thinking changedbuild-with-claude/thinking
Nearest release: v2.1.321, published under 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+21added
Lines−15removed
From line
8
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits42to this page, all time
The whole hunk
from line 8, old and new numbered
/
from line 8
88 eligibility: eligible
99 note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
1010 supportedModels:
11 - claude-fable-5-2
12 - claude-mythos-5-2
1113 - claude-fable-5-1
1214 - claude-mythos-5-1
1315 - claude-fable-5
from line 87
8587| Claude Opus 5.5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
8688| Claude Sonnet 5.5 | Adaptive thinking | Adaptive thinking | 400 error | Up-front thinking off at `high` effort or below | 400 error |
8789| Claude Haiku 5.5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | Thinking off at `high` effort or below |
90| Claude Fable 5.2 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
91| Claude Mythos 5.2 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
8892| Claude Fable 5.1 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
8993| Claude Mythos 5.1 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
9094| Claude Fable 5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |
from line 498
494498
495499Claude Haiku 5.5 also has thinking on by default and accepts `thinking: {type: "disabled"}` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. At `xhigh` or `max` effort, that combination returns a 400 error. To get less thinking, lower the effort level first. With thinking off, the model can skip a tool call it needs when you also request JSON output. A [per-message `output_config.effort`](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) that differs from the level in effect also returns a 400 error while thinking is off. See [Use effort to control thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5#use-effort-to-control-thinking) and [Use adaptive thinking with JSON output and your own tools](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5#json-output-with-your-own-tools).
496500
497Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, and Claude Mythos Preview reject `thinking: {type: "disabled"}`. Thinking can’t be turned off on these models.
501Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, and Claude Mythos Preview reject `thinking: {type: "disabled"}`. Thinking can’t be turned off on these models.
498502
499503To check whether a model accepts `"disabled"` or `"between_tools"` before you send a request, read its `capabilities.thinking.types.disabled.supported` or `capabilities.thinking.types.between_tools.supported` value from the Models API. [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api) describes both fields.
500504
from line 511
507511The `display` field on the thinking configuration controls how thinking content is returned in API responses. `display` works in both modes: set it alongside `type: "adaptive"` or `type: "enabled"`. It accepts these values:
508512
509513* `"summarized"`: thinking blocks contain [summarized thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#summarized-thinking) text, a readable summary of Claude’s reasoning. This is the default on Claude Opus 4.6, Claude Sonnet 4.6, and earlier models.
510* `"omitted"`: thinking blocks are returned with an empty `thinking` field. The `signature` field still carries the encrypted full thinking for multi-turn continuity (see [Thinking encryption](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-encryption)). This is the default on Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, [Claude Mythos Preview](https://anthropic.com/glasswing), and Claude Haiku 5.5.
514* `"omitted"`: thinking blocks are returned with an empty `thinking` field. The `signature` field still carries the encrypted full thinking for multi-turn continuity (see [Thinking encryption](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-encryption)). This is the default on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, [Claude Mythos Preview](https://anthropic.com/glasswing), and Claude Haiku 5.5.
511515* `"updates"` (beta): reasoning blocks are returned with an empty `thinking` field, as with `"omitted"`, and the short [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) some models write between tool calls come back as readable text. Requires the beta header `thinking-display-updates-2026-08-18`.
512516
513517Set `display: "omitted"` when your application doesn’t surface thinking content to users. The primary benefit is faster time-to-first-text-token when streaming: the server skips streaming thinking tokens entirely and delivers only the signature, so the final text response starts streaming sooner.
from line 561
557561 In rare cases where you need access to full thinking output, [contact Anthropic sales](mailto:[email protected]).
558562</Note>
559563
560To see the model’s reasoning, read the `thinking` blocks rather than prompting for reasoning in the response text. On Claude Fable 5.1, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Fable 5, a request that attempts to elicit the model’s internal reasoning as part of the response text might be refused with `stop_details.category: "reasoning_extraction"`. See [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the field reference and [Keep reasoning in thinking blocks](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#keep-reasoning-in-thinking-blocks) for what to ask for instead.
564To see the model’s reasoning, read the `thinking` blocks rather than prompting for reasoning in the response text. On Claude Fable 5.2, Claude Fable 5.1, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Fable 5, a request that attempts to elicit the model’s internal reasoning as part of the response text might be refused with `stop_details.category: "reasoning_extraction"`. See [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the field reference and [Keep reasoning in thinking blocks](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#keep-reasoning-in-thinking-blocks) for what to ask for instead.
