We match your deposits, up to $150 in free credits. Ends October 1.Learn more  

gpu catalog: l4

Rent L4 from $0.270/hr

A 72-watt inference card, the efficiency pick for video pipelines, embeddings, and small-model serving at scale.

Live platform rates

27 GPU types online
GPUVRAMRegionsAvailabilityPrice / GPU
L424G3 regionsavailable$0.44/hrlaunch

A 72-watt inference card, the efficiency pick for video pipelines, embeddings, and small-model serving at scale.

VRAM24 GB GDDR6
Memory bandwidth0.3 TB/s
FP16 tensor121 TFLOPS
ArchitectureAda Lovelace
InterconnectPCIe 4.0
Board power72 W
CUDA cores7,424
Released2023
Regionseu-east, india-south, us-east
L4community24G2 regionsrunning low$0.27/hrlaunch
L40S48G3 regionshigh availability$0.80/hrlaunch
L4048G2 regionshigh availability$0.78/hrlaunch
RTX A600048G2 regionshigh availability$0.40/hrlaunch
RTX PRO 600096G4 regionshigh availability$1.99/hrlaunch
RTX 4090community24G7 regionshigh availability$0.28/hrlaunch
RTX 5090community32G7 regionshigh availability$0.35/hrlaunch
A10080G4 regionshigh availability$1.07/hrlaunch
RTX 6000 ADA48G1 regionhigh availability$0.65/hrlaunch
RTX PRO 450032G2 regionshigh availability$0.72/hrlaunch
H200 SXMcommunity141G5 regionshigh availability$3.59/hrlaunch
RTX 3090community24G7 regionshigh availability$0.12/hrlaunch
H200 SXM141G6 regionshigh availability$3.99/hrlaunch
H100 SXM80G5 regionshigh availability$2.54/hrlaunch
RTX A4000community16G5 regionsavailable$0.08/hrlaunch
A100community80G5 regionsavailable$0.95/hrlaunch
RTX 409024G4 regionsavailable$0.74/hrlaunch
RTX PRO 6000community96G3 regionsavailable$1.69/hrlaunch
H100 NVLcommunity94G5 regionsavailable$2.59/hrlaunch
B200192G3 regionsavailable$6.79/hrlaunch
L40Scommunity48G3 regionsavailable$0.61/hrlaunch
H100 SXMcommunity80G3 regionsavailable$1.87/hrlaunch
RTX 3080community10G3 regionsavailable$0.07/hrlaunch
H100 NVL94G3 regionsavailable$3.19/hrlaunch
B300288G2 regionsavailable$7.89/hrlaunch
RTX 5080community16G7 regionsavailable$0.16/hrlaunch
A100 40GBcommunity40G5 regionsavailable$0.72/hrlaunch
H200 NVLcommunity141G4 regionsavailable$3.61/hrlaunch
H100 PCIE80G2 regionsavailable$1.98/hrlaunch
H100 PCIEcommunity80G2 regionsavailable$2.54/hrlaunch
RTX 4080community16G4 regionsrunning low$0.17/hrlaunch
RTX 2000 ADA16G2 regionsrunning low$0.24/hrlaunch
A4048G2 regionsrunning low$0.49/hrlaunch
B200community192G2 regionsrunning low$5.32/hrlaunch
RTX A5000community24G2 regionsrunning low$0.23/hrlaunch
RTX 4000 ADAcommunity20G1 regionrunning low$0.20/hrlaunch
RTX A400016G1 regionrunning low$0.25/hrlaunch
RTX 4000 ADA20G1 regionrunning low$0.28/hrlaunch
H200 NVL141G1 regionrunning low$3.29/hrlaunch
RTX A6000community48G1 regionrunning low$0.48/hrlaunch
A100 40GB40G1 regionrunning low$0.89/hrlaunch

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

L4 price comparison (September 2026)

ProviderPrice / GPU / hrNotes
GPU.ai (Secure Cloud)$0.440/hrVetted data center capacity, per-second billing
GPU.ai (Community Cloud)$0.270/hrMarketplace capacity from independent suppliers
CoreWeavePublic on-demand list rate
AWSPublic on-demand list rate
AzurePublic on-demand list rate

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

Compare and explore

faq

L4 rental questions

How much does it cost to rent an L4 in the cloud?

L4 cloud instances on GPU.ai currently start at $0.270 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 and add zero markup.

How much VRAM does the L4 have?

The NVIDIA L4 has 24 GB of GDDR6 memory with up to 300 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 L4 node?

Yes: real 4× L4 nodes are launchable right now, from $0.323 per GPU per hour. We only advertise node sizes that exist in live inventory, not theoretical configurations.

How does GPU.ai's L4 pricing compare to AWS, Azure, and CoreWeave?

GPU.ai aggregates a dozen-plus GPU clouds and passes through each provider's raw price with no markup, 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.