L4 cloud GPU pricing

The cheapest L4 on the table right now is $0.056 per GPU-hour at Google Cloud (spot), out of 19 offers from 9 providers. The L4 carries 24 GB of VRAM on NVIDIA's Ada generation.

On-demand pricing for the same card spans $0.202 to $0.966 per GPU-hour — a 4.8× spread between the cheapest and the most expensive provider for identical silicon. That gap is the entire reason this table exists.

Cheapest by pricing model: on-demand $0.202 at Vast.ai · spot $0.056 at Google Cloud.

Every L4 price we track

ProviderTier$/GPU-hrPricingNode CommitIn stock
Google Cloud dedicated $0.056 spot 1× GPU rent
Vast.ai marketplace $0.080 spot 1× GPU yes rent
Vast.ai marketplace $0.200 spot 2× GPU yes rent
Vast.ai marketplace $0.202 on-demand 1× GPU yes rent
Vast.ai marketplace $0.320 spot 4× GPU yes rent
Vast.ai marketplace $0.334 on-demand 2, 4× GPU yes rent
Jarvis Labs dedicated $0.440 on-demand 1× GPU yes rent
Seeweb dedicated $0.442 on-demand 1× GPU rent
Runpod dedicated $0.490 on-demand 1× GPU yes rent
Runpod dedicated $0.490 spot 1× GPU yes rent
Google Cloud dedicated $0.558 on-demand 1× GPU rent
Modal dedicated $0.799 on-demand 1× GPU yes rent
Baseten dedicated $0.848 on-demand 1× GPU yes rent
Scaleway dedicated $0.917 on-demand 1–8× GPU rent
OVHcloud dedicated $0.966 on-demand 1× GPU rent

Rows that quote one rate across several node sizes are folded together. "Marketplace" is peer capacity (Vast.ai, Salad, RunPod Community, Lium) and is not directly comparable to dedicated instances.

Questions

How much does an L4 cost per hour?
As of the latest scrape, $0.056 per GPU-hour at Google Cloud is the cheapest L4 offer across 9 tracked cloud providers. The cheapest on-demand rate is $0.202 per GPU-hour at Vast.ai, and the most expensive on-demand rate is $0.966 at OVHcloud.

Which cloud is cheapest for the L4?
Google Cloud at $0.056 per GPU-hour on spot capacity. Prices move constantly, so this page is regenerated from the live scrape every 15 minutes. Note that marketplace tiers are peer hardware and are not directly comparable to dedicated capacity.

Is spot L4 capacity cheaper?
Yes — the cheapest spot L4 is $0.056 per GPU-hour at Google Cloud, -73% versus the cheapest on-demand rate of $0.202. Spot instances can be reclaimed by the provider at any time, so they suit checkpointed training and batch inference rather than long-lived services.

How many GB of VRAM does the L4 have?
24 GB, on the Ada architecture. Multi-GPU instances multiply that: an 8× L4 node exposes 192 GB of GPU memory in total.

Compare with other GPUs

All GPUs · All providers · Live sortable table