NVIDIA H100 cloud GPU prices
Compare H100 cloud rental rates across providers, including the reported memory configuration and minimum instance size. An eight-GPU rate per GPU is useful for comparison, but the full eight-GPU instance is what you pay for.
Rates dated Oct 14, 2026–Oct 14, 2026
Publication dates, not live quotes. Confirm the current rate and capacity with the provider.
Catalog generated .
Lowest listed on-demand rate
$3.19/GPU·hr
RunPod · H100 NVL 94GB · NVL · 94 GB per GPU · 1 GPUs · $3.19/instance·hr · US-KS-2
Lowest listed spot / interruptible rate
$0.790/GPU·hr
Nebius · H100 80GB · SXM · 80 GB per GPU · 1 GPUs · $0.790/instance·hr · eu-north1
Compare rental prices
Lowest listed compute rates. Explore comparison filters for your region.
| Provider / GPU / variant | VRAM per GPU | Pricing | Per GPU / hr | Full instance / hr | Region | Provider / rate date |
|---|---|---|---|---|---|---|
| Nebius H100 80GB · SXM Instance: gpu-h100-sxm 1gpu-16vcpu-200gb Link to offer | 80 GB | Spot / interruptible | $0.790 | $0.790 1 GPUs | eu-north1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Nebius H100 80GB · SXM Instance: gpu-h100-sxm 8gpu-128vcpu-1600gb Link to offer | 80 GB | Spot / interruptible | $0.790 | $6.32 8 GPUs | eu-north1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Google Cloud H100 80GB · Unspecified Instance: a3-highgpu-1g Link to offer | 80 GB | Spot / interruptible | $1.09 | $1.09 1 GPUs | europe-north1-c Stock unknown Stock & project cost | Check provider priceRate dated |
| Google Cloud H100 80GB · Unspecified Instance: a3-highgpu-2g Link to offer | 80 GB | Spot / interruptible | $1.09 | $2.18 2 GPUs | europe-north1-c Stock unknown Stock & project cost | Check provider priceRate dated |
| Google Cloud H100 80GB · Unspecified Instance: a3-highgpu-4g Link to offer | 80 GB | Spot / interruptible | $1.09 | $4.35 4 GPUs | europe-north1-c Stock unknown Stock & project cost | Check provider priceRate dated |
| Google Cloud H100 80GB · Unspecified Instance: a3-highgpu-8g Link to offer | 80 GB | Spot / interruptible | $1.14 | $9.14 8 GPUs | europe-north1-c Stock unknown Stock & project cost | Check provider priceRate dated |
| Azure H100 NVL 94GB · Unspecified Instance: Standard_NC40ads_H100_v5 Link to offer | 94 GB | Spot / interruptible | $1.29 | $1.29 1 GPUs | eastus Stock unknown Stock & project cost | Check provider priceRate dated |
| Azure H100 NVL 94GB · Unspecified Instance: Standard_NC80adis_H100_v5 Link to offer | 94 GB | Spot / interruptible | $1.29 | $2.58 2 GPUs | eastus Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 8H100.80S.176V Link to offer | 80 GB | Spot / interruptible | $2.06 | $16.51 8 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 1H100.80S.30V Link to offer | 80 GB | Spot / interruptible | $2.06 | $2.06 1 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 2H100.80S.80V Link to offer | 80 GB | Spot / interruptible | $2.06 | $4.13 2 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 4H100.80S.176V Link to offer | 80 GB | Spot / interruptible | $2.06 | $8.26 4 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| AWS H100 80GB · Unspecified Instance: p5.48xlarge Link to offer | 80 GB | Spot / interruptible | $2.25 | $18.02 8 GPUs | ca-central-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| AWS H100 80GB · Unspecified Instance: p5.4xlarge Link to offer | 80 GB | Spot / interruptible | $2.63 | $2.63 1 GPUs | us-west-2 Stock unknown Stock & project cost | Check provider priceRate dated |
| RunPod H100 NVL 94GB · NVL Instance: NVIDIA H100 NVL Link to offer | 94 GB | On-demand | $3.19 | $3.19 1 GPUs | US-KS-2 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda H100 80GB · PCIe Instance: gpu_1x_h100_pcie Link to offer | 80 GB | On-demand | $3.29 | $3.29 1 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| RunPod H100 80GB · Unspecified Instance: NVIDIA H100 80GB HBM3 Link to offer | 80 GB | On-demand | $3.99 | $3.99 1 GPUs | AP-JP-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| RunPod H100 80GB · Unspecified Instance: NVIDIA H100 80GB HBM3 Link to offer | 80 GB | On-demand | $3.99 | $7.98 2 GPUs | US-GA-2 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda H100 80GB · SXM5 Instance: gpu_8x_h100_sxm5 Link to offer | 80 GB | On-demand | $3.99 | $31.92 8 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda H100 80GB · SXM5 Instance: gpu_4x_h100_sxm5 Link to offer | 80 GB | On-demand | $4.09 | $16.36 4 