Nvidia logo

H200 vs H800

The H200 doubles memory to 141GB with full NVLink, while the H800 has 80GB with reduced NVLink. Choose H200 for memory and bandwidth, H800 for export compliance.

Overview

Nvidia logo Nvidia H200

The Nvidia H200 is a data center GPU on the Hopper architecture, released Q4 2023, with 141 GB HBM3e and 4,800 GB/s memory bandwidth.

High Performance Datacenter

Nvidia logo Nvidia H800

The Nvidia H800 is a data center GPU on the Hopper architecture, released Q1 2023, with 80 GB HBM2e and 2,000 GB/s memory bandwidth.

High Performance Datacenter

Memory per GPU

1.8x more on H200
Nvidia logo H200
141 GB HBM3e
Nvidia logo H800
80 GB HBM2e

Memory bandwidth

2.4x higher on H200
Nvidia logo H200
4,800 GB/s
Nvidia logo H800
2,000 GB/s

GPU interconnect

2.2x higher on H200
Nvidia logo H200
NVLink 900 GB/s
Nvidia logo H800
NVLink 400 GB/s

Peak performance (FP8)

1.3x higher on H200
Nvidia logo H200
1,979 TFLOPS
Nvidia logo H800
1,513 TFLOPS

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

FP8 per watt

1.5x higher on H800
Nvidia logo H200
2.83 TFLOPS/W
Nvidia logo H800
4.32 TFLOPS/W

Board power

2x higher on H200
Nvidia logo H200
700 W
Nvidia logo H800
350 W

Precision support

Nvidia logo H200
FP8 FP16 BF16 TF32 FP32 FP64 INT8
Nvidia logo H800
FP8 FP16 BF16 TF32 FP32 FP64 INT8

Highlighted formats are supported by only one of the two.

Architecture

Nvidia logo H200
Hopper
Nvidia logo H800
Hopper

Released

8 months newer on H200
Nvidia logo H200
Q4 2023
Nvidia logo H800
Q1 2023

Source: H200 datasheet .

Price comparison

Cheapest on-demand

Nvidia logo H200
$2.09 / GPU / hr
Nvidia logo H800
--

Typical rate

Nvidia logo H200
$4.40 / GPU / hr
Nvidia logo H800
--

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

Spot floor

Nvidia logo H200
$1.32 / GPU / hr
Nvidia logo H800
No spot listings

Providers listing it

Nvidia logo H200
41
Nvidia logo H800
None

Price, last 90 days

Nvidia logo H200
+3%
Nvidia logo H800
Not tracked yet

Change in the market-wide median, which moves when providers reprice and when cheaper or more expensive listings enter the market.

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. Verify before provisioning. More on how we price.

Offers and availability

How this list works

Order

Each provider appears once per GPU. We pick the one configuration that speaks for that provider, and rank on it in this order:

  1. Availability: in stock, then waitlist, then not reported, then out of stock. A price you can act on outranks a cheaper one you cannot.
  2. Billing type: on-demand first, then reserved, then spot, then quote-only. On-demand leads because it is the only rate you can hold without committing to anything.
  3. Price: the lowest per-GPU hourly rate the provider lists, converted to USD.

The configuration we pick is chosen the same way, availability before billing before price. The rest of that provider's configurations are on the GPU's own page.

Ties sort alphabetically. Reserved rates are not separated by term length, so a three-year commitment can sit above a one-month one: the label beneath each price says which you are looking at. Providers who publish no rate are listed last within their group.

Transparency and funding

  • Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
  • Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
  • Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.

Similar GPUs

Other comparisons in the same class:

View all GPUs

Our data for Nvidia H200 was last updated on Sept. 3, 2026, and for Nvidia H800 on Sept. 3, 2026.