Unverified50% confidenceFactExact time
推理模型的中间思维链步骤在计费层面同样计入token消耗，OpenAI的o1模型思考token有时高达正常输出的数倍
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedThe number of internal reasoning tokens in OpenAI's o1/o3 series models is often several times to dozens of times that of the final output.79% similarUnverifiedReasoning models (such as the o1 series) can cost several times to more than ten times more than regular models because they need to generate a large number of intermediate thinking steps.78% 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.77% similarUnverifiedIn the o1 series models, OpenAI internalized the chain-of-thought mechanism as a spontaneous model behavior and introduced the concept of Reasoning Tokens.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/544907API
curl https://kongchang.com/api/v1/knowledge/claims/544907MCP
get_claim(id=544907)