{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:57:05Z","timestamp":1773802625758,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"20","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>The proliferation of Large Language Models (LLMs) has established LLM routing as a standard service delivery mechanism, where users select models based on cost, Quality of Service (QoS), among other things.\nHowever, optimal pricing in LLM routing platforms requires precise modeling for dynamic service markets, and solving this problem in real time at scale is computationally intractable.\nIn this paper, we propose PriLLM, a novel practical and scalable solution for real-time dynamic pricing in competitive LLM routing.\nPriLLM models the service market as a Stackelberg game, where providers set prices and users select services based on multiple criteria.\nTo capture real-world market dynamics, we incorporate both objective factors (eg cost, QoS) and subjective user preferences into the model.\nFor scalability, we employ a deep aggregation network to learn provider abstraction that preserve user-side equilibrium behavior across pricing strategies.\nMoreover, PriLLM offers interpretability by explaining its pricing decisions.\nEmpirical evaluation on real-world data shows that PriLLM achieves over 95% of the optimal profit while only requiring less than 5% of the optimal solution's computation time.<\/jats:p>","DOI":"10.1609\/aaai.v40i20.38748","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:50:56Z","timestamp":1773795056000},"page":"17005-17013","source":"Crossref","is-referenced-by-count":0,"title":["Pricing Online LLM Services with Data-Calibrated Stackelberg Routing Game"],"prefix":"10.1609","volume":"40","author":[{"given":"Zhendong","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenchao","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38748\/42710","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38748\/42710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:50:56Z","timestamp":1773795056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i20.38748","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}