atlas
f1…
Try

3 of 1348 instances · cheapest is f1.2xlarge at $1,204/mo

Instance Workload vCPUs Memory Local disk Network On-demand/mo ↑ Per vCPU
f1.2xlargeGPU & accelerators 8 122 GiB 470 GB NVMe Up to 10 Gbps $1,204 $151
f1.4xlargeGPU & accelerators 16 244 GiB 940 GB NVMe 10 Gbps $2,409 $151
f1.16xlargeGPU & accelerators 64 976 GiB 3.8 TB NVMe 25 Gbps $9,636 $151