"LLM Request Router team on AI Infra Summit Hackathon Hackathon"
Team Idea
An LLM request Router small service that sits in front of 2-3 model APIs (e.g. a cheap/fast model and a stronger/slower one) and routes each incoming request based on task complexity, then logs cost and latency tradeoffs.
Team Members
.png&w=256&q=75)
Abdul Khan
Muqsit
Submission
Team Leader hasn't made a submission yet