atlas
p3…
Try

3 of 830 instances · cheapest is p3.2xlarge at $3.589/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 $3.589 $0.4486
p3.8xlargeGPU & accelerators 32 244 GiB EBS only 10 Gbps $14.36 $0.4486
p3.16xlargeGPU & accelerators 64 488 GiB EBS only 25 Gbps $28.71 $0.4486