561565
562566### Streaming thinking
563567
from line 940
936940
937941Thinking works alongside [tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), letting Claude reason through tool selection and process tool results. Two constraints apply:
938942
9391. **Tool choice limitation (manual mode):** tool use with manual extended thinking (`thinking: {type: "enabled"}`) only supports `tool_choice: {"type": "auto"}` (the default) or `tool_choice: {"type": "none"}`. Using `tool_choice: {"type": "any"}` or `tool_choice: {"type": "tool", "name": "..."}` results in an error because these options force tool use, which is incompatible with manual extended thinking. Adaptive thinking, including on models where thinking is on by default, supports forced tool use, except on Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1 (see [Response prefill and forced tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#limits-and-feature-compatibility)). Where forced tool use is accepted, the response starts with the tool call and has no `thinking` block.
9431. **Tool choice limitation (manual mode):** tool use with manual extended thinking (`thinking: {type: "enabled"}`) only supports `tool_choice: {"type": "auto"}` (the default) or `tool_choice: {"type": "none"}`. Using `tool_choice: {"type": "any"}` or `tool_choice: {"type": "tool", "name": "..."}` results in an error because these options force tool use, which is incompatible with manual extended thinking. Adaptive thinking, including on models where thinking is on by default, supports forced tool use, except on Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1 (see [Response prefill and forced tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#limits-and-feature-compatibility)). Where forced tool use is accepted, the response starts with the tool call and has no `thinking` block.
9409442. **Preserving thinking blocks:** when you return tool results, you must pass the thinking blocks from the assistant message back to the API, complete and unmodified. See [Preserving thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks).
941945
942946**A tool-use loop is one assistant turn.** From the model’s perspective, an assistant turn ends only when Claude completes its full response, which might include multiple tool calls and results. This whole sequence is a single assistant turn:
from line 1004
10001004 Consecutive tool calls do not require interleaved thinking. Claude can chain tool calls with or without interleaved thinking. Interleaving changes where thinking blocks appear between tool calls, not whether tool calls can chain.
10011005</Note>
10021006
1003With adaptive thinking, interleaved thinking is automatic on every model that supports adaptive thinking. No beta header is needed. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Opus 4.8, and Claude Opus 4.7, reasoning between tool calls always appears in thinking blocks. Claude Haiku 4.5 does not support interleaved thinking. On models using manual extended thinking, interleaving requires a beta header and changes how the thinking budget is counted. [Interleaved thinking in manual mode](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#interleaved-thinking) covers the per-model rules and platform-specific header behavior.
1007With adaptive thinking, interleaved thinking is automatic on every model that supports adaptive thinking. No beta header is needed. On Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Opus 4.8, and Claude Opus 4.7, reasoning between tool calls always appears in thinking blocks. Claude Haiku 4.5 does not support interleaved thinking. On models using manual extended thinking, interleaving requires a beta header and changes how the thinking budget is counted. [Interleaved thinking in manual mode](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#interleaved-thinking) covers the per-model rules and platform-specific header behavior.
10041008
10051009With interleaved thinking, the thinking allocation can span the entire assistant turn rather than a single response. Interleaved thinking is only supported for [tools used through the Messages API](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
10061010
from line 1012
10081012
10091013### Progress updates between tool calls
10101014
1011On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Fable 5, the model can write a progress update between tool calls. A progress update is a note on what the model just found and what it’s about to do next, written for the person watching the agent rather than as reasoning. Each one comes back as its own `thinking` block with its own `signature`, separate from any reasoning block at the same point. It sits immediately before the `tool_use` or `server_tool_use` block it introduces. At most one progress update precedes each tool call, and the model can skip any of them. Progress updates aren’t [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking): they appear whether or not reasoning blocks appear between tool calls, and a response can contain both.
1015On Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Fable 5, the model can write a progress update between tool calls. A progress update is a note on what the model just found and what it’s about to do next, written for the person watching the agent rather than as reasoning. Each one comes back as its own `thinking` block with its own `signature`, separate from any reasoning block at the same point. It sits immediately before the `tool_use` or `server_tool_use` block it introduces. At most one progress update precedes each tool call, and the model can skip any of them. Progress updates aren’t [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking): they appear whether or not reasoning blocks appear between tool calls, and a response can contain both.
