Extended Thinking
Extended thinking is a Claude feature that lets the model allocate additional reasoning tokens before producing its final answer, with a user-controllable thinking budget set per request. It is distinct from dedicated reasoning models, which always reason internally — extended thinking is a toggle you enable when the task benefits from slower, deeper thought.
It pays off on math, code, multi-step planning, and evaluations that reward careful steps, and is usually not worth the extra cost on creative writing, simple recall, or short chat turns.
Example
A developer debugging a tricky race condition sets a 16k-token thinking budget on a Claude request and asks the model to trace the execution order of two coroutines. The model uses most of its budget working through interleavings internally, then returns a short answer identifying the exact ordering that triggers the bug. For a follow-up "reword this to be friendlier," the same developer disables extended thinking — the task does not need it, and the latency and cost are not justified.
Related Resources
Prompting Reasoning Models in 2026: GPT-5.6 Sol, Claude, Gemini, and DeepSeek
How to prompt GPT-5.6 Sol reasoning effort, Claude adaptive thinking, Gemini 3.1 Pro thinking, and DeepSeek V4 in 2026 — the 6-slot anatomy, per-model dialects, and when to skip them.
Extended Thinking Prompts for Claude (2026)
How to prompt Claude's extended thinking mode — when it helps, when it wastes budget, and how prompt structure shapes the reasoning process.
Claude 4 Prompting Guide: Adaptive Thinking, Extended Context, and Best Practices
Master Claude prompting with practical techniques for system prompts, XML formatting, extended thinking, and long-context workflows.