DictionaryPrompt Engineering
Extended Thinking
Letting the AI quietly reason before it replies, the older way of switching this on with a fixed thinking allowance.
Definition
A model capability where additional compute is used for internal reasoning before generating a response. The manual mode (thinking type enabled with budget_tokens) is deprecated on Claude Opus 4.6 and Sonnet 4.6 and returns a 400 error on Claude Opus 4.7 and later and on 5.x models; adaptive thinking, steered by effort and task budgets, replaces it.
Example
thinking: {type: "enabled", budget_tokens: 8000} works on older models; on Claude Opus 5.5 it returns a 400 error, so use {type: "adaptive"}.