AI Cost Attribution & Optimization for LLM Consumption
As AI adoption grows, understanding and controlling the cost of LLM consumption becomes increasingly important. Traditional API metrics provide only part of the picture, while AI workloads introduce new dimensions such as token usage, model selection, context size, and agent-driven interactions.
This session explores how AI Analytics and AI API Governance can provide greater visibility and control over AI consumption. It looks at how organizations can attribute usage and cost across applications, consumers, models, and teams, while applying governance mechanisms to manage how AI services are accessed and consumed.
The session also examines how analytics can support better optimization decisions by identifying usage patterns, inefficiencies, and opportunities to reduce unnecessary consumption. Together, analytics and governance provide a foundation for managing AI APIs in a more measurable, controlled, and cost-aware way.
Speakers
Anusha Jayasundara is a Senior Technical Lead at WSO2 with over nine years of experience driving innovation in API management, governance, analytics, and cloud-native integration. He has led the design and implementation of key capabilities in WSO2 API Manager, with deep expertise in API Analytics, streaming data integration, and API governance. Anusha is passionate about building scalable, secure, and insight-driven API ecosystems that empower organizations to thrive in multi-cloud and hybrid environments.