A data center GPU against a workstation card, one Hopper and one Pascal: 141 GB HBM3e against 24 GB GDDR5X, 11x the memory bandwidth on the H200, and NVLink 900 GB/s on the H200 where the P6000 is PCIe only.
At a glance
Updated 6 minutes ago- Memory
- 141 GB
- HBM3e
- Memory bandwidth
- 4.80 TB/s
- From
- $2.09 /GPU/hr
- 46 providers
- Memory
- 24 GB
- GDDR5X
- Memory bandwidth
- 432 GB/s
- From
- $1.10 /GPU/hr
- 1 provider
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | H200 | P6000 | Difference |
|---|---|---|---|
| On-demand | $2.09 | $1.10 | 47% cheaper on P6000 |
| Spot | $1.32 | No spot listings | |
| Reserved | $2.29 | No reserved listings | |
| Median | $4.40 | $1.10 | 4x more expensive on H200 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
H200 vs P6000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H200 | P6000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 141 GB HBM3e | 24 GB GDDR5X | 5.9x more on H200 |
| Bandwidth | 4,800 GB/s | 432 GB/s | 11x higher on H200 |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP8 | 1,979 TFLOPS | Not supported | H200 only |
| FP16 / BF16 | 989.5 TFLOPS | ||
| INT8 | 1,979 TOPS | Not supported | H200 only |
| FP32 | 67 TFLOPS | 12.6 TFLOPS | 5.3x higher on H200 |
| FP64 | 34 TFLOPS | Not supported | H200 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s | PCIe only | NVLink on H200 only |
| Board power | 700 W | 250 W | 2.8x higher on H200 |
| Released | Q4 2023 | Q4 2016 | 7 years newer on H200 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP16FP32 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: H200 datasheet and P6000 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | H200 /GPU/hr | P6000 /GPU/hr |
|---|---|---|
Koyeb
|
On-Demand $3.00 | -- |
GPU.ai
|
On-Demand $3.29 | -- |
Vast.ai
|
On-Demand $3.34 | -- |
Runpod
|
On-Demand $3.59 | -- |
Massed Compute
|
On-Demand $3.62 | -- |
Lium
|
On-Demand $3.65 | -- |
Verda
|
On-Demand $4.00 | -- |
Lyceum
|
On-Demand $4.29 | -- |
Paperspace
|
-- | On-Demand $1.10 |
46 providers list the H200 and 1 the P6000. Every listing is on the H200 page and the P6000 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia H200 was last updated on Sept. 7, 2026, and for Nvidia P6000 on Sept. 7, 2026.