Nvidia H100 vs Nvidia RTX PRO 6000

The H100 has 2.1x the bandwidth, while the RTX PRO 6000 is newer and has 20% more memory. The RTX PRO 6000 is typically cheaper.

At a glance

Memory

20% more on RTX PRO 6000

H100: 80 GB

RTX PRO 6000: 96 GB

Memory bandwidth

2.1x higher on H100

H100: 3.35 TB/s

RTX PRO 6000: 1.60 TB/s

Cheapest on-demand

50% cheaper on RTX PRO 6000

H100: $1.30 /GPU/hr

RTX PRO 6000: $0.65 /GPU/hr

Price comparison

Median price per GPU per hour by billing type, with the cheapest listing under it.

Billing	H100	RTX PRO 6000	Difference
On-demand	$3.39 /GPU/hr from $1.30	$2.17 /GPU/hr from $0.65	36% cheaper on RTX PRO 6000
Reserved	$3.03 /GPU/hr from $1.53 (1 mo)	$1.81 /GPU/hr from $0.48 (1 mo)	40% cheaper on RTX PRO 6000
Spot	$2.00 /GPU/hr from $0.67	$1.19 /GPU/hr from $0.27	40% cheaper on RTX PRO 6000

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 PRO 6000 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	H100	RTX PRO 6000	Difference
Memory
Capacity	80 GB HBM3 94 GB on NVL	96 GB GDDR7	20% more on RTX PRO 6000
Bandwidth	3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL	1,597 GB/s	2.1x higher on H100
Bus width	5,120-bit	512-bit	10x wider on H100
Compute · dense
FP4	Not supported	2,000 TFLOPS	RTX PRO 6000 only
FP8	1,979 TFLOPS	1,000 TFLOPS	98% higher on H100
FP16 / BF16	989.5 TFLOPS	500 TFLOPS	98% higher on H100
INT8	1,979 TOPS	1,000 TOPS	98% higher on H100
FP32	67 TFLOPS	120 TFLOPS	79% higher on RTX PRO 6000
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	600 W	17% higher on H100
Released	Q3 2022	Q1 2025	2 years newer on RTX PRO 6000
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 PRO 6000 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 PRO 6000
Lium Distributed	$1.30 /GPU/hr On-demand SXM	$1.20 /GPU/hr On-demand
Vast.ai USA	$1.60 /GPU/hr On-demand SXM	$1.01 /GPU/hr On-demand
HyperAI Hong Kong	$1.80 /GPU/hr On-demand	$0.80 /GPU/hr On-demand
GPU.ai UAE	$2.42 /GPU/hr On-demand NVL	$1.69 /GPU/hr On-demand
Runpod USA	$2.59 /GPU/hr On-demand NVL	$1.64 /GPU/hr On-demand
Runcrate USA	$2.59 /GPU/hr On-demand SXM	--
EmpirioLabs AI USA	$2.60 /GPU/hr On-demand	--
Jarvislabs India	$2.69 /GPU/hr On-demand SXM	--
Packet·ai USA	--	$0.66 /GPU/hr On-demand
GPUhub Singapore	--	$1.10 /GPU/hr On-demand
UpCloud Finland	--	$1.88 /GPU/hr On-demand