NVIDIA · Hopper
NVIDIA H200 cloud pricing
Compare every cloud instance with NVIDIA H200 GPUs across AWS, Azure: 3 instance types with 8 to 8 H200s. Cheapest on demand: $7.912 per H200-hour on AWS p5e.48xlarge in US East (Ohio).
- on-demand / H200-hour
- $7.912
- spot / H200-hour
- –
- memory per device
- 141 GB
- instance types
- 3
AWS p5e.48xlarge
not offered
2 clouds
Every NVIDIA H200 instance
cheapest region per instance · Linux · on-demand per GPU-hour = hourly price ÷ GPU count · government regions excluded
| Provider | Instance | GPUs | GPU memory | vCPU | RAM | On-demand /hr | Per GPU-hr | Spot per GPU-hr | Cheapest region |
|---|---|---|---|---|---|---|---|---|---|
| AWS | p5e.48xlarge | 8 | 1,128 GiB | 192 | 2 TiB | $63.30 | $7.912 | – | US East (Ohio) us-east-2 |
| AWS | p5en.48xlarge | 8 | 141 GiB | 192 | 2 TiB | $63.30 | $7.912 | – | US East (N. Virginia) us-east-1 |
| Azure | ND96isr H200 v5 | 8 | 1,128 GiB | 96 | 1,900 GiB | $84.80 | $10.60 | – | East US 2 eastus2 |
Other GPUs
B300 $17.80B200 $14.24RTX PRO 6000 Blackwell $0.5596Trainium2 $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 $0.3785Inferentia $0.228Quadro RTX 6000 $1.50T4 $0.526V100 $3.06P40 $2.07P100 $2.07M60 $0.75K80 $0.90GRID K520 $0.65
NVIDIA H200 FAQ
How much does an H200 cost per hour in the cloud?
On demand, from $7.912 per H200-hour (AWS p5e.48xlarge, $63.30 per hour for 8 H200 in US East (Ohio)).
Which clouds offer H200 instances?
AWS (from $7.912 per GPU-hour, e.g. p5e.48xlarge); Azure (from $10.60 per GPU-hour, e.g. ND96isr H200 v5).
How much memory does the H200 have?
141 GB per GPU (Hopper architecture). Cloud instances combine 1 to 8 of them.