The H100 has 2.5x the memory and 87% more bandwidth. The RTX 5090 is newer and typically cheaper.
At a glance
Memory
2.5x more on H100
- H100
- 80 GB
- RTX 5090
- 32 GB
Memory bandwidth
87% higher on H100
- H100
- 3.35 TB/s
- RTX 5090
- 1.79 TB/s
Cheapest on-demand
73% cheaper on RTX 5090
- H100
- $1.30 /GPU/hr
- RTX 5090
- $0.35 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | H100 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $3.44 /GPU/hr from $1.30 | $0.65 /GPU/hr from $0.35 | 81% cheaper on RTX 5090 |
| Reserved | $3.09 /GPU/hr from $1.53 (1 mo) | $0.59 /GPU/hr from $0.21 (1 mo) | 81% cheaper on RTX 5090 |
| Spot | $2.23 /GPU/hr from $0.67 | $0.45 /GPU/hr from $0.25 | 80% cheaper on RTX 5090 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. Verify before provisioning. More on how we price.
Price history
H100 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H100 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM3 94 GB on NVL | 32 GB GDDR7 | 2.5x more on H100 |
| Bandwidth | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 1,792 GB/s | 87% higher on H100 |
| Bus width | 5,120-bit | 512-bit | 10x wider on H100 |
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | 1,979 TFLOPS | 419 TFLOPS | 4.7x higher on H100 |
| FP16 / BF16 | 989.5 TFLOPS | 209.5 TFLOPS | 4.7x higher on H100 |
| INT8 | 1,979 TOPS | 838 TOPS | 2.4x higher on H100 |
| FP32 | 67 TFLOPS | 104.8 TFLOPS | 56% higher on RTX 5090 |
| FP64 | 34 TFLOPS | Not supported | H100 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | PCIe only | NVLink on H100 only |
| Board power | 700 W | 575 W | 22% higher on H100 |
| Released | Q3 2022 | Q1 2025 | 2 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: H100 datasheet and RTX 5090 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | H100 | RTX 5090 |
|---|---|---|
Lium
Distributed
|
$1.30 /GPU/hr On-demand SXM | $0.45 /GPU/hr On-demand |
HyperAI
Hong Kong
|
$1.80 /GPU/hr On-demand | $0.35 /GPU/hr On-demand |
Vast.ai
USA
|
$1.73 /GPU/hr On-demand SXM | $0.40 /GPU/hr On-demand |
GPU.ai
UAE
|
$1.98 /GPU/hr On-demand PCIe | $0.47 /GPU/hr On-demand |
Hyperstack
UK
|
$2.50 /GPU/hr On-demand PCIe | -- |
EmpirioLabs AI
USA
|
$2.60 /GPU/hr On-demand | -- |
Spheron
Singapore
|
$2.65 /GPU/hr On-demand PCIe | -- |
Jarvislabs
India
|
$2.69 /GPU/hr On-demand SXM | -- |
GPUhub
Singapore
|
-- | $0.46 /GPU/hr On-demand |
Theta EdgeCloud
Distributed
|
-- | $0.64 /GPU/hr On-demand |
Nova Cloud
Canada
|
-- | $0.66 /GPU/hr On-demand PCIe |
Runpod
USA
|
-- | $0.69 /GPU/hr On-demand |
56 providers list the H100 and 23 the RTX 5090. Every listing is on the H100 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia B300
288 GB HBM3e · 2.4x the bandwidth of the H100
From $4.99 /GPU/hr Compare -
Nvidia H200
141 GB HBM3e · 43% more bandwidth than the H100
From $2.09 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 42% less bandwidth than the H100
From $0.40 /GPU/hr Compare
-
Nvidia RTX PRO 6000
96 GB GDDR7 · workstation card
From $0.65 /GPU/hr Compare
-
Nvidia RTX 4090
24 GB GDDR6X · 44% less bandwidth than the RTX 5090
From $0.26 /GPU/hr Compare
Our data for Nvidia H100 was last updated on Sept. 14, 2026, and for Nvidia RTX 5090 on Sept. 14, 2026.