Two Nvidia data center GPUs, one Grace Hopper and one Pascal: 96 GB HBM3 against 8 GB GDDR5, 21x the memory bandwidth on the GH200, and NVLink 900 GB/s on the GH200 where the P4 is PCIe only.

At a glance

Updated 21 minutes ago
Memory
96 GB
HBM3
Memory bandwidth
4.00 TB/s
From
$6.50 /GPU/hr
4 providers
Memory
8 GB
GDDR5
Memory bandwidth
192 GB/s
From
$0.65 /GPU/hr
1 provider

Price comparison

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing GH200 P4 Difference
On-demand $6.50 $0.65 9.9x more expensive on GH200
Spot No spot listings $0.12
Reserved No reserved listings $0.34
Median $6.50 $0.81 8x more expensive on GH200

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Price history

GH200 vs P4 price history

Weekly median on-demand price per GPU per hour

Last 12 months
Aggregating historical prices...

Specs comparison

Spec GH200 P4 Difference
Memory
Capacity 96 GB HBM3 8 GB GDDR5 12x more on GH200
Bandwidth 4,000 GB/s 192 GB/s 21x higher on GH200
Bus width 256-bit
Compute · dense
FP8 1,979 TFLOPS Not supported GH200 only
FP16 / BF16 989.5 TFLOPS
INT8 1,979 TOPS 22 TOPS 90x higher on GH200
FP32 67 TFLOPS 5.5 TFLOPS 12x higher on GH200
FP64 34 TFLOPS Not supported GH200 only
Platform
Interconnect NVLink 900 GB/s PCIe only NVLink on GH200 only
Released Q2 2023 Q3 2016 7 years newer on GH200
Precision
Supported formats FP8FP16BF16TF32FP32FP64INT8 FP16FP32INT8

Compute: Vendor peak figures, dense and per GPU. Not measured throughput.

Source: GH200 datasheet and P4 datasheet.

Where to rent them

Providers listing these GPUs, those with both first, so you can switch without moving clouds.

Provider GH200 /GPU/hr P4 /GPU/hr
CoreWeave logo CoreWeave On-Demand $6.50 --
Lambda Labs logo Lambda Labs On-Demand $2.29 --
Sesterce logo Sesterce On-Demand $2.52 --
Vultr logo Vultr Spot $1.99 --
Google Cloud logo Google Cloud -- On-Demand $0.65

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia GH200 was last updated on Sept. 7, 2026, and for Nvidia P4 on Sept. 7, 2026.