whichvm

AWS · ai

AWS Inferentia cloud pricing

Compare every cloud instance with AWS Inferentia accelerators across AWS: 4 instance types with 1 to 16 Inferentias. Cheapest on demand: $0.228 per Inferentia-hour on AWS inf1.xlarge in US East (N. Virginia).

on-demand / Inferentia-hour
$0.228

AWS inf1.xlarge

spot / Inferentia-hour
$0.0337

AWS inf1.24xlarge

memory per device
8 GB
instance types
4

1 cloud

Every AWS Inferentia instance

cheapest region per instance · Linux · on-demand per GPU-hour = hourly price ÷ GPU count · government regions excluded

ProviderInstanceGPUsGPU memoryvCPURAMOn-demand /hrPer GPU-hrSpot per GPU-hrCheapest region
AWSinf1.xlarge18 GiB48 GiB$0.228$0.228$0.0434US East (N. Virginia) us-east-1
AWSinf1.6xlarge432 GiB2448 GiB$1.18$0.295$0.0344US East (N. Virginia) us-east-1
AWSinf1.24xlarge16128 GiB96192 GiB$4.721$0.2951$0.0337US East (N. Virginia) us-east-1
AWSinf1.2xlarge18 GiB816 GiB$0.362$0.362$0.0608US East (N. Virginia) us-east-1

Other GPUs

B300 $17.80B200 $14.24RTX PRO 6000 Blackwell $0.5596H200 $7.912Trainium2 $6.447Radeon Pro V710 $1.994H100 NVL $6.98L40S $1.861Inferentia2 $0.7582L4 $0.7045RTX 4000 Ada $0.52Qualcomm Cloud AI 100 $1.115H100 $6.88Trainium $1.344Habana Gaudi $1.639Radeon Pro V620 $2.54A10G $1.006A10 $2.20T4G $0.42A16 $0.471A100 80GB $2.397A40 $1.712A100 40GB $2.745Radeon Pro V520 $0.3785Quadro RTX 6000 $1.50T4 $0.526V100 $3.06P40 $2.07P100 $2.07M60 $0.75K80 $0.90GRID K520 $0.65

AWS Inferentia FAQ

How much does an Inferentia cost per hour in the cloud?

On demand, from $0.228 per Inferentia-hour (AWS inf1.xlarge, $0.228 per hour for 1 Inferentia in US East (N. Virginia)). Spot capacity starts at $0.0337 per Inferentia-hour on AWS inf1.24xlarge.

Which clouds offer Inferentia instances?

AWS (from $0.228 per GPU-hour, e.g. inf1.xlarge).

How much memory does the Inferentia have?

8 GB per device. Cloud instances combine 1 to 16 of them.