Home / Compare / A100 vs L40S

A100 vs L40S: Cloud GPU Pricing

By median on-demand price, L40S is about 15% cheaper per GPU-hour today (A100 $2.00 vs L40S $1.70). Price per hour is not price per result: a faster GPU can finish a job in fewer hours, so compare cost per job on your own workload.

A100

NVIDIA Ampere

Lowest
$1.00/hr
Median
$2.00/hr
Highest
$4.10/hr
Listings
75
Providers
14
Cheapest on
RunPod

L40S

NVIDIA Ada Lovelace

Lowest
$0.69/hr
Median
$1.70/hr
Highest
$7.58/hr
Listings
52
Providers
12
Cheapest on
BoostRun

Cheapest A100 listings

ProviderGPUsVRAMvCPURAM (GB)RegionAvailability$/GPU-hr
RunPod140 GB32125ES–$1.00
Excess Supply880 GB1201892tokyo-japan-5In stock$1.35
Excess Supply880 GB2401280omaha-usa-2Out of stock$1.35
Excess Supply880 GB2401280omaha-usa-2In stock$1.35
Hyperstack280 GB60240montreal-canada-2In stock$1.35
Hyperstack480 GB124480montreal-canada-2Out of stock$1.35
Hyperstack880 GB2521440montreal-canada-2Out of stock$1.35
Hyperstack180 GB28120montreal-canada-2In stock$1.35

Cheapest L40S listings

ProviderGPUsVRAMvCPURAM (GB)RegionAvailability$/GPU-hr
BoostRun848 GB641536dallas-usa-4Out of stock$0.69
Latitude148 GB16128frankfurt-germany-5Out of stock$0.74
Latitude848 GB1281536frankfurt-germany-5Out of stock$0.87
Massed Compute148 GB1272kansascity-usa-1In stock$0.88
Massed Compute448 GB88288kansascity-usa-1In stock$0.88
Massed Compute848 GB142768desmoines-usa-1Out of stock$0.88
Massed Compute248 GB44256kansascity-usa-1In stock$0.88
RunPod148 GB32125EU-NL-1–$1.09

On-demand USD per GPU-hour. Spot, reserved and fractional-GPU offers are excluded. Data refreshed 2026-11-18. Prices come from provider APIs and public catalogs; confirm on the provider's site before committing spend.