> The biggest problem: developers don’t want GPUs. They don’t even want AI/ML models. They want LLMs.
I considered using a Fly GPU instance for a project and went with Hetzner instead. Fly.io’s GPU offering was just way too expensive to use for inference.
Hetzner is more expensive by default though? It starts at $200/month. Which is fine if you are running for 720 hours every month, but you can run more cheaply on fly if it doesn’t get used more than 150ish hours in a month.
I considered using a Fly GPU instance for a project and went with Hetzner instead. Fly.io’s GPU offering was just way too expensive to use for inference.