Unverified50% confidenceSolutionExact time
For reasoning (thinking) models, it is recommended to set the thinking intensity to low or turn it off to avoid consuming thousands of tokens on casual conversation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedThe author recommends disabling thinking, on the grounds that most use cases for building agents or simple applications do not require deep reasoning, and LangChain's compatibility with thinking mode is not yet complete.77% similarUnverifiedOpus 5 enables Extended Thinking by default; thinking can only be disabled at effort levels of high or below, and the official guidance strongly recommends not disabling thinking.73% similarUnverified对话中最有价值的建议是让模型运用自身判断力，而非硬性规定其工作方式73% similarUnverifiedThinking mode should remain enabled for math, code, and complex logical tasks, while it should be disabled or depth-limited for routine Q&A and conversation.72% similarUnverifiedStandard reasoning mode does not use long chain-of-thought, and token consumption is typically one-tenth or even less than that of high reasoning mode.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/916619API
curl https://kongchang.com/api/v1/knowledge/claims/916619MCP
get_claim(id=916619)