10121016
10131017What a progress-update block contains depends on [`display`](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display):
10141018
from line 1086
10821086* A progress-update block can come back with an empty `thinking` field under any `display` value. Render nothing for an empty block. Under `"updates"` it looks the same as an empty reasoning block and needs no separate handling.
10831087* When a response stops on `max_tokens`, `model_context_window_exceeded`, or `stop_sequence` soon after a tool call or tool result, its last block can be a progress-update block standing in for the work the model hadn’t completed. Under `"updates"` and `"summarized"` its text is exactly `This part of the response was interrupted before it finished.` and you can show it like any other update. Under `"omitted"` it’s empty. To continue, pass the assistant turn back unchanged and append a new `user` message (with a `tool_result` for each `tool_use` block in that turn).
10841088* When [streaming](https://platform.claude.com/docs/en/build-with-claude/thinking#streaming-thinking), expect a pause of several seconds before a progress-update block opens. See the `"updates"` trace in [Streaming thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#streaming-thinking).
1085* These models write fewer progress updates at higher [effort](https://platform.claude.com/docs/en/build-with-claude/effort) and in long tool chains. If your interface depends on them, see [Ask for user-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#ask-for-user-facing-progress-updates). For Claude Opus 5.5 and Claude Sonnet 5.5, see User-facing progress updates in [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates) or [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#user-facing-progress-updates).
1089* These models write fewer progress updates at higher [effort](https://platform.claude.com/docs/en/build-with-claude/effort) and in long tool chains. If your interface depends on them, see [Ask for user-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#ask-for-user-facing-progress-updates). For Claude Opus 5.5 and Claude Sonnet 5.5, see User-facing progress updates in [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates) or [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#user-facing-progress-updates). For Claude Fable 5.2, see [Keep users informed during long turns](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#keep-users-informed-during-long-turns).
10861090
10871091### Thinking block preservation by model
10881092
10891093Whether thinking blocks from previous assistant turns stay in context by default depends on the model:
10901094
1091* **Keep all prior turns:** Claude Opus 4.5 and later Opus models, Claude Sonnet 4.6 and later Sonnet models, Claude Haiku 5.5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview.
1095* **Keep all prior turns:** Claude Opus 4.5 and later Opus models, Claude Sonnet 4.6 and later Sonnet models, Claude Haiku 5.5, Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview.
10921096* **Keep only the turn in progress (last-turn-only models):** earlier Opus and Sonnet models, and all Haiku models through Claude Haiku 4.5. When you pass older thinking blocks back, the API strips them automatically. You don’t need to remove them yourself.
10931097
10941098Preservation brings two benefits:
from line 1102
10981102
10991103The tradeoff is context usage: long conversations consume more context space on keep-all models, because retained thinking blocks count as input like any other conversation history (see [Thinking and the context window](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-the-context-window)). The behavior is automatic in both regimes. No code changes or beta headers are required, and you should keep passing complete, unmodified thinking blocks back as described in [Preserving thinking blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks). To override the default in either direction, use [thinking block clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#thinking-block-clearing).
11001104
1101**Switching models mid-conversation.** Keep passing thinking blocks back unchanged when you switch models, for example after a [classifier refusal fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback). A thinking block is readable only by the model that produced it and certain other models, and the API ignores or drops the blocks the target model can’t read. On Claude Fable 5.1 and Claude Mythos 5.1 the direction matters: they read earlier models’ thinking blocks, and only the two of them read each other’s, so switching to them keeps the conversation’s reasoning and switching from them to any other model drops it (see [how dropped blocks are billed and reported](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)). Claude Opus 5.5 reads Claude Opus 5’s thinking blocks and those of earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), of Claude Sonnet 5.5 and Claude Haiku 5.5, but not those of the Claude Fable and Claude Mythos models; on the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5’s blocks. A switch from Claude Opus 5.5 up to Claude Fable 5.1 on the Claude API keeps the earlier turns’ reasoning; a switch from Claude Fable 5.1 to Claude Opus 5.5 drops it. Claude 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, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On those two platforms, Claude Opus 5.5 reads Claude Sonnet 5.5’s blocks and no other model does: a switch from Claude Sonnet 5.5 up to Claude Opus 5.5 there keeps the earlier turns’ reasoning, and any other switch away from Claude Sonnet 5.5 drops it. Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5’s blocks and no other model does. Strip prior `thinking` and `redacted_thinking` blocks yourself only to save input tokens on models that ignore rather than drop them, and never when redeeming a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit), which requires the body unchanged.
