One read of Claude Developer Platformapi-20261006T050710Z
3 pages moved out of 753 read.
Pages moved
3
significant first
Pages read
753
in this capture
Captured
05:07 UTC
Corpus hash
eb589c66bd06
corpus-hash
What this read moved
1-3 of 3models/opus-5-5/migration-guide Changed · +4 / -4 lines
from line 31
3131* **Effort:** Control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort), the only request parameter that controls it. All five levels (`low`, `medium`, `high`, `xhigh`, `max`) are supported, and the default is `medium`. See [Recommended effort levels for Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-opus-5-5).
3232* **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).
3333* **Sampling parameters:** Omit `temperature`, `top_p`, and `top_k`, or leave them at their defaults: any other value is rejected. Use prompting to guide the model's behavior.
34* **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.
34* **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. On Amazon Bedrock, structured outputs aren't available for Claude Opus 5.5, so use system prompt instructions there.
3535* **Computer use:** On the Claude API and Google Cloud, 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).
3636* **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.
3737
from line 284
284284* Update the model ID to `claude-opus-5-5`.
285285* Remove `thinking: {"type": "disabled"}` and `thinking: {"type": "enabled", ...}`; choose an effort level instead.
286286* Set `effort` explicitly: the default is `medium`, where Claude Opus 5's is `high`.
287* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.
287* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs, or with `auto` alone on Amazon Bedrock.
288288* If you use computer use on the Claude API or Google Cloud, 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.
289289* 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 Google Cloud, from Claude Sonnet 5.5, but not from Claude Fable or Claude Mythos models.
290290* Read content blocks by `type`, and pass `thinking` blocks back unmodified in tool-use loops.
from line 568
568568
569569#### Forced tool use is not supported
570570
571`tool_choice` types `any` and `tool` return a 400 error (`tool_choice: type "tool" and "any" are not supported for this model.`), including on the token counting endpoint. Use `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), and say in the prompt when the tool applies. Strict tool use accepts a subset of JSON Schema, so check each tool's `input_schema` before you add `strict: true`. Every object in the schema must set `additionalProperties: false`; see [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations). See [Forced tool use is not supported](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported).
571`tool_choice` types `any` and `tool` return a 400 error (`tool_choice: type "tool" and "any" are not supported for this model.`), including on the token counting endpoint. Use `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), and say in the prompt when the tool applies. Strict tool use accepts a subset of JSON Schema, so check each tool's `input_schema` before you add `strict: true`. Every object in the schema must set `additionalProperties: false`; see [JSON Schema limitations](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#json-schema-limitations). On Amazon Bedrock, structured outputs, which include strict tool use, aren't available for Claude Opus 5.5. There, send `auto` without `strict`, say in the prompt when the tool applies, and validate the tool input in your code. See [Forced tool use is not supported](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported).
572572
573573Before. Claude Opus 5 accepts this request, and Claude Opus 5.5 rejects it with a 400 error:
574574
from line 1511
15111511
15121512 Update your `max_tokens` parameters to give additional headroom, including compaction triggers, and re-test any code path that estimates tokens client-side or assumes a fixed token-to-character ratio. Use the [Token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting) to verify. Prompting interventions, [`task_budget`](https://platform.claude.com/docs/en/build-with-claude/task-budgets), and [`effort`](https://platform.claude.com/docs/en/build-with-claude/effort) can help control costs; these controls may trade off model intelligence.
15131513
15145. **Prefill removal (already in effect on Claude Opus 4.6):** Prefilling assistant messages returns a 400 error on Claude Opus 4.6 and later Opus models, including Claude Opus 5.5, so this is a change only if you come from Claude Opus 4.5 or earlier. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), system prompt instructions, or `output_config.format` instead.
15145. **Prefill removal (already in effect on Claude Opus 4.6):** Prefilling assistant messages returns a 400 error on Claude Opus 4.6 and later Opus models, including Claude Opus 5.5, so this is a change only if you come from Claude Opus 4.5 or earlier. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) or system prompt instructions instead. On Amazon Bedrock, structured outputs aren't available for Claude Opus 5.5, so use system prompt instructions there.
15151515
15161516### Behavior changes
15171517
manage-claude/inference-hooks Changed · +1 / -1 lines
from line 79
7979
8080One hook governs conversations across claude.ai, Cowork, Claude Code, and Claude Tag sessions in your Claude Enterprise organization, whether they run on the web, in the desktop or mobile apps, in the CLI, or in Slack. Inference hooks are not available on Amazon Bedrock or Google Cloud.
8181
82Governed requests are the inference requests behind the user's conversation. Ancillary requests, such as conversation title generation, aren't sent to your endpoint, and system prompts and tool definitions are never included in what is sent. Voice mode is not covered.
82Governed requests are the inference requests behind the user's conversation. Ancillary requests aren't sent to your endpoint. These include conversation title generation and a measurement that Anthropic runs on Claude's reply after Claude Tag has posted it in Slack. System prompts and tool definitions are never included in what is sent. Voice mode is not covered.
8383
8484With **Validate tool calls** on, `tool_call` events may leave out calls to some of claude.ai's own tools, such as tools that suggest connectors or skills, give Claude the user's local time, or read the user's own past chats and saved memory. These calls and their results stay in the conversation, so the next `prompt` event from that conversation, if there is one, includes them.
8585
models/sonnet-5-5/migration-guide Changed · +1 / -1 lines
from line 1213
12131213
12141214Replace each prefill according to what it was for:
12151215
1216* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification.
1216* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification. On Amazon Bedrock, structured outputs aren't available for Claude Sonnet 5.5. There, describe the format in the prompt or use a tool without `strict`, and validate the output in your code.
12171217* **Preambles:** ask in the system prompt for a direct answer.
12181218* **Unwanted refusals:** clear instructions in the user message are usually enough.
12191219* **Continuations:** move them to the user message, for example "Your previous response was interrupted and ended with `[previous_response]`. Continue from where you left off."