Skip to content
State of GPU Compute 2026
Cloud ServersNVIDIA H100NVIDIA

NVIDIA DGX H800

On demand · 8× H100
€24.00/server·hr
Per GPU
€3.00/GPU·hr

GPU as listed: NVIDIA DELTA-NEXT Vulcan SXM5 8xNVIDIA H100 640G

Proven Hopper nodes at the lowest hourly rate in the fleet. Ideal for steady inference and fine-tuning. You get the whole machine, billed per second in euros.

Rent this serverCompare

Spec sheet updated 27 Oct 2026

Exploded view of a Nexpod node: an 8U server with eight NVIDIA H100 GPUs on an HGX baseboard, an NVLink switch tray above it, and data paths to the EU-AMS-1, EU-FRA-1 and US-NYC-1 regions.
GPUs
8× H100
One NVLink fabric
Memory per GPU
80GB
HBM3
GPU memory, server
640GB
8 × 80 GB
System memory
32x 64GB
32x 64GB DDR5 4800MHz
Front elevation · NVIDIAForm factor · Configurable on request
GPU tray8× H100
CPU2 sockets
CPU0
CPU1
Memory32 × 64GB
Drives8 + 2 bays

Drawn at 8U for scale. The listing leaves the rack height open.

This chassis

The whole host, not a slice

The CPUs, system memory and local NVMe come with the GPUs. Nothing is carved up for other tenants.

nexctl · describe
$ nexctl servers describe nvidia-dgx-h800
model
NVIDIA DGX H800
gpu
NVIDIA DELTA-NEXT Vulcan SXM5 8xNVIDIA H100 640G
cpu
2x Intel Xeon Platinum 8480C (56C 105M Cache 2.00 GHz)
memory
32x 64GB DDR5 4800MHz
storage
8x3.84T NVMe PCIe / 2x960Gb NVMe M.2
form
Configurable on request
● 8/8 GPUs healthy · NVLink all-to-all

Hopper

Eight H100 GPUs. One machine.

What the H100 brings to this chassis, from the package to the fabric between all eight.
Hopper
HBM3
HBM3
HBM3
HBM3
NVIDIAH10080 GB
HBM3
HBM3
HBM3
HBM3
Silicon

NVIDIA Hopper

Each of the eight packages is an NVIDIA H100 with 80 GB of HBM3 next to the die.

B300288 GB
B200180 GB
H200141 GB
H10080 GB
Memory

80 GB on every GPU

640 GB across the server. Here is how H100 sits in the fleet.

NVLINKGPU 0GPU 1GPU 2GPU 3GPU 4GPU 5GPU 6GPU 7
Interconnect

All-to-all NVLink

Every GPU talks to every other one directly, so tensor-parallel runs stay inside the box.

Use it for

Where the H100 earns its rate.

4 workloads / scroll

Technical specs

Every field on the spec sheet.

Server values appear exactly as the builder lists them, spelling included. Anything they leave open, we configure to order.

Talk to an engineer
Server
ModelNVIDIA DGX H800The exact chassis you get. No substitutes after you deploy.
BrandNVIDIARacked, cabled and burn-in tested by us before it goes live.
GPUNVIDIA DELTA-NEXT Vulcan SXM5 8xNVIDIA H100 640GAll eight GPUs are yours. Nothing is split or shared.
GPU familyH100NVIDIA Hopper generation.
CPU2x Intel Xeon Platinum 8480C (56C 105M Cache 2.00 GHz)Host cores for data loading, tokenising and preprocessing.
System memory32x 64GB DDR5 4800MHzRoom for datasets, page cache and CPU offload.
Local storage8x3.84T NVMe PCIe / 2x960Gb NVMe M.2Local NVMe for checkpoints and scratch. Network volumes mount on top.
Form factorConfigurable on requestNot in the builder's listing. We fit it to your order and confirm it in writing.
Model IDnvidia-dgx-h800Pin this chassis with nexctl --model or the API.
Catalogue no.16Its position in the Nexpod server list.
GPU · NVIDIA H100
ArchitectureNVIDIA HopperThe generation behind every H100 we rent.
Memory per GPU80 GB HBM3Holds weights, activations and KV cache on the GPU itself.
GPU memory per server640 GB8 GPUs × 80 GB, reachable over NVLink.
GPU interconnectNVLink, all-to-allEvery GPU reaches every other GPU without going through the host.

Pricing

Two ways to pay. Same machine.

Run it on demand by the second, or reserve it for a year at a lower rate. Both are invoiced in euros, excluding VAT.
On-demand

Start now, stop any time.

€24.00/server·hr
Per GPU·hr
€3.00
Per second, full server
€0.00667
Month at 730 h
€17,520
Rent on demand
Reserved · 12 months

The same server, held for you all year.

−33%
€16.00/server·hr
Per GPU·hr
€2.00
Per second, full server
€0.00444
Month at 730 h
€11,680
Reserve this server
billing · nvidia-dgx-h800
metering
€0.00667/s
8 × H100 · on demand · per second
0s€0.0015s€0.1030s€0.2045s€0.3060s€0.40
1 minute
€0.40
20-min test
€8.00
1 hour
€24.00

Related servers

Also worth a look.

All 20 servers
  • ASUS ESC N8A-E12
    ASUS · H100 · 7U
    €24.00/server·hr€3.00/GPU·hr
    6144GB (DDR5 ECC REG)
  • NVIDIA DGX B300
    NVIDIA · B300
    €48.00/server·hr€6.00/GPU·hr
    2000GB (DDR5 ECC REG)
  • ASUS ESC NB8-E11
    ASUS · B200
    €40.00/server·hr€5.00/GPU·hr
    8192GB (DDR5 ECC REG)
Compare withASUS ESC N8A-E12NVIDIA DGX B300ASUS ESC NB8-E11

FAQ

Before you rent it.

Short answers. The docs have the long ones.
Do I share the NVIDIA DGX H800 with anyone?
No. You rent the whole machine: all eight H100 GPUs, the host and its system memory. Nobody else runs work on it while it is yours.
How is it billed?
Per second while it runs. On demand it is €24.00 per hour for the full server, or €16.00 per hour on a 12-month reservation. Invoices are in euros.
What does “Configurable on request” mean?
The builder's listing leaves that part open. We fit it to your order, for example CPU or local storage, before handover and confirm the exact configuration in writing.
Can I join it with other servers?
Yes. Instant Clusters link several 8-GPU servers over a high-speed fabric. Start on one node and add more when the job needs them.
Which regions can I deploy in?
Nexpod runs in EU-AMS-1, EU-FRA-1 and US-NYC-1. You pick the region at deploy time and the console shows current capacity for this model.
Placeholder

Placeholder quote. A customer describes, in one or two plain sentences, what changed after moving a real workload to Nexpod.

Customer nameRole, Company

Rent the NVIDIA DGX H800

Eight H100 GPUs, ready in minutes.

Create an account, pick a region and connect over SSH. Stop the server when the job is done and the meter stops with it.

Get startedTalk to sales
nexctl · eu-ams-1
$ nexctl servers rent nvidia-dgx-h800 --region eu-ams-1
reserved 1 × NVIDIA DGX H800
status provisioning → ready
ssh root@node-07.ams.nexpod.ai
RelatedAll serversGPU comparePricingCloud Servers