OpenAlex ·
Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption
- Published
- Source
- OpenAlex
- DOI
- 10.48550/arxiv.2609.00710
- Original
- Read it at the publisher
- Topics
Abstract
An LLM application often sells or internally allocates several service products: a small or premium model, a short or long token cap, and possibly multiple posted prices. The operational decision is not merely which model answers a prompt. A price changes purchase probability, a token cap changes both user value and the tail of resource consumption, and accepted requests compete for shared compute and premium-model capacity. Demand and output length are initially uncertain, while an offline model may provide useful but imperfect predictions. We formulate sequential pricing and admission with stochastic resource consumption. Each arriving request belongs to an observable segment. The platform chooses a product--price pair or makes no offer; purchase, revenue, and resource use are then random. An offline predictor supplies a uniform, validated error radius for every segment--product cell. We propose Prediction-Clipped UCB (PCUCB), which intersects the offline prediction interval with an online confidence interval, evaluates products using resource shadow prices, and reserves a sample-path envelope before commitment. The prior gives a fast start when accurate, while online learning protects the platform when predictions are coarse. The analysis is modular. On a simultaneous confidence event, regret against a buffered fluid benchmark is bounded by a pacing term plus the cumulative diameter of the intersected intervals. For $J$ segment-product cells and prediction radius $\varepsilon$, this yields \[ \widetilde O\left( \sqrt{T}+(1+\barΛ) \min\{T\varepsilon,\sqrt{JT}\} \right), \] where $\barΛ$ bounds operational shadow prices. Thus the algorithm smoothly interpolates between an almost full-information regime and learning from scratch. Hard feasibility holds on every sample path through reservation envelopes.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Networking & Internet
From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning
Weighted Fair Division of Indivisible Mixed Manna
FOXDEN: FAIR Services for AI-Ready Scientific Datasets
IMU-Aided Correction of Orientation-Induced Ranging Error in Bluetooth Channel Sounding on Commercial Hardware
Network Availability Enhancement in Low-Altitude HetNets: A Cross-Layer Design Perspective
Get the few papers worth your time in Networking & Internet every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.