H100 · PCIe reference design

NVIDIA H100

80 GB HBM3 · Hopper · 989 FP16 TFLOPS

Live NVIDIA H100 cloud prices from 16 providers, updated .

from$1.50/ GPU / hr
Nosana · median $3.20 across 68 offers
Launch on Nosana

21 offerings from 16 providers

ProviderPer GPU / hourAction
LiumSponsored
Check Lium for NVIDIA H100 availability.
No listed priceVisit
1 GPU
$1.50Launch
1 GPU
from$1.56Launch
4 GPUs · $7.65 total
from$1.913Launch
$2.29Launch
from$2.50
Akash NetworkUp to$100credit
1 GPU
$2.55Launch
$2.60Launch
$2.85Launch
Showing 8 of 21

* We may earn a referral fee or commission from some providers when you sign up through our links. This does not affect ranking or ordering.

NVIDIA H100 price history

The median NVIDIA H100 price is up 19% since November 24, 2025.

MedianLowest
From November 24, 2025 to November 22, 2026, the median price went from $2.69 to $3.20 and the lowest price from $1.83 to $1.50.

Similar GPUs

See more GPUs like this inHighest performance

Frequently asked questions

How much does the H100 cost per hour?
The H100 starts at $1.50 per GPU-hour, with a median of $3.20 across 68 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the H100?
25 providers currently list the H100: Hyperstack, Omega Gradient, Novita AI, Latitude.sh, Geodd, Akash Network and 19 more. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the H100 have?
The H100 comes with 80 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Which LLMs can I run on the H100?
With 80 GB of VRAM, a single H100 can serve models such as gpt-oss-120b, Qwen3.6 35B-A3B, Qwen3 32B, Gemma 4 31B. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.
What's the biggest LLM I can run on multiple H100 GPUs?
The largest models we track that fit across several H100 cards are GLM-5.2 on 8 GPUs at 4-bit, DeepSeek R1 on 8 GPUs at 4-bit, DeepSeek V4 Flash on 3 GPUs at 4-bit. A multi-GPU configuration means you rent and pay for every card for the whole run, and splitting a model across cards costs throughput as well: the GPUs exchange activations on every token, so performance depends on how fast they are wired together. We do not track interconnect, so check the provider's node specification. The table above gives the smallest configuration for each model at 16-bit, 8-bit and 4-bit precision.
Where is the H100 cheapest?
The lowest on-demand price we currently track for the H100 is $1.50 per GPU-hour at Nosana. Because providers update pricing and availability frequently, check the live table above before you launch.