1105**Switching models mid-conversation.** Keep passing thinking blocks back unchanged when you switch models, for example after a [classifier refusal fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback). A thinking block is readable only by the model that produced it and certain other models, and the API ignores or drops the blocks the target model can’t read. On Claude Fable 5.1 and Claude Mythos 5.1 the direction matters: they read earlier models’ thinking blocks, and only they and, on the Claude API, Claude Fable 5.2 and Claude Mythos 5.2 read those two models’ blocks, so switching to them keeps the conversation’s reasoning and switching from them to any model outside that group drops it (see [how dropped blocks are billed and reported](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models)). Claude Opus 5.5 reads Claude Opus 5’s thinking blocks and those of earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), of Claude Sonnet 5.5 and Claude Haiku 5.5, but not those of the Claude Fable and Claude Mythos models; on the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5’s blocks. A switch from Claude Opus 5.5 up to Claude Fable 5.1 on the Claude API keeps the earlier turns’ reasoning; a switch from Claude Fable 5.1 to Claude Opus 5.5 drops it. On the Claude API, Claude Fable 5.2 and Claude Mythos 5.2 read each other’s thinking blocks and those from other models, including Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. No other model reads their blocks, so a switch from either of them to any other model drops the earlier turns’ reasoning. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. Claude 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, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On those two platforms, Claude Opus 5.5 reads Claude Sonnet 5.5’s blocks, as do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API, and no other model does: a switch from Claude Sonnet 5.5 up to Claude Opus 5.5 there, or to Claude Fable 5.2 or Claude Mythos 5.2 where they read Claude Sonnet 5.5 blocks, keeps the earlier turns’ reasoning, and any other switch away from Claude Sonnet 5.5 drops it. Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5’s blocks, as do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API, and no other model does. Strip prior `thinking` and `redacted_thinking` blocks yourself only to save input tokens on models that ignore rather than drop them, and never when redeeming a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit), which requires the body unchanged.
11021106
11031107## Preserved thinking
11041108
from line 1111
11071111* **The model that produced it.** Each model reads its own thinking blocks and those of a fixed set of other models. Claude Fable 5.1 reads blocks from Claude Opus 5 and, on the Claude API, from Claude Opus 5.5; neither Claude Opus 5 nor Claude Opus 5.5 reads blocks from Claude Fable 5.1. The API drops a block the current model can’t read, without an error and without billing it. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
11081112* **Everything sent before it.** A block stays valid only while the top-level `system` prompt, the `tools`, and the messages before it are unchanged. If any of them changes, that block and every later thinking block fail the prefix check. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check).
11091113
1110Thinking blocks from Claude Sonnet 5.5 and Claude Haiku 5.5 are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) for where this applies.
1114Thinking blocks from Claude Sonnet 5.5, Claude Haiku 5.5, Claude Fable 5.2, and Claude Mythos 5.2 are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) for where this applies.
11111115
1112The prefix check runs on Claude 5.1 and later models. Make your integration append-only so that the thinking blocks you send back pass it. [What the API does with an invalid block](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior) covers what happens when one fails.
1116The prefix check runs on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. Make your integration append-only so that the thinking blocks you send back pass it. [What the API does with an invalid block](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior) covers what happens when one fails.
11131117
11141118To keep thinking valid, send every assistant turn back exactly as you received it and add new messages only at the end of `messages`. If your code builds the `messages` array itself, the Preserved thinking page covers:
11151119
from line 1197
11931197* When [streaming responses](https://platform.claude.com/docs/en/build-with-claude/thinking#streaming-thinking), the signature arrives as a `signature_delta` inside a `content_block_delta` event just before the `content_block_stop` event.
11941198* `signature` values are significantly longer in Claude 4 and later models than in previous models.
11951199* The `signature` field is opaque: don’t interpret or parse it.
