r8gn.12xlarge

Analysis

The r8gn.12xlarge is a memory optimized instance in the r8gn series with 48 vCPUs and 384 GiB of memory on AWS Graviton4 (up to 2.8 GHz), which makes it memory-heavy at 8 GiB of memory per vCPU.

Within the same generation and size, the r8g.12xlarge on AWS Graviton4 costs $2.83/hour, 35% less ($1,128 a month). The other variants are the r8i-flex.12xlarge at $3.17, the r8i.12xlarge at $3.33 and the r8gd.12xlarge at $3.53.

Its price is almost flat across the 2 regions that offer it ($4.37 to $4.37/hour), so latency and data residency should decide where it runs. It is not offered in Ohio, Canada Central, São Paulo, Ireland, London, Frankfurt, Mumbai, Singapore, Sydney and Tokyo, so plan around that if you need a presence there.

On demand it costs $4.37/hour in US East (N. Virginia), $3,192 a month if left running, which puts it mid-table for memory optimized types at the 63rd percentile per vCPU ($0.0911 per vCPU-hour) and the 78th percentile per GiB ($0.0114 per GiB-hour).

Looking beyond its own line, 27 of 40 current types with 48 vCPUs and similar memory are cheaper. The cheapest of those is the r6g.12xlarge on AWS Graviton2 at $2.42/hour.

It is size 7 of 10 in the r8gn series. Stepping up to the r8gn.16xlarge gives 64 vCPUs and 512 GiB for $1,064 more a month. Dropping to the r8gn.8xlarge saves $1,064 a month.