Unverified50% confidenceConceptExact time
Reasoning tokens refer to the tokens consumed by the internal reasoning content generated by models with chain-of-thought capabilities (such as the OpenAI o series, DeepSeek-R1, etc.) before giving a final answer; they are usually not shown directly to the user but are counted toward billing and context window usage.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThinking tokens are billed as output tokens just like the final answer, and are usually invisible to users or shown only in collapsed form.75% similarUnverifiedThe context window refers to the upper limit on the number of tokens a model can read simultaneously in one inference; it is only the input limit for a single request and does not mean the model can continuously remember the entire codebase.70% similarUnverifiedToken consumption includes both the input content and the output returned by the model.69% similarUnverified语言模型生成 token 本质上是内存带宽受限任务而非纯算力受限68% similarVerifiedThe context of a large language model is essentially the total amount of information the model can process in a single inference, typically measured in the number of tokens.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064578API
curl https://kongchang.com/api/v1/knowledge/claims/1064578MCP
get_claim(id=1064578)