1196* `signature` values are compatible across platforms, including the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). Values generated on one platform work on another, except that thinking blocks from Claude Sonnet 5.5 and Claude Haiku 5.5 work only in the account that produced them or in an account linked to it. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
1200* `signature` values are compatible across platforms, including the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). Values generated on one platform work on another, except that thinking blocks from Claude Sonnet 5.5, Claude Haiku 5.5, Claude Fable 5.2, and Claude Mythos 5.2 work only in the account that produced them or in an account linked to it. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
11971201
11981202## Redacted thinking blocks
11991203
from line 1224
12201224
12211225### Sampling parameters
12221226
1223On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Haiku 5.5, non-default `temperature`, `top_p`, or `top_k` values return a 400 error on every request, regardless of whether thinking is used. On these models, the `top_p` default is `0.99`, so a `top_p` of `1` returns a 400 error, and so does a request that includes both `temperature` and `top_p`, even at their defaults. See [Remove sampling parameters](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters). Starting with [API version `2026-10-21`](https://platform.claude.com/docs/en/api/migration-2026-10-21#sampling-parameters), a request that includes `temperature`, `top_p`, or `top_k` at any value returns a 400 error on every model. On older models in API versions before `2026-10-21`, the restriction applies only while thinking is on: `temperature` and `top_k` are incompatible with thinking, and `top_p` is allowed at values between 0.95 and 1.
1227On Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Haiku 5.5, non-default `temperature`, `top_p`, or `top_k` values return a 400 error on every request, regardless of whether thinking is used. On these models, the `top_p` default is `0.99`, so a `top_p` of `1` returns a 400 error, and so does a request that includes both `temperature` and `top_p`, even at their defaults. See [Remove sampling parameters](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#remove-sampling-parameters). Starting with [API version `2026-10-21`](https://platform.claude.com/docs/en/api/migration-2026-10-21#sampling-parameters), a request that includes `temperature`, `top_p`, or `top_k` at any value returns a 400 error on every model. On older models in API versions before `2026-10-21`, the restriction applies only while thinking is on: `temperature` and `top_k` are incompatible with thinking, and `top_p` is allowed at values between 0.95 and 1.
12241228
12251229### Response prefill and forced tool use
12261230
1227Claude 4.6 and later models and Claude Mythos Preview reject a prefilled final assistant turn with a 400 error, whether or not thinking is on (see [Prefill not supported](https://platform.claude.com/docs/en/api/errors#prefill-not-supported)). On earlier models, you can’t prefill the assistant response while thinking is on. Forced tool use (`tool_choice: {"type": "any"}` or `{"type": "tool", ...}`) is incompatible with manual extended thinking but works with adaptive thinking. The exceptions are Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1, which reject forced tool use on every request with a 400 error. On those models, use `tool_choice: {"type": "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) instead. Where forced tool use is accepted, the response starts with the tool call and has no `thinking` block. To let the model think before it calls a tool, use `tool_choice: {"type": "auto"}` and say in the prompt when to use the tool. See [Thinking with tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use).
1231Claude 4.6 and later models and Claude Mythos Preview reject a prefilled final assistant turn with a 400 error, whether or not thinking is on (see [Prefill not supported](https://platform.claude.com/docs/en/api/errors#prefill-not-supported)). On earlier models, you can’t prefill the assistant response while thinking is on. Forced tool use (`tool_choice: {"type": "any"}` or `{"type": "tool", ...}`) is incompatible with manual extended thinking but works with adaptive thinking. The exceptions are Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, which reject forced tool use on every request with a 400 error. On those models, use `tool_choice: {"type": "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) instead. Where forced tool use is accepted, the response starts with the tool call and has no `thinking` block. To let the model think before it calls a tool, use `tool_choice: {"type": "auto"}` and say in the prompt when to use the tool. See [Thinking with tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use).
12281232
12291233### Output limits
12301234
from line 1236
12321236
12331237| Model | Max output tokens | Batches beta ceiling |
12341238| :-------------------- | :---------------- | :------------------- |
1239| Claude Fable 5.2 | 128K | — |
1240| Claude Mythos 5.2 | 128K | — |
12351241| Claude Fable 5.1 | 128K | — |
12361242| Claude Mythos 5.1 | 128K | — |
12371243| Claude Fable 5 | 128K | — |
No line in this hunk matches that.