atlas
Try

9 of 484 instances · cheapest is inf1.xlarge at $0.3020/hr

Instance Workload vCPUs Memory Local disk Network On-demand/hr ↑ Per vCPU
inf1.xlargeGPU & accelerators 4 8 GiB EBS only Up to 25 Gbps $0.3020 $0.0755
g4dn.xlargeGPU & accelerators 4 16 GiB 125 GB NVMe Up to 25 Gbps $0.6980 $0.1745
g4dn.2xlargeGPU & accelerators 8 32 GiB 225 GB NVMe Up to 25 Gbps $0.9980 $0.1247
g4dn.4xlargeGPU & accelerators 16 64 GiB 225 GB NVMe Up to 25 Gbps $1.597 $0.0998
g4dn.8xlargeGPU & accelerators 32 128 GiB 900 GB NVMe 50 Gbps $2.887 $0.0902
g4dn.12xlargeGPU & accelerators 48 192 GiB 900 GB NVMe 50 Gbps $5.190 $0.1081
g4dn.16xlargeGPU & accelerators 64 256 GiB 900 GB NVMe 50 Gbps $5.774 $0.0902
inf1.24xlargeGPU & accelerators 96 192 GiB EBS only 100 Gbps $6.249 $0.0651
g4dn.metalGPU & accelerators 96 384 GiB 1.8 TB NVMe 100 Gbps $10.38 $0.1081