Nvidia A100 vs Nvidia H200

The H200 is newer, with 76% more memory and 2.5x the bandwidth. The A100 is typically cheaper.

At a glance

Memory

76% more on H200

A100: 80 GB

H200: 141 GB

Memory bandwidth

2.5x higher on H200

A100: 1.94 TB/s

H200: 4.80 TB/s

Cheapest on-demand

79% cheaper on A100

A100: $0.43 /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	A100	H200	Difference
On-demand	$1.68 /GPU/hr from $0.43	$4.45 /GPU/hr from $2.09	62% cheaper on A100
Reserved	$1.60 /GPU/hr from $0.66 (24 mo)	$4.00 /GPU/hr from $2.25 (1 mo)	60% cheaper on A100
Spot	$1.19 /GPU/hr from $0.21	$2.62 /GPU/hr from $0.57	54% cheaper on A100

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

A100 vs H200 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	A100	H200	Difference
Memory
Capacity	80 GB HBM2e 40 GB on SXM, PCIe	141 GB HBM3e	76% more on H200
Bandwidth	1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe	4,800 GB/s	2.5x higher on H200
Bus width	5,120-bit
Compute · dense
FP8	Not supported	1,979 TFLOPS	H200 only
FP16 / BF16	312 TFLOPS	989.5 TFLOPS	3.2x higher on H200
INT8	624 TOPS	1,979 TOPS	3.2x higher on H200
FP32	19.5 TFLOPS	67 TFLOPS	3.4x higher on H200
FP64	9.7 TFLOPS	34 TFLOPS	3.5x higher on H200
Platform
Interconnect	NVLink 600 GB/s	NVLink 900 GB/s	50% higher on H200
Board power	300 W	700 W	2.3x higher on H200
Released	Q2 2020	Q4 2023	4 years newer on H200
Precision
Supported formats	FP16BF16TF32FP32FP64INT4INT8	FP8FP16BF16TF32FP32FP64INT8

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: A100 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	A100	H200
Vast.ai USA	$0.43 /GPU/hr On-demand SXM	$4.14 /GPU/hr On-demand NVL
Lium Distributed	$1.23 /GPU/hr On-demand SXM	$3.00 /GPU/hr On-demand SXM
GPU.ai UAE	$0.81 /GPU/hr On-demand	$3.29 /GPU/hr On-demand NVL
Jarvislabs India	$0.89 /GPU/hr On-demand	$3.99 /GPU/hr On-demand SXM
Runpod USA	$1.00 /GPU/hr On-demand SXM	$3.59 /GPU/hr On-demand SXM
Massed Compute USA	$1.35 /GPU/hr On-demand	$3.62 /GPU/hr On-demand NVL
Thunder Compute USA	$1.09 /GPU/hr On-demand	--
Spheron Singapore	$1.43 /GPU/hr On-demand PCIe	--
Lyceum Germany	--	$4.29 /GPU/hr On-demand
Daytona USA	--	$4.54 /GPU/hr On-demand