atlas
g4dn…
Try

7 of 497 instances · cheapest is g4dn.xlarge at $450/mo

Instance Workload vCPUs Memory Local disk Network On-demand/mo ↑ Per vCPU
g4dn.xlargeGPU & accelerators 4 16 GiB 125 GB NVMe Up to 25 Gbps $450 $112
g4dn.2xlargeGPU & accelerators 8 32 GiB 225 GB NVMe Up to 25 Gbps $642 $80.30
g4dn.4xlargeGPU & accelerators 16 64 GiB 225 GB NVMe Up to 25 Gbps $1,029 $64.33
g4dn.8xlargeGPU & accelerators 32 128 GiB 900 GB NVMe 50 Gbps $1,859 $58.10
g4dn.12xlargeGPU & accelerators 48 192 GiB 900 GB NVMe 50 Gbps $3,343 $69.65
g4dn.16xlargeGPU & accelerators 64 256 GiB 900 GB NVMe 50 Gbps $3,719 $58.11
g4dn.metalGPU & accelerators 96 384 GiB 1.8 TB NVMe 100 Gbps $6,687 $69.65