atlas
p2…
Try

3 of 1179 instances · cheapest is p2.xlarge at $1.542/hr

Instance Workload vCPUs Memory Local disk Network On-demand/hr ↑ Per vCPU
p2.xlargeGPU & accelerators 4 61 GiB EBS only High $1.542 $0.3855
p2.8xlargeGPU & accelerators 32 488 GiB EBS only 10 Gbps $12.34 $0.3855
p2.16xlargeGPU & accelerators 64 732 GiB EBS only 20 Gbps $24.67 $0.3855