GPU MODELS / H200 NVL

H200 NVL cloud GPU pricing

17 listings across 9 providers. Cheapest published rate: $3.620/GPU/hr at Massed Compute. Sorted by per-GPU hourly price. Every row links to the provider's own published price.

WHAT IS THE H200 NVL

The H200 NVL pairs two 141 GB HBM3e cards over an NVLink bridge - 282 GB per pair, the most inference-friendly memory footprint in the Hopper line. It serves 70B models at BF16 on a single card and large MoE models on the pair, in standard PCIe servers.

MAKER
NVIDIA
ARCHITECTURE
Hopper
LAUNCHED
2024
MEMORY
141 GB HBM3e per GPU
MEMORY BANDWIDTH
4.8 TB/s
TENSOR COMPUTE
835 TFLOPS FP16/BF16 tensor dense; FP8 1,671 dense
POWER DRAW
up to 600 W
INTERCONNECT
NVLink bridge 600 GB/s

WHAT IT IS GOOD AT

70B+ serving
141 GB per card covers BF16 70B with context headroom.
MoE and long-context inference
The pair's 282 GB handles footprints 80 GB cards cannot.

WHO SHOULD NOT RENT THE H200 NVL

Training clusters - inference-first design.
Small models - the 141 GB goes unused.
ProviderConfigVRAMLocation$/hr$/GPU/hrSource
RunPodRunPodH200 NVL × 1143 GBGlobal$0.500$0.500UNUSUALLY LOWreceipt
SpotGPUsSpotGPUsH200 NVL × 1141 GBNot published$0.990$0.990STALEreceipt
Massed ComputeMassed ComputeH200 NVL × 1141 GBNot published$3.620$3.620receipt
Massed ComputeMassed ComputeH200 NVL × 8141 GBNot published$28.960$3.620receipt
Massed ComputeMassed ComputeH200 NVL NVLink × 8141 GBNot published$30.560$3.820receipt
gpu.aigpu.aiH200 NVL × 1141 GBNot published$4.170$4.170receipt
Hostnot GPUHostnot GPUH200 NVL × 1141 GBUS West$4.590$4.590receipt
TeamCloudTeamCloudH200 NVL (from) × 1141 GBMalaysia$4.691$4.691receipt
GPUBrazilGPUBrazilH200 NVL × 1140 GBNorth America$4.757$4.757receipt
Hostnot GPUHostnot GPUH200 NVL × 2141 GBEU West$9.520$4.760receipt
GPUBrazilGPUBrazilH200 NVL × 1140 GBEurope$4.764$4.764receipt
Hostnot GPUHostnot GPUH200 NVL × 1141 GBEU West$4.770$4.770receipt
NovaGPU (IP ServerOne)NovaGPU (IP ServerOne)H200 NVL × 1141 GBMalaysia$5.030$5.030receipt
NovaGPU (IP ServerOne)NovaGPU (IP ServerOne)H200 NVL × 2282 GBMalaysia$10.063$5.031receipt
Hostnot GPUHostnot GPUH200 NVL × 1141 GBUS East$5.130$5.130receipt
SelectelSelectelH200 NVL × 1141 GBRussia$7.877$7.877receipt
Hostnot GPUHostnot GPUH200 NVL × 1141 GBEU East$8.880$8.880receipt

THE H200 NVL MARKET, BY THE NUMBERS

PROVIDERS
9
CONFIGURATIONS
17
MEDIAN $/GPU/HR
$4.76
SPREAD
2.5x

9 providers publish 17 H200 NVL configurations on the panel today. Published per-GPU hourly rates run from $3.620 (Massed Compute) to $8.88 (Hostnot GPU), a 2x spread between the cheapest and the most expensive published rate for the same chip. The median listing sits at $4.76/GPU/hr. 7 rows were reported in stock by the provider at last observation; the rest are published catalog rates. All rates are on-demand - committed-use and reserved pricing is excluded.