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 4H100.80S.176V Link to offer | 80 GB | On-demand | $4.13 | $16.51 4 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 8H100.80S.176V Link to offer | 80 GB | On-demand | $4.13 | $33.02 8 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 1H100.80S.30V Link to offer | 80 GB | On-demand | $4.13 | $4.13 1 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch H100 80GB · Unspecified Instance: 2H100.80S.80V Link to offer | 80 GB | On-demand | $4.13 | $8.26 2 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda H100 80GB · SXM5 Instance: gpu_2x_h100_sxm5 Link to offer | 80 GB | On-demand | $4.19 | $8.38 2 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda H100 80GB · SXM5 Instance: gpu_1x_h100_sxm5 Link to offer | 80 GB | On-demand | $4.29 | $4.29 1 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Nebius H100 80GB · SXM Instance: gpu-h100-sxm 1gpu-16vcpu-200gb Link to offer | 80 GB | On-demand | $4.50 | $4.50 1 GPUs | eu-north1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Nebius H100 80GB · SXM Instance: gpu-h100-sxm 8gpu-128vcpu-1600gb Link to offer | 80 GB | On-demand | $4.50 | $36.00 8 GPUs | eu-north1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Google Cloud H100 80GB · Unspecified Instance: a3-edgegpu-8g Link to offer | 80 GB | On-demand | $5.38 | $43.07 8 GPUs | us-east4-a Stock unknown Stock & project cost | Check provider priceRate dated |
| AWS H100 80GB · Unspecified Instance: p5.4xlarge Link to offer | 80 GB | On-demand | $6.88 | $6.88 1 GPUs | us-east-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| AWS H100 80GB · Unspecified Instance: p5.48xlarge Link to offer | 80 GB | On-demand | $6.88 | $55.04 8 GPUs | us-east-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Azure H100 NVL 94GB · Unspecified Instance: Standard_NC40ads_H100_v5 Link to offer | 94 GB | On-demand | $6.98 | $6.98 1 GPUs | eastus Stock unknown Stock & project cost | Check provider priceRate dated |
| Azure H100 NVL 94GB · Unspecified Instance: Standard_NC80adis_H100_v5 Link to offer | 94 GB | On-demand | $6.98 | $13.96 2 GPUs | eastus Stock unknown Stock & project cost | Check provider priceRate dated |
| Oracle Cloud H100 80GB · Unspecified Instance: BM.GPU.H100.8 Link to offer | 80 GB | On-demand | $10.00 | $80.00 8 GPUs | af-casablanca-1 Stock unknown Stock & project cost | Check provider priceRate dated |
Manufacturer specifications, with conditions
Reviewed September 26, 2026 against NVIDIA documentation. These are hardware specifications and theoretical peaks, not NVGPU measurements or third-party benchmark results. Sparse Tensor Core peaks require supported structured sparsity; they are not expected dense training throughput.
| Reference variant | Memory | Memory bandwidth | FP16 Tensor Core peak | Conditions and source |
|---|---|---|---|---|
| H100 SXM | 80 GB HBM3 | 3.35 TB/s | 1,979 TFLOPS with sparsity | SXM reference; do not apply its bandwidth or peak throughput to an unspecified or PCIe rental. NVIDIA source |
| H100 NVL (per GPU) | 94 GB HBM3 | 3.9 TB/s | 1,671 TFLOPS with sparsity | NVL is distinct from H100 80GB. A two-GPU NVL pair has 188 GB combined memory; that is not per-GPU VRAM. NVIDIA source |
NVGPU has not run application benchmarks for these comparisons. To assess a third-party result, require the model and revision, precision, batch size, sequence lengths, GPU count and variant, software versions, interconnect, test date and methodology.
Before you rent
- Check whether the listing is H100 or H100 NVL and compare its reported VRAM before choosing.
- For multi-GPU jobs, confirm the interconnect and topology with the provider; GPU count alone does not establish training performance.
- Use spot instances only when your workload can recover from interruptions and checkpoints are stored persistently.
What is included?
These are listed compute rates. The instance shown is the configuration being priced, not evidence of the provider's smallest available rental. Storage, data transfer, tax, licenses and support can be additional. Reserved contracts, commitment discounts and serverless per-request charges are not compared. Listed spot capacity can disappear or be interrupted.
Hourly price vs. total cost
Multiply the full-instance hourly rate by billed hours, then add storage, transfer and other charges. Compare the same workload and quality target. Rental throughput and uptime have not been measured by NVGPU.