Nvidia A40 vs Nvidia H200

The H200 is newer, with 2.9x the memory and 6.9x the bandwidth. The A40 is typically cheaper.

At a glance

Memory

2.9x more on H200

A40: 48 GB

H200: 141 GB

Memory bandwidth

6.9x higher on H200

A40: 696 GB/s

H200: 4,800 GB/s

Cheapest on-demand

87% cheaper on A40

A40: $0.28 /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	A40	H200	Difference
On-demand	$0.65 /GPU/hr from $0.28	$4.38 /GPU/hr from $2.09	85% cheaper on A40
Reserved	-- /GPU/hr from $0.61 (24 mo)	$3.85 /GPU/hr from $2.23 (1 mo)
Spot	-- /GPU/hr from $0.27	$2.62 /GPU/hr from $0.74

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 reserved and spot on the A40: 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

A40 vs H200 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	A40	H200	Difference
Memory
Capacity	48 GB GDDR6	141 GB HBM3e	2.9x more on H200
Bandwidth	696 GB/s	4,800 GB/s	6.9x higher on H200
Bus width	384-bit
Compute · dense
FP8	Not supported	1,979 TFLOPS	H200 only
FP16 / BF16	149.7 TFLOPS	989.5 TFLOPS	6.6x higher on H200
INT8	299.3 TOPS	1,979 TOPS	6.6x higher on H200
FP32	37.4 TFLOPS	67 TFLOPS	79% higher on H200
FP64	Not supported	34 TFLOPS	H200 only
Platform
Interconnect	PCIe only	NVLink 900 GB/s	NVLink on H200 only
Board power	300 W	700 W	2.3x higher on H200
Released	Q4 2020	Q4 2023	3 years newer on H200
Precision
Supported formats	FP16BF16TF32FP32INT4INT8	FP8FP16BF16TF32FP32FP64INT8

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

Source: A40 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	A40	H200
Vast.ai USA	$0.28 /GPU/hr On-demand	$2.54 /GPU/hr On-demand NVL
GPU.ai UAE	$0.49 /GPU/hr On-demand	$2.54 /GPU/hr On-demand NVL
Runpod USA	$0.49 /GPU/hr On-demand	$3.59 /GPU/hr On-demand SXM
Runcrate USA	$2.42 /GPU/hr On-demand PCIe	$4.24 /GPU/hr On-demand SXM
Sesterce France	$2.05 /GPU/hr On-demand	--
Denvr Canada	$0.65 /GPU/hr On-demand	--
Exoscale Switzerland	$1.05 /GPU/hr On-demand	--
Database Mart USA	$0.61 /GPU/hr Reserved	--
Lium Distributed	--	$2.95 /GPU/hr On-demand SXM
Massed Compute USA	--	$3.62 /GPU/hr On-demand NVL
Hyperstack UK	--	$3.99 /GPU/hr On-demand SXM
Jarvislabs India	--	$3.99 /GPU/hr On-demand SXM