, `"reasoning_extraction"`, or `"general_harms"` declines. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) and [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).
883883
884884Real-time cyber safeguards are new for code from Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5. For legitimate security work, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus-and-sonnet).
885885
from line 1231
12311231
12321232### Migrating from Claude Sonnet 4 or earlier
12331233
1234Claude Sonnet 4 is retired on the Claude API and still available on Amazon Bedrock and Google Cloud. Claude 3.7 Sonnet is retired. From either model, first apply every preceding section, then these changes:
1234Claude Sonnet 4 is retired on the Claude API and still available on Amazon Bedrock and Claude Models on Google Cloud (Google managed). Claude 3.7 Sonnet is retired. From either model, first apply every preceding section, then these changes:
12351235
12361236* **Tool versions:** Use `text_editor_20250728`, with the tool name `str_replace_based_edit_tool` and no `undo_edit` command. Use `code_execution_20260521`. See the [text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool) and the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#upgrade-to-latest-tool-version).
12371237* **Stop reasons:** Handle `refusal`. Claude 4.5 and later models also stop with `model_context_window_exceeded` at the context window limit. See [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).
No line in this hunk matches that.