Pricing Online LLM Services with Data-Calibrated Stackelberg Routing Game
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (20) · 17005-17013
DOI: 10.1609/aaai.v40i20.38748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhendong Guo und 2 weiteren Autor:innen.
Abstract (Originalsprache)
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. However, 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. In this paper, we propose PriLLM, a novel practical and scalable solution for real-time dynamic pricing in competitive LLM routing. PriLLM models the service market as a Stackelberg game, where providers set prices and users select services based on multiple criteria. To capture real-world market dynamics, we incorporate both objective factors (eg cost, QoS) and subjective user preferences into the model. For scalability, we employ a deep aggregation network to learn provider abstraction that preserve user-side equilibrium behavior across pricing strategies. Moreover, PriLLM offers interpretability by explaining its pricing decisions. Empirical 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.
Zitieren
APA
Guo, Z., Bai, W., & Jin, J. (2026). Pricing Online LLM Services with Data-Calibrated Stackelberg Routing Game. Proceedings of the AAAI Conference on Artificial Intelligence, 40(20), 17005-17013. https://doi.org/10.1609/aaai.v40i20.38748
Vancouver
Guo Z, Bai W, Jin J. Pricing Online LLM Services with Data-Calibrated Stackelberg Routing Game. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(20):17005-17013. doi:10.1609/aaai.v40i20.38748
BibTeX
@article{Guo2026,
author = {Guo, Zhendong and Bai, Wenchao and Jin, Jiahui},
title = {Pricing Online LLM Services with Data-Calibrated Stackelberg Routing Game},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {20},
pages = {17005--17013},
doi = {10.1609/aaai.v40i20.38748}
}
EUVIMED