Search/H200

H200

141GB 700W 6 providers 208 offers

A Hopper GPU with the same compute as the H100 but 141 GB of HBM3e and ~4.8 TB/s bandwidth, ideal for memory-bound LLM inference.

Cheapest
$1.400/hr
Verda
Median
$80.000/hr
across 208 offers
P90
$110.240/hr
90th percentile
Prices updated 1 hour ago6 providers trackedHow we collect prices
Memory
141 GB
TDP
700 W
Bandwidth
4800 GB/s
FP16
495 TFLOPS
Brand
NVIDIA
Series
NVIDIA
Year
2024
Arch
Hopper

Price by provider

cheapest rate · $/GPU/hr · lower is better
Verda
0 regions
$1.400/hr
Vast.ai
0 regions
$2.193/hr
Nebius
0 regions
$2.450/hr
RunPod
0 regions
$3.590/hr
OCI
0 regions
$80.000/hr
Azure
0 regions
$84.800/hr

6 providers

ProviderPrice RangeMedianTypeCPU / RAMAction
VE
Verda
Best price
$1.400$32.000
$6.800 Spot
44-176
182-1450GB
Browse
VA
Vast.ai
$2.193$28.061
$10.178 Spot
24-192
31-2063GB
Browse
NE
Nebius
$2.450$36.000
$12.050 Spot
16-128
200-1600GB
Browse
RU
RunPod
$3.590$42.144
$11.970 Spot
12-160
188-1885GB
Browse
OC
OCI
$80.000$80.000
$80.000Mixed
224-224
3072-3072GB
Browse
AZ
Azure
$84.800$169.600
$106.000 Spot
96-96
1850-1850GB
Browse
Best Deal Right Now
VE
Verda
$1.400/hr
per GPU / hour
Configurationx1 · H200
System RAM182-1450GB
Region
Launch on Verda

Estimated Running Cost

At cheapest rate · per GPU

1 hour$1.40
24 hours$33.60
1 week$235.20
1 month$24528.00

Compare

See how H200 stacks up against other GPUs.

H200 vs H100