Ettore Ciarcia.

Talk · · Benevento

One Endpoint, Hundreds of Models: LiteLLM Explained to My Mom

Linux Day Benevento 2026

How can we interact with hundreds of AI models through a single API? In this talk, we'll explore how LiteLLM simplifies LLM integration by providing a unified endpoint for models like GPT, Gemini, and Llama. Through a live demo, we'll discover how to switch between cloud and local models while managing authentication, routing, costs, and guardrails

← All talks