gpu catalog: l40

Rent L40 from $0.935/hr●

The L40S's visualization-oriented sibling: the same 48 GB of GDDR6, commonly rented for diffusion inference and virtual workstations.

Live platform rates

● 27 GPU types online
GPUVRAMRegionsAvailabilityPrice / GPU
L4048G2 regionshigh availability$0.94/hrlaunch

The L40S's visualization-oriented sibling: the same 48 GB of GDDR6, commonly rented for diffusion inference and virtual workstations.

VRAM48 GB GDDR6
Memory bandwidth0.9 TB/s
FP16 tensor181 TFLOPS
ArchitectureAda Lovelace
InterconnectPCIe 4.0
Board power300 W
CUDA cores18,176
Released2022
Regionsca-central, us-central
RTX PRO 600096G4 regionshigh availability$2.03/hrlaunch
RTX A600048G2 regionshigh availability$0.54/hrlaunch
RTX 6000 ADA48G2 regionshigh availability$0.78/hrlaunch
RTX 5090community32G8 regionshigh availability$0.52/hrlaunch
RTX 4090community24G7 regionshigh availability$0.45/hrlaunch
RTX 3090community24G6 regionshigh availability$0.18/hrlaunch
A10080G5 regionsavailable$1.48/hrlaunch
H200 SXMcommunity141G5 regionsavailable$4.31/hrlaunch
H200 SXM141G5 regionsavailable$6.35/hrlaunch
H100 SXM80G4 regionsavailable$5.27/hrlaunch
RTX 5080community16G7 regionsavailable$0.24/hrlaunch
RTX 3080community10G4 regionsavailable$0.13/hrlaunch
RTX A4000community16G6 regionsavailable$0.10/hrlaunch
A100community80G5 regionsavailable$1.28/hrlaunch
B200192G3 regionsavailable$9.59/hrlaunch
A1616G6 regionsavailable$0.56/hrlaunch
H100 PCIE80G1 regionavailable$2.98/hrlaunch
H200 NVLcommunity141G6 regionsavailable$3.92/hrlaunch
L40S48G2 regionsavailable$0.96/hrlaunch
A4048G3 regionsrunning low$0.71/hrlaunch
L40Scommunity48G3 regionsrunning low$0.93/hrlaunch
RTX 409024G2 regionsrunning low$1.07/hrlaunch
RTX 509032G2 regionsrunning low$1.67/hrlaunch
B300288G1 regionrunning low$10.79/hrlaunch
H200 NVL141G1 regionrunning low$3.95/hrlaunch
L4community24G2 regionsrunning low$0.53/hrlaunch
A40community48G1 regionrunning low$0.63/hrlaunch
A100 40GBcommunity40G4 regionsrunning low$0.45/hrlaunch
B200community192G1 regionrunning low$12.75/hrlaunch
RTX 4080community16G2 regionsrunning low$0.27/hrlaunch
RTX 4000 ADA20G1 regionrunning low$0.34/hrlaunch
RTX 309024G1 regionrunning low$0.60/hrlaunch
L424G1 regionrunning low$0.83/hrlaunch
RTX PRO 450032G1 regionrunning low$0.86/hrlaunch
H100 SXMcommunity80G2 regionsrunning low$4.41/hrlaunch
RTX A6000community48G1 regionrunning low$0.58/hrlaunch
H100 NVLcommunity94G1 regionrunning low$5.08/hrlaunch
V100community16G1 regionrunning low$0.16/hrlaunch

lowest live on-demand rate per GPU, refreshed continuously · per-second billing

L40 price history

last 90 days

Our floor price for the L40, sampled continuously across every provider in the fleet and rolled up to one point per day. A dot on the zero line is a day we checked and found nothing launchable; a shaded break is a day we did not sample. Those are different facts, so this chart never draws one as the other.

  • Price ($/GPU-hr)
  • Sold out — 0 available
  • No data collected for this window

Daily trend, updated hourly · Full 15-minute history available via API

L40 price comparison (November 2026)

ProviderPrice / GPU / hrNotes
GPU.ai (Secure Cloud)$0.935/hrVetted data center capacity, per-second billing
CoreWeave—Public on-demand list rate
AWS—Public on-demand list rate
Azure—Public on-demand list rate

competitor rates are public on-demand list prices, refreshed daily · gpu.ai prices are live floor rates

Compare and explore

faq

L40 rental questions●

How much does it cost to rent an L40 in the cloud?

L40 cloud instances on GPU.ai currently start at $0.935 per GPU per hour, billed per second. That is the live floor price across every provider in our fleet. We route your launch to the cheapest provider with stock.

How much VRAM does the L40 have?

The NVIDIA L40 has 48 GB of GDDR6 memory with up to 864 GB/s of bandwidth. GPU.ai reports the minimum VRAM actually delivered across our fleet, so the figure you see at launch is the figure you get.

Can I rent a multi-GPU L40 node?

Yes: real 4× L40 nodes are launchable right now, from $0.935 per GPU per hour. We only advertise node sizes that exist in live inventory, not theoretical configurations.

How does GPU.ai's L40 pricing compare to AWS, Azure, and CoreWeave?

GPU.ai aggregates a dozen-plus GPU clouds and routes each launch to the cheapest one with stock, so the same silicon is typically far cheaper than hyperscaler list rates. The comparison table on this page shows the current public on-demand list prices side by side.

How does billing work?

Billing is per second, starting when your instance is SSH-ready and stopping the moment you terminate. There are no minimum commitments, no reservation fees, and no egress surprises: you pay the listed hourly rate pro-rated to the second.