c7a.16xlarge

Analysis

The c7a.16xlarge is a compute optimized instance in the c7a series with 64 vCPUs and 128 GiB of memory on AMD EPYC 9R14 (up to Up to 3.7 GHz), which makes it compute-heavy at 2 GiB of memory per vCPU.

Within the same generation and size, the c7g.16xlarge on AWS Graviton3 costs $2.32/hour, 29% less ($704 a month), though switching means rebuilding software for arm64. The other variants are the c7i-flex.16xlarge at $2.71, the c7i.16xlarge at $2.86 and the c7gd.16xlarge at $2.90.

Compared with the previous generation, it costs 34% more than the c6a.16xlarge on AMD EPYC 7R13 ($611 more a month per instance), in exchange for the newer processor. The newer c8a.16xlarge on AMD EPYC 9R45 is 5.0% dearer at $3.45/hour.

Running it in N. Virginia instead of Tokyo saves $620 a month per instance: $3.28/hour against $4.13/hour, a 26% spread. It is not offered in Canada Central, São Paulo, Mumbai and Sydney, so plan around that if you need a presence there.

On demand it costs $3.28/hour in US East (N. Virginia), $2,398 a month if left running, which puts it mid-table for compute optimized types at the 61st percentile per vCPU ($0.0513 per vCPU-hour) and the 63rd percentile per GiB ($0.0257 per GiB-hour).