Anthropic APINew featureinfo
Anthropic Models API now reports between_tools thinking support
- Detected
- Oct 20, 2026
- Confidence
- 92%
What changed
Anthropic added documentation for a new thinking.types.between_tools capability field in the Models API response, which reports whether a model accepts thinking: {type: "between_tools"} to disable up-front thinking. Claude Sonnet 5.5 is cited as an example where this is supported but thinking.types.disabled is not.
What to do
If you programmatically inspect model capabilities, update your code to handle the new thinking.types.between_tools field in the capabilities object, especially if you need to determine support for between-tools thinking mode.
Affected
model: thinking.types.between_toolsparam: thinking.types.between_tools.supportedmodel: claude-sonnet-5-5Source: docs.anthropic.com (Anthropic's own page, checked by Breakwatch)
Is your code affected?
Search your repositories for the Anthropic SDK and the names above:
Or let Breakwatch do it: connect a repo and see which files call Anthropic, then get the next change as an alert pointing at those files. Check a repo free