Relay and reseller APIs increasingly intermediate access to large language models (LLMs), but users have no direct way to verify that a claimed endpoint is actually serving the advertised model. We introduce KBF, a low-cost black-box auditing protocol that fingerprints model APIs using stable numerical recall near the knowledge boundary. Across 16 production LLM endpoints, KBF flags all 155 economically relevant substitutions without rejecting any same-model controls, remains stable under deployment variation, detects high-separation mixed-routing attacks when only 5-10% of traffic is substituted, and finds that 7 of 27 platform model cells in a six-platform shadow API audit are statistically inconsistent with their reference endpoints, with inconsistencies concentrated on premium Claude endpoints.

翻译：中继和转售API日益成为大型语言模型（LLM）访问的中间渠道，但用户无法直接验证声称的端点是否真正服务于所宣传的模型。我们提出KBF，一种低成本的黑盒审计协议，通过利用知识边界附近的稳定数值召回率来为模型API生成指纹。在16个生产级LLM端点上的实验表明，KBF能标记所有155个经济相关的替代模型，且未错误拒绝任何同模型对照；在部署变异条件下保持稳定性；当仅5%-10%的流量被替换时即可检测到高分离度的混合路由攻击；并且在对六个平台进行的影子API审计中发现，27个平台模型单元中有7个的统计特征与其参考端点不一致，不一致情况集中于高级Claude端点。