The c8g.8xlarge pairs 32 vCPU with 64 GiB of RAM, the 2.00 GiB-per-vCPU ratio that marks a compute-optimized instance. In the name, "c" stands for compute, "8" is the generation, "g" marks AWS Graviton (ARM) processors and "8xlarge" is the size within the c8g family. It runs on AWS Graviton4 Processor at 2.7 GHz, and AWS introduced it in September 2024. AWS has since shipped c9g; c9g.8xlarge is the direct replacement at this size, scoring 1,163,636 CoreMark/s against this instance's 1,024,082 — roughly 14% more throughput for the same vCPU count. Spot's node ladder tops out below this size, so c8g.8xlarge becomes 2 × ch.vs1.2xlarge (32 vCPU, 64 GiB combined), about 94% below the US East (N. Virginia) on-demand rate. Spot delivers compute as managed Kubernetes, so a node pool of that size is the native shape of the answer rather than a workaround — provided the workload scales horizontally.
| Region | AWS on-demand | AWS Spot | 1-yr Reserved | 3-yr Reserved | Rackspace Spot | You save |
|---|---|---|---|---|---|---|
| US East, N. Virginia | $1.276 | $0.370 | $0.841 | $0.561 | $0.082 | $1.194 savings |
| US Central, Chicago | no AWS region | $0.022 | ||||
| US Central, Dallas | no AWS region | $0.222 | ||||
| Hong Kong | $1.602 | $1.071 | $0.741 | $0.082 | $1.520 savings | |
| Sydney, Australia | $1.661 | $0.591 | $1.097 | $0.755 | $0.082 | $1.579 savings |
| London, UK | $1.511 | $0.388 | $0.998 | $0.687 | $0.262 | $1.249 savings |
| US West, San Jose | $1.586 | $0.842 | $1.047 | $0.721 | $0.004 | $1.582 savings |
| US Central, Dallas 2 | no AWS region | $0.244 | ||||
| US East, N. Virginia 2 | $1.276 | $0.370 | $0.841 | $0.561 | $0.324 | $0.952 savings |