Menu

1 / 3

When does reserved GPU capacity beat on-demand pricing?

DEV Community: cloud·Viswaretas Kotra·about 3 hours ago
#Wz6OvBC5
#devtocloud#devto#dev#demand#rate
Reading 0:00
15s threshold

Reserved GPU capacity beats on-demand once your utilization over the term exceeds the reserved rate divided by the on-demand rate: 63.0% of all hours for an 8 x NVIDIA H100 machine on a 1-year Amazon EC2 Instance Savings Plan. Nodus lists the H100 SXM at $2.60/hr on its pricing page, a GPU rate below even AWS's 3-year plan per GPU-hour, and Nodus Reserved Compute (Beta) quotes dedicated capacity for a steady floor. Commit only the GPUs that stay busy above the line and run the rest on demand.

How do you calculate the break-even utilization for reserved GPUs?

Divide the reserved rate by the on-demand rate you would otherwise pay. The answer is the fraction of the term's hours you must actually use for the commitment to cost less.

The reasoning is short. A commitment bills every hour of the term, used or not. On-demand bills only the hours you run.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.