Skip to content
aipowered

Find your next machine.

Try “5090”, “Jetson”, or “DGX”.

NVIDIA H200 (141GB HBM3e)

141GB HBM3e
Memory
4,800GB/s
Memory bandwidth
Q4 2024
Released

Price history

On-demandReservedSpot
USD / GPU / HR
On-demand · latest$4.372026-10-05

What it costs to rent an NVIDIA H200

The NVIDIA H200 is a Hopper-architecture fine-tuning NVIDIA GPU with 141GB of HBM3e memory and 4,800 GB/s of memory bandwidth, released Q4 2024. It is built for large-model training and high-throughput inference.

Renting one currently costs between $1.47 and $10.67 per GPU-hour across the 19 cloud providers we track, with a median of $4.35. The cheapest live rate is $1.47/hr from Vast.ai (Spot), and hosting one pays about $3.11/hr on RunPod while it is running. All rates below are normalised to a single GPU per hour so providers with multi-GPU nodes compare like-for-like.

Where to rent the H200

How we rank

The median is one provider, one vote: each provider contributes the median of its own on-demand listings, then the headline is the median across providers — so no single marketplace or hyperscaler sets the price alone. Below two providers we show the range instead.

Default order is relevance, weighed the way a buyer would: price per GPU first, lightly blended with total node cost; on-demand preferred over spot and reserved when prices are close; established clouds edged above marketplaces; in-stock, recently-checked offers above stale ones; and no single provider is allowed to crowd the top. Click a column to sort by the raw numbers. No paid placements — ranking is never sold.

Scroll horizontally to compare all columns →

ProviderTierConfigTotal VRAMBillingAvailabilityGo to provider
Vast.aiGPU cloud7× H200 NVL987GBSpot$1.47$10.27Rent
EnvergeBestMarketplace1× H200141GBOn-demand$2.50$2.50Rent
VerdaMarketplace1× H200141GBSpot$2.61$2.61Rent
TogetherEnterprise1× H200141GBOn-demand$2.99$2.99Rent
Vast.aiGPU cloud1× H200 NVL141GBSpot$2.52$2.52Rent
DigitalOceanEnterprise1× H200141GBOn-demand$3.40$3.40Rent
Vast.aiGPU cloud2× H200 NVL282GBSpot$2.52$5.04Rent
CivoGPU cloud1× H200141GBOn-demand$3.49$3.49Rent

Earn by hosting the H200

How this is worked out

“Renters pay” is the median live rate for this GPU on that marketplace — the median, not the floor, because the cheapest listing is one host undercutting everyone. “You earn” is that figure less the platform’s cut.

“Per day” is a ceiling: 24 hours, every hour rented, which no host achieves — scale it by the utilisation you expect. A card sitting idle earns nothing.Fees marked as published come from the platform’s terms; the rest are our estimates, labelled on each row.

Go to platform
RunPodBest yield$3.11/hrHost
Vast.ai$3.06/hrHost

Technical specifications

Throughput
FP6434 TFLOPS
FP3267 TFLOPS
TF32495 TFLOPS
FP16/BF16990 TFLOPS
FP81,979 TFLOPS
Silicon & memory
Memory
141 GB
Memory bandwidth
4,800 GB/s
TDP
700 W
INT8
1,979 TOPS
Process
5 nm
Foundry
TSMC
Released
18 Nov 2024
Launch price
$30,000
TrainingInference
Datasheet
ArchitectureHopper
Memory141 GB HBM3e
Bandwidth4.8 TB/s
FP8 Tensor3,958 TFLOPS (sparse)
NVLink900 GB/s
MIGup to 7 instances
Powerup to 700 W (SXM)
Class
Fine-tuning
Cloud providers
19 tracked
Price range
$1.47 – $10.67 / GPU / hr

SNAPSHOT 2026-10-12T05:40:41.151564+00:00 · BACK TO THE FULL INDEX