Troubleshooting thinking

This page covers the most common failures when configuring thinking or round-tripping thinking blocks (sending returned thinking blocks back in later requests). The first section maps each model to its supported thinking configurations and the ones it rejects; the sections after it each start from a symptom you observe, so you can match an error message or unexpected response directly to its cause and fix. For how thinking works, see the Thinking overview.



Configurations each model rejects

Most thinking configuration errors are a mismatch between the thinking.type value in the request and what the model supports. On current models, thinking runs as thinking: {type: "adaptive"}, and on the newest it is on by default. Some earlier models instead use extended thinking, a legacy manual mode configured as thinking: {type: "enabled", budget_tokens: N}.

Extended thinking (thinking.type: "enabled" with budget_tokens) is deprecated on Claude Opus 4.6 and Claude Sonnet 4.6 (it still works there). Claude Opus 4.7, Claude Opus 4.8, Claude Sonnet 5, Claude Fable 5, and Claude Mythos 5 do not support it and reject requests that use it, returning a 400 error. On earlier models, including Claude Sonnet 4.5, Claude Opus 4.5, and Claude Haiku 4.5, extended thinking is the only thinking mode. Claude Mythos Preview supports both modes. Where both modes are available, use adaptive thinking instead.

The table lists what each model supports, what it defaults to, and which thinking.type values it rejects with a 400 error; any value not listed as rejected is accepted.

¹ enabled and budget_tokens still work on these models but are deprecated; use adaptive thinking instead.

Models marked Always on cannot turn thinking off. Models marked On default to thinking but accept thinking: {type: "disabled"}.

Earlier Claude 4 models (Claude Sonnet 4 and Claude Opus 4) support extended thinking only; see model deprecations for their availability. Claude Fable 5 and Claude Mythos 5 are not available under zero data retention.



A 400 error says "thinking.type.enabled" is not supported

The request fails with a 400 error whose message reads:

"thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.

This happens because the model you requested has removed extended thinking (see Configurations each model rejects).

Switch the request to thinking: {type: "adaptive"} and steer thinking depth with effort instead of budget_tokens. Migrating to adaptive thinking walks through the conversion.



A 400 error says "thinking.type.disabled" is not supported

The request fails with a 400 error whose message reads:

"thinking.type.disabled" is not supported for this model. Thinking defaults to adaptive mode when not specified; use "thinking.type.enabled" with "budget_tokens" for extended thinking.

This happens on models where thinking is always on: Claude Fable 5, Claude Mythos 5, and Claude Mythos Preview reject "disabled". On Claude Fable 5 and Claude Mythos 5, the error text's suggestion of "thinking.type.enabled" does not apply either: those models reject it too.

Omit the thinking parameter; these models think without any configuration. If your goal was to keep thinking text out of responses, use display: "omitted" instead of disabling thinking; see Controlling thinking display.



A 400 error says adaptive thinking is not supported

The request fails with a 400 error whose message reads:

adaptive thinking is not supported on this model

This happens because the model supports only extended thinking (see Configurations each model rejects).

Use thinking: {type: "enabled", budget_tokens: N} instead; see Extended thinking for the configuration.



A 400 error says thinking blocks cannot be modified

A request that returns tool results fails with a 400 invalid_request_error whose message contains:

`thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified

In multi-turn and tool-use conversations you send previous assistant messages, including their thinking and redacted_thinking blocks, back to the API, and the API verifies they arrive unmodified. This error happens when the assistant message you send back differs from the one the API returned, most often because your code filters content blocks by type and drops redacted_thinking blocks, or rebuilds the assistant message instead of echoing it.

Echo the assistant turn back verbatim, thinking blocks included. See Preserving thinking blocks for the rules, and the worked round trip in Thinking in tool and multi-turn workflows for correct code in every SDK.



The thinking field is empty in the response

The response contains thinking blocks, but their thinking field is an empty string and only the signature field is populated.

This happens because display defaults to "omitted" on newer models, which returns thinking blocks without their text.

Set display: "summarized" in your thinking configuration to receive the summarized thinking text; see Controlling thinking display for the defaults per model.



No thinking block appears on some turns

Some responses contain no thinking block at all, even though thinking is configured.

This is normal in adaptive mode: Claude skips thinking on requests it judges simple enough to answer directly.

If you want thinking more often or more deeply, raise effort or steer with prompting; see Steering how often Claude thinks.



The response stops with stop_reason: "max_tokens"

The response ends with stop_reason: "max_tokens", often with a truncated or missing text block.

This happens because thinking tokens count toward max_tokens, so a long thinking pass can consume the budget before the text response completes.

Raise max_tokens to leave room for both thinking and text, or lower effort so Claude spends less on thinking; see Cost control and Thinking and the context window.



Cache hits drop after changing thinking settings

cache_read_input_tokens falls to zero on requests that previously hit the cache.

This happens because the thinking configuration and the effort level (or its default) are part of the cached prompt prefix, so changing any of them starts a new prefix: switching thinking modes, changing the effort value, and changing budget_tokens all invalidate message cache breakpoints, and can invalidate tool and system-prompt breakpoints too, depending on where the model renders the configuration.

Keep the thinking configuration and effort level constant across requests that share a conversation; setting a parameter explicitly to its default is equivalent to omitting it and does not invalidate. See Thinking and prompt caching.



Setting effort does not change thinking

You change effort but thinking frequency or depth stays the same.

This happens because effort is the primary thinking lever only in adaptive mode. On extended-thinking-only models, thinking depth is set by budget_tokens instead.

Adjust budget_tokens on those models, or check which mode your model runs in; see Thinking and effort. On Claude Opus 4.5, the one extended-thinking-only model that supports effort, effort composes with the budget; see Budget rules and tuning.



Next steps