Skip to main content

H100 vs V100

The H100 delivers 7.9× the FP16 compute of the V100 while costing 1.0× less on average, making it 706% more cost-efficient per TFLOP.

Spec Comparison

Spec
H100
V100
Architecture
Hopper
Older
VRAM
80 GB
32 GB
FP16 TFLOPS
989
125
Memory Bandwidth
3,350 GB/s
900 GB/s
MSRP
$30,000
N/A
Used/Market Price
N/A
$2,000

Live Pricing

H100
Cheapest
$0.801/hr
Median
$8.97/hr
Average
$16/hr
Providers
36
Instances
327
V100
Cheapest
$0.0133/hr
Median
$9.14/hr
Average
$11/hr
Providers
9
Instances
527

Cost Efficiency

Metric
H100
V100
$/TFLOP/hr
$0.0091
$0.0731
$/GB-VRAM/hr
$0.1121
$0.2855

Lower $/TFLOP and $/GB-VRAM is better. Based on median hourly pricing.

Provider Availability

H100 Cloud Pricing

327 instances
ProviderGPUsVRAMRegionTypePrice/hr
CHEAPESTVerda1x80 GBEU-CentralSpot$0.801Rent
Verda1x80 GBEU-CentralSpot$0.801Rent
Nebius1x80 GBeu-north1Spot$1.25Rent
GCP1x80 GBeurope-north1-cSpot$1.29Rent
GCP1x80 GBEU-WestSpot$1.39Rent
Vast.ai1x80 GBfr-franceSpot$1.47Rent
Vast.ai1x80 GBfr-franceOn-Demand$1.55Rent
Verda2x160 GBEU-CentralSpot$1.60Rent
Shadeform1x80 GBUS-EastOn-Demand$1.66Rent
E2E Networks1x80 GBAsia-PacificOn-Demand$1.69Rent

V100 Cloud Pricing

527 instances
ProviderGPUsVRAMRegionTypePrice/hr
CHEAPESTVast.ai1x16 GBUS-WestSpot$0.0133Rent
Vast.ai1x16 GBUS-WestSpot$0.0147Rent
Vast.ai2x32 GBUS-WestSpot$0.0267Rent
Vast.ai2x32 GBUS-WestSpot$0.0293Rent
Vast.ai1x16 GBUS-WestOn-Demand$0.0344Rent
Vast.ai1x16 GBUS-WestOn-Demand$0.0351Rent
Verda1x16 GBEU-CentralSpot$0.0483Rent
Vast.ai4x64 GBUS-WestSpot$0.0533Rent
Vast.ai2x32 GBUS-WestOn-Demand$0.0702Rent
Vast.ai2x32 GBUS-WestOn-Demand$0.0722Rent

Compare with Other GPUs