Unverified50% confidenceFactExact time
Fable 5's increased token consumption is attributed to Extended Thinking or Chain of Thought mechanisms, where the model performs internal reasoning and self-verification before generating a final answer
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
Unverified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79% similarUnverifiedSome AI models incorporate 'thinking tokens' mechanisms, performing internal reasoning steps before generating the final answer74% similarUnverified推理模式会在最终回答前进行内部链式推理，产生的思考 Token 计入账单，复杂编程任务中思考 Token 可能占总消耗的 60%-70%，费用可能是普通模式的 3-5 倍73% similarUnverified扩展思考模式会让模型在输出前进行显式内部推理链，代价是Token消耗大幅增加且推理Token通常按更高费率计费71% similarUnverified顶尖模型采用思维链或扩展推理等技术，在推理时生成大量中间Token，导致每次调用的Token消耗数倍于普通模型71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/45361API
curl https://kongchang.com/api/v1/knowledge/claims/45361MCP
get_claim(id=45361)