arXiv:2608.16956cs.AIcs.CL2026-08

明确要求高推理成本的API比省略该要求更贵,但准确率未显著提升。

The Price of Thinking: Reasoning Effort as a Model-Specific API Contract

  • 通过对比同一模型在显式高推理与省略推理下的表现,测试成本差异
  • 高推理合同下每调用成本高出0.01031美元,但准确率无显著差异
  • 适合关注大模型服务成本与定价策略的开发者和研究者

API买家购买的不仅是模型名称,还包括包含推理努力、输出限制、价格表等条款的协议。本研究通过注册的成对对比实验,比较Sonnet 5在显式高推理与省略推理两种条件下的表现,使用30道AIME 2026题目,每题5次调用。每次调用分配一个固定终态类别,重复调用保留。显式高推理合同下平均每调用成本高0.01031美元(95%置信区间:+0.00204至+0.01974);准确率差异为+0.0133(-0.0267至+0.0467),未检测到显著差异,但可能高达4.67个百分点。高推理合同下单位正确答案成本为0.08665美元,省略合同为0.07662美元。请求注册、解析器、终态分类体系、统计计划及分析流程均在结果审查前冻结,结论仅适用于所研究模型、任务与数据采集日期。

原文摘要 · Abstract (English)

API buyers purchase a dated contract, not a model name alone: the contract includes the requested and served model, reasoning-effort term or its omission, output rail, service product, prompt, and price schedule. We study the reasoning-effort term through a registered paired contrast of Sonnet 5 with explicit high effort against the same model with effort omitted, using 30 AIME 2026 items and five calls per item. Every paid attempt was assigned one frozen terminal category, and inference resampled items while retaining their repeated calls. Mean delivered cost was \$0.01031 per call higher under the explicit-high contract than under the omitted contract [+\$0.00204, +\$0.01974]. The corresponding accuracy contrast was +0.0133 [-0.0267, +0.0467]; we did not detect an accuracy difference, and the interval permits a gain of up to 4.67 percentage points that this design cannot rule out. Cost per correct answer was \$0.08665 under the high-effort contract and \$0.07662 under the omitted contract, as registered point estimates. A dated contract census, Models-API metadata, and preregistered raw-response probes further documented model-specific omission semantics, including within a provider; claims remained at documentation grade when raw structure was indeterminate. The request registry, parser, terminal taxonomy, statistical plan, and analysis pipeline were frozen before outcomes were examined; the resulting claims are bounded to the model, task, and collection date studied.

API定价推理成本大模型

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。