PACT: A Contract-Theoretic Framework for Pricing Agentic AI Services Powered by Large Language Models

Agentic AI, often powered by large language models (LLMs), is becoming increasingly popular and adopted to support autonomous reasoning, decision-making, and task execution across various domains. While agentic AI holds great promise, its deployment as services for easy access raises critical challenges in pricing, due to high infrastructure and computation costs, multidimensional and task-dependent Quality of Service (QoS), and liability concerns in high-stakes applications. In this work, we propose PACT, a Pricing framework for cloud-based Agentic AI services through a Contract-Theoretic approach. PACT models quality of service along both objective and subjective dimensions, while accounting for computational, infrastructure, and liability costs on the provider side. It enables heterogeneous users to select tailored service options that align with their needs. Numerical evaluations demonstrate that PACT ensures 100% QoS alignment between users and providers while offering a scalable and liable approach to pricing agentic AI services.