NVIDIA GH200 Grace Hopper cloud pricing
- Vendor
- NVIDIA
- VRAM
- 96 GB
- Architecture
- Hopper
- FP16
- 989 TFLOPS
- Launched
- 2023
0 results
No offerings match your filters.
Frequently asked questions
How much does an NVIDIA GH200 Grace Hopper cost per hour in the cloud?
The lowest on-demand NVIDIA GH200 Grace Hopper price we track is - per GPU-hour. Spot and reserved rates are usually lower; sort the table above by price to see the current rate from every provider.
What is the cheapest NVIDIA GH200 Grace Hopper cloud provider?
Sort the table by price (low to high) to see the cheapest NVIDIA GH200 Grace Hopper provider right now. Marketplace and spot providers often undercut hyperscalers by a wide margin for the same NVIDIA GH200 Grace Hopper.
Which cloud providers offer NVIDIA GH200 Grace Hopper GPUs?
Every provider with published NVIDIA GH200 Grace Hopper availability is listed above, with per-hour pricing, the number of GPUs per instance, region coverage, and on-demand, spot, and reserved rates.
Is spot NVIDIA GH200 Grace Hopper cheaper than on-demand?
Yes. Spot (preemptible) capacity is typically 40-70% cheaper than on-demand but can be reclaimed at short notice. Use the pricing-mode filter to compare on-demand, spot, and reserved rows side by side.
How much VRAM does the NVIDIA GH200 Grace Hopper have?
The NVIDIA GH200 Grace Hopper ships with 96 GB of VRAM. Larger VRAM lets you fit bigger models and batch sizes without sharding.
Is the NVIDIA GH200 Grace Hopper good for AI training and inference?
The NVIDIA GH200 Grace Hopper is used for both LLM training and inference. Match its VRAM and throughput (shown above) to your model size, and use spot capacity for fault-tolerant training to cut costs.