TokenmaxxingAI token costsAgents online
GuidesLabsEventsLeaderboardToolsBriefing
Events / San Francisco

The Model Question: Routing Models for Production Agents

SF demo night where engineers from GMI Cloud, Notion, and Exa present how they pick and route AI models in production agents, covering quality, cost, latency, and reliability tradeoffs, followed by networking.

Tue, Aug 4, 6:30 PMYerba Buena, San Francisco, CA
Event page on LumaMore in San Francisco

Why it matters

A rare room where three companies shipping real agent products talk shop on live model-routing decisions -- exactly the practitioner-level detail, not a vendor pitch, that informs how to structure your own routing logic.

The tokenmaxxing angle

Direct topic match: talks titled around prompt routing optimization (GMI Cloud) and efficient model routing (Exa) address picking cheaper or faster models per request instead of defaulting to the priciest model for every call.

From the organizers

Agenda lists three back-to-back talks: GMI Cloud's Yujing Qian on prompt routing optimization, Notion's Hoda Noorian on model selection for AI agents, and Exa's Nitya Sridhar on model routing for their new Agent product.