反向拍卖按任务竞价：固定 token 定价存在 10%–71% 价差
Learning the Cost of Reliable Inference
一篇把拍卖机制套到 LLM 采购上的论文，Llama 和 Qwen 实测显示固定定价比竞价贵 10% 到 71%，做 API 成本优化的可以看看思路。
arXiv 论文提出一个采购平台设计，通过逆向第二价格拍卖让 LLM 提供商按任务竞价，报价为其服务该查询的真实平均成本估计。平台在路由查询过程中学习各提供商的质量，逐步把查询分配给满足质量阈值中成本最低者。实验使用 Llama 与 Qwen 系列多个模型，在数学推理和问答基准上测试，结果显示最具成本竞争力提供商的定价加价幅度在 10% 到 71% 之间波动，具体取决于任务和质量阈值。这说明按 token 固定定价的市场存在明显低效，竞价机制可让用户在竞争条件下获得最大节省。
Learning the Cost of Reliable Inference
Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with end-users. However, providers on these platforms typically use a fixed price per token, preventing users from achieving the most competitive price for their tasks. % workloads. In this work, we design a procurement platform where token prices for each task are driven by provider competition, enabling users to secure competitive pricing for guaranteed quality levels. To this end, the platform sequentially routes queries via a reverse second-price auction that incentivizes model providers to truthfully bid their best estimate of the average cost to serve a user's query. As it routes queries, the platform learns the quality offered by each provider and progressively routes queries to the most cost-competitive provider among those meeting a desired quality threshold. To validate our design, we conduct experiments with multiple LLMs from the \texttt{Llama} and \texttt{Qwen} families on popular mathematical reasoning and question-answering benchmarks. The results show that the pricing margin of the most cost-competitive provider on our platform varies significantly---from $10\%$ to $71\%$---depending on the task and quality threshold. This suggests a substantial inefficiency in the current fixed-price market, and it demonstrates that our platform may enable users to capture maximum savings whenever competitive market conditions permit.
