gpu catalog: h200 sxm
An H100 with 76% more memory and 43% more bandwidth: 141 GB of HBM3e makes it the sweet spot for large-model inference without Blackwell pricing.
| GPU | VRAM | Regions | Availability | Price / GPU | |
|---|---|---|---|---|---|
| H200 SXMcommunity | 141G | 5 regions | high availability | $3.59/hr | launch |
An H100 with 76% more memory and 43% more bandwidth: 141 GB of HBM3e makes it the sweet spot for large-model inference without Blackwell pricing. VRAM141 GB HBM3e Memory bandwidth4.8 TB/s FP16 tensor990 TFLOPS ArchitectureHopper InterconnectNVLink 4 (900 GB/s) Board power700 W Released2024 Regionsasia-pacific, ca-central, eu-west, us-east, us-west | |||||
| H200 SXM | 141G | 5 regions | high availability | $4.59/hr | launch |
| L40S | 48G | 3 regions | high availability | $0.80/hr | launch |
| RTX 5090community | 32G | 8 regions | high availability | $0.43/hr | launch |
| RTX 4090community | 24G | 7 regions | high availability | $0.34/hr | launch |
| A100 | 80G | 5 regions | high availability | $1.07/hr | launch |
| RTX PRO 6000 | 96G | 4 regions | high availability | $2.09/hr | launch |
| RTX 3090community | 24G | 6 regions | high availability | $0.15/hr | launch |
| H100 PCIE | 80G | 2 regions | high availability | $1.98/hr | launch |
| A100community | 80G | 5 regions | high availability | $0.88/hr | launch |
| H100 SXM | 80G | 4 regions | high availability | $3.49/hr | launch |
| L40Scommunity | 48G | 4 regions | available | $0.79/hr | launch |
| A100 40GBcommunity | 40G | 6 regions | available | $0.40/hr | launch |
| RTX A6000 | 48G | 3 regions | available | $0.40/hr | launch |
| RTX A4000 | 16G | 1 region | available | $0.12/hr | launch |
| RTX 6000 ADA | 48G | 2 regions | available | $0.65/hr | launch |
| RTX 4090 | 24G | 3 regions | available | $0.74/hr | launch |
| RTX 5080community | 16G | 6 regions | available | $0.24/hr | launch |
| L4 | 24G | 3 regions | available | $0.49/hr | launch |
| RTX PRO 4500 | 32G | 1 region | available | $0.72/hr | launch |
| RTX A4000community | 16G | 4 regions | available | $0.10/hr | launch |
| A40 | 48G | 3 regions | available | $0.49/hr | launch |
| RTX 3080community | 10G | 3 regions | available | $0.14/hr | launch |
| RTX 4000 ADAcommunity | 20G | 2 regions | running low | $0.20/hr | launch |
| RTX 2000 ADA | 16G | 2 regions | running low | $0.24/hr | launch |
| RTX 4000 ADA | 20G | 2 regions | running low | $0.28/hr | launch |
| RTX 6000 ADAcommunity | 48G | 2 regions | running low | $0.74/hr | launch |
| L40 | 48G | 1 region | running low | $0.78/hr | launch |
| RTX 4080community | 16G | 4 regions | running low | $0.21/hr | launch |
| H100 NVLcommunity | 94G | 5 regions | running low | $2.67/hr | launch |
| H200 NVLcommunity | 141G | 2 regions | running low | $4.69/hr | launch |
| RTX A5000 | 24G | 1 region | running low | $0.27/hr | launch |
| RTX A6000community | 48G | 3 regions | running low | $0.41/hr | launch |
| RTX 3090 | 24G | 1 region | running low | $0.50/hr | launch |
| L40community | 48G | 1 region | running low | $0.69/hr | launch |
| RTX 5090 | 32G | 1 region | running low | $0.99/hr | launch |
| RTX PRO 6000community | 96G | 1 region | running low | $1.69/hr | launch |
| H100 NVL | 94G | 1 region | running low | $3.19/hr | launch |
| H200 NVL | 141G | 1 region | running low | $3.29/hr | launch |
| B200 | 192G | 1 region | running low | $6.79/hr | launch |
| B300 | 288G | 1 region | running low | $7.89/hr | launch |
| L4community | 24G | 2 regions | running low | $0.33/hr | launch |
| B200community | 192G | 1 region | running low | $7.50/hr | launch |
| V100community | 16G | 1 region | running low | $0.13/hr | launch |
| RTX A4500community | 20G | 1 region | running low | $0.13/hr | launch |
| RTX A5000community | 24G | 1 region | running low | $0.30/hr | launch |
| RTX PRO 4500community | 32G | 1 region | running low | $0.35/hr | launch |
| H100 SXMcommunity | 80G | 1 region | running low | $3.95/hr | launch |
lowest live on-demand rate per GPU, refreshed continuously · per-second billing
Our floor price for the H200 SXM, sampled continuously across every provider in the fleet and rolled up to one point per day. A dot on the zero line is a day we checked and found nothing launchable; a shaded break is a day we did not sample. Those are different facts, so this chart never draws one as the other.
Daily trend, updated hourly · Full 15-minute history available via API
| Provider | Price / GPU / hr | Notes |
|---|---|---|
| GPU.ai (Secure Cloud) | $4.59/hr | Vetted data center capacity, per-second billing |
| GPU.ai (Community Cloud) | $3.59/hr | Marketplace capacity from independent suppliers |
| CoreWeave | $6.30/hr | Public on-demand list rate |
| AWS | $7.91/hr | Public on-demand list rate |
| Azure | $10.60/hr | Public on-demand list rate |
competitor rates are public on-demand list prices, refreshed daily · gpu.ai prices are live floor rates with zero markup · market data via Compute Prices
faq
H200 SXM cloud instances on GPU.ai currently start at $3.59 per GPU per hour, billed per second. That is the live floor price across every provider in our fleet. We route your launch to the cheapest provider with stock and add zero markup.
The NVIDIA H200 SXM has 141 GB of HBM3e memory with up to 4,800 GB/s of bandwidth. GPU.ai reports the minimum VRAM actually delivered across our fleet, so the figure you see at launch is the figure you get.
Yes: real 2× H200 SXM nodes are launchable right now, from $5.12 per GPU per hour. We only advertise node sizes that exist in live inventory, not theoretical configurations.
GPU.ai aggregates a dozen-plus GPU clouds and passes through each provider's raw price with no markup, so the same silicon is typically far cheaper than hyperscaler list rates. The comparison table on this page shows the current public on-demand list prices side by side.
Billing is per second, starting when your instance is SSH-ready and stopping the moment you terminate. There are no minimum commitments, no reservation fees, and no egress surprises: you pay the listed hourly rate pro-rated to the second.