A data center GPU against a consumer card, one Hopper and one Blackwell: 141 GB HBM3e against 32 GB GDDR7, 2.7x the memory bandwidth on the H200, and NVLink 900 GB/s on the H200 where the RTX 5090 is PCIe only.
At a glance
Memory
- H200
- 141 GB
- RTX 5090
- 32 GB
4.4x more on H200
Memory bandwidth
- H200
- 4.80 TB/s
- RTX 5090
- 1.79 TB/s
2.7x higher on H200
Cheapest on-demand
- H200
- $2.09 /GPU/hr
- RTX 5090
- $0.35 /GPU/hr
6x more expensive on H200
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | H200 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $4.44 /GPU/hr from $2.09 | $0.65 /GPU/hr from $0.35 | 6.8x more expensive on H200 |
| Reserved | $3.80 /GPU/hr from $2.27 (1 mo) | $0.58 /GPU/hr from $0.21 (1 mo) | 6.6x more expensive on H200 |
| Spot | $3.03 /GPU/hr from $1.32 | $0.35 /GPU/hr from $0.19 | 8.6x more expensive on H200 |
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
H200 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H200 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 141 GB HBM3e | 32 GB GDDR7 | 4.4x more on H200 |
| Bandwidth | 4,800 GB/s | 1,792 GB/s | 2.7x higher on H200 |
| Bus width | 512-bit | ||
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | 1,979 TFLOPS | 419 TFLOPS | 4.7x higher on H200 |
| FP16 / BF16 | 989.5 TFLOPS | 209.5 TFLOPS | 4.7x higher on H200 |
| INT8 | 1,979 TOPS | 838 TOPS | 2.4x higher on H200 |
| FP32 | 67 TFLOPS | 104.8 TFLOPS | 1.6x higher on RTX 5090 |
| FP64 | 34 TFLOPS | Not supported | H200 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s | PCIe only | NVLink on H200 only |
| Board power | 700 W | 575 W | 1.2x higher on H200 |
| Released | Q4 2023 | Q1 2025 | 15 months newer on RTX 5090 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: H200 datasheet and RTX 5090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | H200 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
Lium
|
On-Demand $3.00 | On-Demand $0.48 |
Vast.ai
|
On-Demand $3.57 | On-Demand $0.40 |
GPU.ai
|
On-Demand $3.29 | On-Demand $0.47 |
Runpod
|
On-Demand $3.59 | On-Demand $0.69 |
Koyeb
|
On-Demand $3.00 | -- |
Massed Compute
|
On-Demand $3.62 | -- |
Verda
|
On-Demand $4.24 | -- |
Runcrate
|
On-Demand $4.40 | -- |
HyperAI
|
-- | On-Demand $0.35 |
GPUhub
|
-- | On-Demand $0.46 |
Salad
|
-- | On-Demand $0.50 |
Nova Cloud
|
-- | On-Demand $0.63 |
47 providers list the H200 and 20 the RTX 5090. Every listing is on the H200 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 30% less bandwidth than the H200
From $1.30 /GPU/hr Compare -
Nvidia B200
180 GB HBM3e · 60% more bandwidth than the H200
From $3.75 /GPU/hr Compare
-
Nvidia RTX PRO 6000
96 GB GDDR7 · 67% less bandwidth than the H200
From $0.66 /GPU/hr Compare
-
Nvidia RTX 4090
24 GB GDDR6X · 44% less bandwidth than the RTX 5090
From $0.23 /GPU/hr Compare
Our data for Nvidia H200 was last updated on Sept. 14, 2026, and for Nvidia RTX 5090 on Sept. 14, 2026.