Intelligent Model Routing: Frontier Performance Without Frontier Bills
Official Schedule Context
- Date/time: 2026-06-30 · 2:50pm-3:10pm
- Track/room: Sandbox & Platform Engineering · Leadership 2
- Speaker(s): Tomás Hernando Kofman
- Session type/status: session · confirmed
Official Description
It is Summer 2026 and the world is burning for token consumption—figuratively and literally.
Accelerating frontier model capabilities increasingly allow agents to operate across long-running,
highly parallelized tasks at exponential inference growth. In this talk, I explain how dynamic model
routing—intelligently directing agent requests to the best-suited model at the best price—can reduce
token costs by up to 90% while maintaining or improving accuracy. I walk through how routing works,
when it doesn't, and why the world (and your agent) need routing to scale intelligence to infinity
and beyond.
Related YouTube Video
No related AI Engineer channel video found yet.
Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.