Unverified50% confidenceFactExact time
Reasoning tokens are internal text generated by the model during its thinking process; they are not directly shown to users but consume computational resources and are billed separately.
1
Sources
50%
Confidence
Long-term
Relevance
9/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedReasoning models perform extended reasoning within thinking blocks wrapped in special tokens (such as <think> and </think>); this content is typically not shown directly to users but consumes a large number of tokens.79% similarUnverifiedReasoning-enhanced models (such as o1 and DeepSeek-R1) consume large numbers of reasoning tokens in their chain-of-thought process that are invisible to users; the actual tokens consumed by o1-preview are often 3 to 8 times that of the visible output.72% similarUnverifiedTool calling allows models to dynamically invoke external functions during inference and incorporate execution results into the context of subsequent reasoning, forming a closed loop of perception, decision-making, and execution.71% similarUnverified思维链将模型内部工作记忆外部化，把中间推导结果存入上下文，借助注意力机制随时读取和复用70% similarUnverified推理模型在生成最终答案前会先产生大量内部思维链（Chain-of-Thought）token，这些 token 不直接暴露给用户70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/842829API
curl https://kongchang.com/api/v1/knowledge/claims/842829MCP
get_claim(id=842829)