The New Stack Podcast cover image

2026 Will Be the Year of Agentic Workloads in Production on Amazon EKS

The New Stack Podcast

00:00

Where to deploy models: endpoints or in-cluster

Mike outlines choices: external endpoints like OpenAI or Bedrock versus running models inside the cluster to save costs.

Play episode from 07:42
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app