preserved-thinking changedbuild-with-claude/preserved-thinking
Nearest release: v2.1.293, published 2 hours after 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+4added
Lines−2removed
From line
4
where the diff opens
First seen
1 Sep 2026
this site's first read of the page
Recorded edits22to this page, all time
The whole hunk
from line 4, old and new numbered
/
from line 4
44description: Preserved thinking lets a model use a thinking block from an earlier turn only if that model or one of a fixed set of other models produced it and nothing before the block has changed.
55---
66
7Preserved thinking is a property of newer Claude models that guards against distillation. It decides whether the model can use a thinking block that you send back from an earlier turn. Starting with Claude Fable 5.1, when a `thinking` or `redacted_thinking` block comes back in a request, the API checks the block's `signature` for two things:
7Preserved thinking is a property of newer Claude models that guards against distillation. It determines whether the model can use a thinking block that you send back from an earlier turn. Starting with Claude Fable 5.1, when a `thinking` or `redacted_thinking` block comes back in a request, the API checks the block's `signature` for two things:
88
99* **The model can read the block.** 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. If the current model can't read a block, the API drops it from that request without an error. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
1010* **Nothing before the thinking block has changed.** The top-level `system` prompt, `tools`, and `messages` before the block are its prefix. If the prefix differs from what you sent when the block was produced, that block and every later thinking block are invalid, and the API rejects the request with a 400 error or drops the invalid blocks, whichever you choose. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check).
from line 1247
12471247
12481248All of these assume you [send assistant turns back exactly as returned](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#append-assistant-turns-exactly-as-returned). Mid-conversation system messages, turn-scoped system messages, and tool changes aren't available on every model: [Mid-conversation system messages and tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) lists the models that accept them. If your code serves several models, keep editing the top-level `system` prompt for the models that don't accept them.
12491249
1250To use several betas in one request, combine the values in one `anthropic-beta` header. Beta names are the same on Amazon Bedrock and Google Cloud wherever the beta is available there (see [Beta headers](https://platform.claude.com/docs/en/api/beta-headers)):
1250To use several betas in one request on the Claude API, combine their names in one `anthropic-beta` header:
12511251
12521252```text wrap
12531253anthropic-beta: thinking-binding-controls-2026-08-01,mid-conversation-system-clear-at-2026-08-21,inline-tools-2026-09-15
12541254```
1255
1256Other platforms that offer these betas use the same names. To send them there, see [Beta features on other platforms](https://platform.claude.com/docs/en/api/beta-headers#beta-features-on-other-platforms).
12551257
12561258### Send assistant turns back exactly as returned
12571259
No line in this hunk matches that.