Nvidia B200 vs Nvidia H100

The B200 is newer, with 2.2x the memory and 2.3x the bandwidth. The H100 is typically cheaper.

At a glance

Memory

2.2x more on B200

B200: 180 GB

H100: 80 GB

Memory bandwidth

2.3x higher on B200

B200: 7.70 TB/s

H100: 3.35 TB/s

Cheapest on-demand

52% cheaper on H100

B200: $3.75 /GPU/hr

H100: $1.80 /GPU/hr

Price comparison

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

Billing	B200	H100	Difference
On-demand	$7.99 /GPU/hr from $3.75	$3.71 /GPU/hr from $1.80	54% cheaper on H100
Reserved	$5.62 /GPU/hr from $3.75	$3.29 /GPU/hr from $1.53 (1 mo)	41% cheaper on H100
Spot	$4.26 /GPU/hr from $4.09	$2.31 /GPU/hr from $1.29	46% cheaper on H100

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

B200 vs H100 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	B200	H100	Difference
Memory
Capacity	180 GB HBM3e	80 GB HBM3 94 GB on NVL	2.2x more on B200
Bandwidth	7,700 GB/s	3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL	2.3x higher on B200
Bus width		5,120-bit
Compute · dense
FP4	9,000 TFLOPS	Not supported	B200 only
FP8	4,500 TFLOPS	1,979 TFLOPS	2.3x higher on B200
FP16 / BF16	2,250 TFLOPS	989.5 TFLOPS	2.3x higher on B200
INT8	4,500 TOPS	1,979 TOPS	2.3x higher on B200
FP32	75 TFLOPS	67 TFLOPS	12% higher on B200
FP64	37 TFLOPS	34 TFLOPS	9% higher on B200
Platform
Interconnect	NVLink 1,800 GB/s	NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL	2x higher on B200
Board power	1,000 W	700 W	43% higher on B200
Released	Q1 2024	Q3 2022	2 years newer on B200
Precision
Supported formats	FP4FP6FP8FP16BF16TF32FP32FP64INT8	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: B200 datasheet and H100 datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.

Provider	B200	H100
Lium Distributed	$5.64 /GPU/hr On-demand SXM	$2.10 /GPU/hr On-demand SXM
GPU.ai UAE	$7.99 /GPU/hr On-demand SXM	$1.98 /GPU/hr On-demand PCIe
Runpod USA	$7.99 /GPU/hr On-demand SXM	$3.19 /GPU/hr On-demand NVL
Packet·ai USA	$3.75 /GPU/hr On-demand	--
Spheron Singapore	$11.12 /GPU/hr On-demand SXM	--
GPUaaS USA	$7.00 /GPU/hr Custom	--
Daytona USA	$6.25 /GPU/hr On-demand	--
Denvr Canada	On request Custom SXM	--
HyperAI Hong Kong	--	$1.80 /GPU/hr On-demand
Massed Compute USA	--	$2.73 /GPU/hr On-demand
Sesterce France	--	$2.75 /GPU/hr On-demand
Runcrate USA	--	$3.25 /GPU/hr On-demand SXM
Lambda Labs USA	--	$3.29 /GPU/hr On-demand PCIe