x2iedn.4xlarge

Analysis

The x2iedn.4xlarge is a memory optimized instance in the x2iedn series with 16 vCPUs and 512 GiB of memory on Intel Xeon Scalable (Icelake) (up to 3.5 GHz), which makes it very memory-heavy at 32 GiB of memory per vCPU.

Within the same generation and size, the x2gd.4xlarge on AWS Graviton2 costs $1.34/hour, 60% less ($1,459 a month), though switching means rebuilding software for arm64. The other variants are the x2iezn.4xlarge at $3.34.

Nothing else with 16 vCPUs and similar memory is cheaper: among 3 current same-shape types it has the lowest on-demand price.

Running it in N. Virginia instead of São Paulo saves $2,313 a month per instance: $3.33/hour against $6.50/hour, a 95% spread.

Per vCPU it is one of the dearer memory optimized types: 94% of the 385 current types in the family cost less than its $0.2084 per vCPU-hour. The premium mostly pays for the local NVMe disk. On demand it is $3.33/hour in US East (N. Virginia), or $2,434 for a 730-hour month.

It has local instance storage (1 x 475 GB NVMe SSD), which is fast but lost when the instance stops. Network: Up to 25 Gigabit.

Reserving it for a year with no upfront payment cuts the Linux rate to $2.05/hour, which beats on demand once it runs more than 62% of the time; three years brings it to $1.07/hour, 68% below on demand. Windows Server roughly adds 22% to the bill at $4.07/hour, because the licence is charged per vCPU.