The cheapest L4 on the table right now is $0.048 per GPU-hour at Vast.ai (spot), out of 16 offers from 9 providers. The L4 carries 24 GB of VRAM on NVIDIA's Ada generation. That is peer/marketplace capacity — rented from other users' machines, and not directly comparable to a dedicated instance.
On-demand pricing for the same card spans $0.112 to $0.925 per GPU-hour — an 8.2× 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 $0.112 at Vast.ai · spot $0.048 at Vast.ai.
| Provider | Tier | $/GPU-hr | Pricing | Node | Commit | In stock | |
|---|---|---|---|---|---|---|---|
| Vast.ai | marketplace | $0.048 | spot | 1× GPU | — | yes | rent |
| Google Cloud | dedicated | $0.056 | spot | 1× GPU | — | — | rent |
| Vast.ai | marketplace | $0.112 | on-demand | 1× GPU | — | yes | rent |
| Vast.ai | marketplace | $0.133 | spot | 2× GPU | — | yes | rent |
| Vast.ai | marketplace | $0.268 | on-demand | 2× GPU | — | yes | rent |
| Seeweb | dedicated | $0.424 | on-demand | 1× GPU | — | — | rent |
| Jarvis Labs * | dedicated | $0.440 | on-demand | 1× GPU | — | yes | rent |
| Google Cloud | dedicated | $0.558 | on-demand | 1× GPU | — | — | rent |
| Runpod | dedicated | $0.590 | on-demand | 1× GPU | — | yes | rent |
| Modal * | dedicated | $0.799 | on-demand | 1× GPU | — | yes | rent |
| Baseten | dedicated | $0.848 | on-demand | 1× GPU | — | yes | rent |
| Scaleway | dedicated | $0.878 | on-demand | 1–8× GPU | — | — | rent |
| OVHcloud | dedicated | $0.925 | on-demand | 1× GPU | — | — | rent |
How much does an L4 cost per hour?
As of the latest scrape, $0.048 per GPU-hour at Vast.ai is the cheapest L4 offer across 9 tracked cloud providers. The cheapest on-demand rate is $0.112 per GPU-hour at Vast.ai, and the most expensive on-demand rate is $0.925 at OVHcloud.
Which cloud is cheapest for the L4?
Vast.ai at $0.048 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 $0.048 per GPU-hour at Vast.ai, -57% versus the cheapest on-demand rate of $0.112. 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.