AI Codex
Foundation Models & LLMs ClaudeOperatorsDevelopers

Extended Thinking

Also: extended thinking mode, Claude thinking mode

Extended thinking is a mode where Claude works through a problem step-by-step before giving its final answer. You see its reasoning process — including the parts where it changes its mind or catches an error. It takes longer and costs more tokens, but produces meaningfully better results on hard problems: complex analysis, multi-step planning, tricky reasoning tasks. Turn it on when accuracy matters more than speed.

In practice

You ask Claude "should we expand into the EU market this year?" With Extended Thinking on, Claude works through the question visibly — considering regulatory complexity, market size, team bandwidth, timing — before giving its recommendation. You can see where it weighed tradeoffs. Use it for decisions that deserve actual analysis, not quick answers.

Related concepts

Where Extended Thinking shows up

2 articles