atlas
g4dn…
Try

7 of 786 instances · cheapest is g4dn.xlarge at $0.6470/hr

Instance Workload vCPUs Memory Local disk Network On-demand/hr ↑ Per vCPU
g4dn.xlargeGPU & accelerators 4 16 GiB 125 GB NVMe Up to 25 Gbps $0.6470 $0.1618
g4dn.2xlargeGPU & accelerators 8 32 GiB 225 GB NVMe Up to 25 Gbps $0.9250 $0.1156
g4dn.4xlargeGPU & accelerators 16 64 GiB 225 GB NVMe Up to 25 Gbps $1.481 $0.0926
g4dn.8xlargeGPU & accelerators 32 128 GiB 900 GB NVMe 50 Gbps $2.677 $0.0837
g4dn.12xlargeGPU & accelerators 48 192 GiB 900 GB NVMe 50 Gbps $4.812 $0.1003
g4dn.16xlargeGPU & accelerators 64 256 GiB 900 GB NVMe 50 Gbps $5.353 $0.0836
g4dn.metalGPU & accelerators 96 384 GiB 1.8 TB NVMe 100 Gbps $9.624 $0.1003