CHEAPEST H200 NVL BY GEOGRAPHY
united statesHostnot GPU$4.590/hrmalaysiaTeamCloud$4.691/hr
H200 NVL PRICE TREND, DAILY PANEL SNAPSHOTS

Across every H200 NVL row on the panel, the daily floor held flat at $3.620/GPU/hr over 53 days of tracking. The median continuously-tracked listing held flat at $3.62. Snapshots run daily; the full history is public in the repo.

H200 NVL PROVIDER NOTES
Massed Compute · 3 configs
Sets the panel floor for this model.
from $3.620/hr
gpu.ai · 1 config
Published catalog rates.
from $4.170/hr
Hostnot GPU · 5 configs · 4 regions · 5 in stock
Widest regional footprint here - 4 regions.
from $4.590/hr
TeamCloud · 1 config · 1 region
Published catalog rates.
from $4.691/hr
GPUBrazil · 2 configs · 2 regions · 2 in stock
2 of 2 configs reported in stock at last check.
from $4.757/hr
NovaGPU (IP ServerOne) · 2 configs · 1 region
Published catalog rates.
from $5.030/hr
Selectel · 1 config · 1 region
Published catalog rates.
from $7.877/hr
BUYING H200 NVL: WHAT THE PANEL SAYS

At the current floor, one H200 NVL running around the clock costs about $2,643 a month (730 hours of on-demand arithmetic). Node shape matters: the single-GPU floor is $3.620/GPU/hr against $3.620/GPU/hr on an 8-GPU node (+0.0%). Per-GPU floors by config size: 1x $3.62 · 2x $4.76 · 8x $3.62. Compare the alternatives below before committing - the same budget often buys more than one chip class.

H200 NVL VS THE ALTERNATIVES

H200 NVL vs H100 NVL
Same shape, 50% more memory and 23% more bandwidth per card. For serving, the H200 NVL is the better part; the H100 NVL is often the better price.

Compare live rates: H200 NVL vs H100 NVL

H200 NVL PRICING FAQ

What is the cheapest H200 NVL cloud GPU right now?
The cheapest published H200 NVL rate on the panel is $3.620 per GPU-hour at Massed Compute (H200 NVL x 1, Not published). Every price links to the provider's own published rate.
How much does a H200 NVL cost per hour?
Across 9 providers tracked today, published per-GPU hourly rates for H200 NVL run from $3.62 to $8.88, with a median of $4.76. Committed-use and reserved rates are excluded; everything shown is on-demand.
How many providers rent H200 NVL GPUs?
9 providers publish 17 distinct H200 NVL configurations on Compute Cafe. 7 of those rows were reported in stock by the provider's live endpoint at last observation.
Where is H200 NVL cheapest?
By published per-GPU hourly rate, the cheapest geography for H200 NVL today is united states at $4.59/hr (Hostnot GPU). The spread across 2 tracked geographies runs to $4.69/hr in malaysia.
Are H200 NVL prices going up or down?
Over the 53 days Compute Cafe has tracked the panel, the H200 NVL floor is holding flat: $3.620 to $3.620/GPU/hr (+0.0%). The median continuously-tracked listing moved from $3.62 to $3.62 (+0.0%). Daily snapshots are public in the repo, so the trend is auditable.
What does a H200 NVL cost per month?
At the current floor of $3.620/GPU/hr, a H200 NVL running 24/7 costs about $2,643 per month (730 hours of on-demand arithmetic on the cheapest published rate). Committed-use contracts can price lower; the panel tracks on-demand rates only.
Is a full 8-GPU H200 NVL node cheaper than a single card?
On today's panel: the single-GPU floor is $3.620/GPU/hr and the 8-GPU node floor is $3.620/GPU/hr - about the same per GPU either way (+0.0%). Check the table for the exact configs behind each floor.
What fits on an H200 NVL pair?
A BF16 70B model with long-context KV cache sits on one card; the pair's 282 GB covers quantized 180B-class models or heavy multi-tenant serving.

See also alternatives to the H200 NVL · cheapest GPU-hour per model · inference chips · training chips · by location