Unverified50% confidenceFactExact time
In extended thinking mode, Claude counts thinking tokens and final output tokens against the same max_tokens budget, whereas OpenAI's o-series models have a separate budget cap for reasoning tokens.
1
Sources
50%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedOpenAI has introduced a 'Thinking Budget' mechanism in its o-series reasoning models, which can dynamically control the length of the internal reasoning chain.76% similarUnverified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75% similarUnverifiedReasoning budget refers to the upper limit on the number of intermediate reasoning tokens a chain-of-thought model is allowed to consume before generating a final answer; the higher the budget, the deeper the self-reflection and multi-step verification the model can perform.75% similarUnverifiedClaude's extended thinking adopts a reasoning paradigm similar to that of OpenAI's o1 series models, but differs in implementation.70% similarVerifiedOpenAI o1 and DeepSeek-R1 achieve breakthroughs on complex benchmarks such as math competition problems by extending the chain of thought, which is essentially dynamically allocating more computational budget during the inference stage.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/820816API
curl https://kongchang.com/api/v1/knowledge/claims/820816MCP
get_claim(id=820816)