InferPrice

All GPUs

NVIDIA L40S price per hour

The cheapest on-demand NVIDIA L40S (48 GB) we found is $1.09/GPU-hr at RunPod (cloud vm). Across 5 listings, prices run up to $2.25. Ada generation PCIe card, a low-cost choice for small and mid-size model inference.

Provider$/GPU-hrTypeVariantNotes
RunPod$1.09Cloud VM48GBsource
Crusoe$1.50Cloud VM48GBsource
Nebius$1.55Cloud VMIntel CPUStarting pricesource
Modal$1.95ServerlessBilled per second ($0.000542/s)source
CoreWeave$2.25Cloud VM8x$18.00 per 8-GPU instance-hoursource
Vast.aiLive pricesMarketplacePrices are set by individual hosts and change constantly. Check current offers on Vast.ai.source

Per-GPU prices for 8-GPU instances are the instance price divided by 8. Reserved and preemptible prices are lower and are listed in the notes where the provider publishes them. Last checked 2026-10-12.