NVIDIA L40S instance prices: AWS vs Azure
8 instance types have NVIDIA L40S GPUs, all on AWS EC2. Per GPU, the cheapest is g6e.xlarge on AWS at $1.861 per GPU-hour on demand (1 GPU, $1.861 per hour).
Every NVIDIA L40S option, cheapest first
| Cloud | Type | vCPUs | Memory (GiB) | GPUs | Per GPU /hr | On-demand /hr | 1-yr reserved /hr | Spot /hr |
|---|---|---|---|---|---|---|---|---|
| AWS | g6e.xlarge | 4 | 32 | 1 | $1.861 | $1.861 | $1.172 | $1.552 |
| AWS | g6e.2xlarge | 8 | 64 | 1 | $2.242 | $2.242 | $1.413 | $2.098 |
| AWS | g6e.4xlarge | 16 | 128 | 1 | $3.004 | $3.004 | $1.893 | $1.623 |
| AWS | g6e.8xlarge | 32 | 256 | 1 | $4.529 | $4.529 | $2.853 | $1.627 |
| AWS | g6e.16xlarge | 64 | 512 | 1 | $7.577 | $7.577 | $4.774 | $2.181 |
| AWS | g6e.12xlarge | 48 | 384 | 4 | $2.623 | $10.493 | $6.61 | $6.23 |
| AWS | g6e.24xlarge | 96 | 768 | 4 | $3.766 | $15.066 | $9.491 | $7.469 |
| AWS | g6e.48xlarge | 192 | 1536 | 8 | $3.766 | $30.131 | $18.983 | $8.504 |
Other GPUs
AMD alveo U250 fpga 64 gbAMD instinct MI25 16 gbAMD radeon pro V520AMD radeon pro V620 32 gbAMD radeon pro V710aws inferentiaaws INFERENTIA2aws trainiumNVIDIA A10NVIDIA A10 24 gbNVIDIA A10GNVIDIA A100NVIDIA H100NVIDIA H200NVIDIA L4NVIDIA pcie A100 80 gbNVIDIA pcie H100 94 gbNVIDIA rtx pro 4500NVIDIA rtx pro server 6000NVIDIA T4NVIDIA T4GNVIDIA tesla K80NVIDIA tesla M60NVIDIA tesla M60 16 gbNVIDIA tesla T4 16 gbNVIDIA tesla V100NVIDIA tesla V100 16 gb
On-demand Linux prices in USD per hour, in each cloud's home region: US East (N. Virginia) for AWS, East US for Azure. Previous-generation types are left out.