atlas
p3…
Try

3 of 938 instances · cheapest is p3.2xlarge at $4.234/hr

Instance Workload vCPUs Memory Local disk Network On-demand/hr ↑ Per vCPU
p3.2xlargeGPU & accelerators 8 61 GiB EBS only Up to 10 Gbps $4.234 $0.5292
p3.8xlargeGPU & accelerators 32 244 GiB EBS only 10 Gbps $16.94 $0.5292
p3.16xlargeGPU & accelerators 64 488 GiB EBS only 25 Gbps $33.87 $0.5292