Anthropic added capabilities.thinking.types.disabled to the Models API, so GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "disabled"} to turn thinking off. This lets developers programmatically check thinking-disable support instead of relying on trial and error.
Read the full story on platform.claude.com
What to doUpdate model capability checks to read capabilities.thinking.types.disabled from the Models API when deciding whether to send thinking: {type: "disabled"}.
- Provider
- Anthropic
- Source
- platform.claude.com