c8a.24xlarge

Analysis

The c8a.24xlarge is a compute optimized instance in the c8a series with 96 vCPUs and 192 GiB of memory on AMD EPYC 9R45 (up to Up to 4.5 GHz), which makes it compute-heavy at 2 GiB of memory per vCPU.

Within the same generation and size, the c8g.24xlarge on AWS Graviton4 costs $3.83/hour, 26% less ($981 a month), though switching means rebuilding software for arm64. The other variants are the c8i.24xlarge at $4.50, the c8gd.24xlarge at $4.70 and the c8id.24xlarge at $5.32.

Running it in N. Virginia instead of Tokyo saves $977 a month per instance: $5.17/hour against $6.51/hour, a 26% spread. It is not offered in Canada Central, São Paulo, London, Mumbai, Singapore and Sydney, so plan around that if you need a presence there.

On demand it costs $5.17/hour in US East (N. Virginia), $3,776 a month if left running, which puts it mid-table for compute optimized types at the 67th percentile per vCPU ($0.0539 per vCPU-hour) and the 71st percentile per GiB ($0.0269 per GiB-hour).

Looking beyond its own line, 14 of 22 current types with 96 vCPUs and similar memory are cheaper. The cheapest of those is the c6a.24xlarge on AMD EPYC 7R13 at $3.67/hour.

Compared with the previous generation, it costs 5.0% more than the c7a.24xlarge on AMD EPYC 9R14 ($180 more a month per instance), in exchange for the newer processor.