What are you running?

Start from a workload or set the minimums yourself. We pick the cheapest instance that meets every one.

Web or API server Stateless, scales out Database Memory and fast disk Cache Redis, Memcached CI and batch jobs Bursty, retry-safe Model inference Serve a 7–13B model Model training Multi-GPU, big VRAM

CPU at least 4 vCPU

1 2 4 8 16 32 64 96 192

1 2 4 8 16 32 64 128 256 512 1T

None 16 GB 24 GB 48 GB 80 GB+ 160 GB+

Any Arm (Graviton) x86 only

For these needs x86 is the cheaper option here. Arm still wins on some families.

Network (EBS) is fine Fast local NVMe

Not sure A year or more Three years

61 instances meet your needs in N. Virginia, priced on-demand.

inf Inferentia

2 Generation 2

xlarge 4 vCPU · 16 GiB

$553/mo

$0.7582 an hour

4 vCPU EPYC Milan

16 GiB 4 GiB per vCPU

EBS only Local disk

Up to 15 Gbps Network

Cheapest match. Meets every requirement on the left with nothing to spare. Full details