The H200 is newer, with 8.8x the memory and 11x the bandwidth. The A4000 is typically cheaper.
At a glance
Memory
8.8x more on H200
- A4000
- 16 GB
- H200
- 141 GB
Memory bandwidth
11x higher on H200
- A4000
- 448 GB/s
- H200
- 4,800 GB/s
Cheapest on-demand
96% cheaper on A4000
- A4000
- $0.07 /GPU/hr
- H200
- $2.09 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A4000 | H200 | Difference |
|---|---|---|---|
| On-demand | $0.18 /GPU/hr from $0.07 | $4.40 /GPU/hr from $2.09 | 96% cheaper on A4000 |
| Reserved | $0.18 /GPU/hr from $0.06 (3 mo) | $4.00 /GPU/hr from $2.23 (1 mo) | 96% cheaper on A4000 |
| Spot | -- /GPU/hr from $0.06 | $2.62 /GPU/hr from $1.32 |
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. No median for spot on the A4000: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
A4000 vs H200 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A4000 | H200 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 16 GB GDDR6 | 141 GB HBM3e | 8.8x more on H200 |
| Bandwidth | 448 GB/s | 4,800 GB/s | 11x higher on H200 |
| Bus width | 256-bit | ||
| Compute · dense | |||
| FP8 | Not supported | 1,979 TFLOPS | H200 only |
| FP16 / BF16 | 76.7 TFLOPS | 989.5 TFLOPS | 13x higher on H200 |
| INT8 | 1,979 TOPS | ||
| FP32 | 19.2 TFLOPS | 67 TFLOPS | 3.5x higher on H200 |
| FP64 | Not supported | 34 TFLOPS | H200 only |
| Platform | |||
| Interconnect | PCIe only | NVLink 900 GB/s | NVLink on H200 only |
| Board power | 140 W | 700 W | 5x higher on H200 |
| Released | Q2 2021 | Q4 2023 | 3 years newer on H200 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A4000 datasheet and H200 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | A4000 | H200 |
|---|---|---|
Vast.ai
USA
|
$0.07 /GPU/hr On-demand | $3.56 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.09 /GPU/hr On-demand | $3.29 /GPU/hr On-demand NVL |
Hyperstack
UK
|
$0.15 /GPU/hr On-demand | $3.99 /GPU/hr On-demand SXM |
Runcrate
USA
|
$0.20 /GPU/hr On-demand PCIe | $4.24 /GPU/hr On-demand SXM |
Spheron
Singapore
|
$0.16 /GPU/hr On-demand PCIe | -- |
Sesterce
France
|
$0.17 /GPU/hr On-demand | -- |
Runpod
USA
|
$0.17 /GPU/hr On-demand | -- |
EmpirioLabs AI
USA
|
$0.25 /GPU/hr On-demand | -- |
Lium
Distributed
|
-- | $2.95 /GPU/hr On-demand SXM |
Massed Compute
USA
|
-- | $3.62 /GPU/hr On-demand NVL |
Jarvislabs
India
|
-- | $3.99 /GPU/hr On-demand SXM |
Lyceum
Germany
|
-- | $4.29 /GPU/hr On-demand |
13 providers list the A4000 and 51 the H200. Every listing is on the A4000 page and the H200 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia T4
16 GB GDDR6 · 33% less bandwidth than the A4000
From $0.10 /GPU/hr Compare -
Nvidia RTX 4000 Ada
20 GB GDDR6 · 20% less bandwidth than the A4000
From $0.20 /GPU/hr Compare
-
Nvidia A5000
24 GB GDDR6 · 71% more bandwidth than the A4000
From $0.23 /GPU/hr Compare
-
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
Our data for Nvidia A4000 was last updated on Sept. 14, 2026, and for Nvidia H200 on Sept. 14, 2026.