Today, we are announcing AWS regions on Koyeb for businesses. The fastest way to build, run, and scale your apps on AWS infrastructure. Over the last months, we've gotten more and more requests from businesses established on AWS to have a way to deploy Koyeb services on AWS infrastructure to: Our platform's core technology is cloud-agnostic and can be operated on top of anything, from high-performance bare metal servers to IaaS providers.

Ready? Day three of Koyeb launch week is on! When you deploy your apps on Koyeb, your data is on ephemeral disks. While this works great for stateless applications, this is challenging for stateful workloads like databases. Just in time to save the day, we are launching the technical preview of Volumes! You can now use Volumes to persist data between deployments, restarts, and even when services are paused. We're gradually onboarding users to ensure the best experience for everyone.

Welcome to day two of Koyeb launch week. Today we're announcing not one, but two major pieces of news: Our lineup ranges from 20GB to 80GB of vRAM with A100 and H100 cards. You can now run high-precision calculations with FP64 instructions support and a gigantic 2TB/s of bandwidth on the H100. With prices ranging from $0.50/hr to $3.30/hr and always billed by the second, you'll be able to run training, fine-tuning, and inference workloads with a card adapted to your needs.

We are thrilled to kickstart this first launch week with autoscaling - now generally available! Our goal is to offer a global and serverless experience for your deployments. Autoscaling makes this vision a reality. Say goodbye to overpaying for unused resources and late-night alerts for unhealthy instances or underprovisioned resources! During the autoscaling public preview, we received key feedback around scaling factors.