# reasoning_extraction: why 'show your reasoning' gets refused

> On Sonnet 5.5 and Opus 5.5, asking the model to reproduce its reasoning can return a reasoning_extraction refusal. Read summarized thinking instead.

URL: https://bartlomiejkrupa.dev/notes/reasoning-extraction-refusal/
Category: concept | Updated: 2026-10-07
Summary: On Sonnet 5.5 and Opus 5.5, asking the model to reproduce its reasoning can return a reasoning_extraction refusal. Read summarized thinking instead.

**`reasoning_extraction`** is a refusal category on Claude Sonnet 5.5 and Claude Opus 5.5. Both models run safety classifiers that check each request; when one matches, the API returns a refusal instead of an answer. This category fires when a request asks the model to reproduce its internal reasoning in the response text. The decline arrives as a normal HTTP 200 response with `stop_reason: "refusal"` and `stop_details.category: "reasoning_extraction"` - a [refusal as an API contract](/notes/refusal-as-api-contract), not an error.

## What triggers it

Prompts written for setups with thinking off, where the only way to get reasoning was to ask for it in the output: "include your reasoning in the response", or a required reasoning section standing in for thinking. The Opus 5.5 guide lists `reasoning_extraction` among its safeguard categories, so a prompt that worked on an older model can be refused now - and since September 2026 a `reasoning_extraction` refusal before any output is billed.

## Why it hurts more than other refusals

Some refusals get retried for you. With server-side fallback (a beta API option), the API re-runs a declined request on another model. On Sonnet 5.5 that covers `cyber` declines (requests that could enable cyber harm) and `frontier_llm` declines (requests that could help develop competing AI models). It does **not** cover `reasoning_extraction` on either model - the refusal comes straight back to your code.

## Fix

1. Remove the instruction from the prompt.
2. Read the reasoning from the response's thinking blocks instead. Thinking blocks are separate content blocks that carry the model's reasoning; `adaptive` thinking lets the model decide how much to think, and `display: "summarized"` returns a readable summary of it:

```json
{ "thinking": { "type": "adaptive", "display": "summarized" } }
```


In context: [Claude 5.5 prompt audit: the bad lines weren't there](/articles/claude-5-5-prompt-audit).

Sources:
- Prompting Claude Sonnet 5.5: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5
- Prompting Claude Opus 5.5: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5
- Refusals and fallback: https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback
- Extended thinking - summarized thinking: https://platform.claude.com/docs/en/build-with-claude/extended-thinking