NVIDIA L4 rental price per hour
24GB GDDR6 VRAM · Ada Lovelace architecture · released 2023
The cheapest way to rent an NVIDIA L4 by the hour in June 2026 is about $0.33/hr on Vast.ai. We track 4 providers publishing an on-demand price for it , and spot/community rates reach as low as $0.33/hr. Low-cost, low-power inference and video/AI serving. 72W single-slot card; the cheapest datacenter GPU for steady inference at scale.
Source: Provider pricing pages. Data as of June 2026.
NVIDIA L4 price by provider
| Provider | Type | On-demand /hr | Spot/community /hr | Notes |
|---|---|---|---|---|
| Vast.ai | marketplace | $0.33/hr | — | Marketplace median. Host-set. |
| RunPod | specialist | $0.39/hr | — | Secure Cloud. |
| Google Cloud | hyperscaler | $0.71/hr | $0.33/hr | g2-standard-4 (1 GPU) $0.71/hr. |
| AWS EC2 | hyperscaler | $0.81/hr | $0.43/hr | g6.xlarge (1 GPU) $0.805/hr. |
| CoreWeave | specialist | — | — | Not on public price list. |
| Crusoe | specialist | — | — | Not offered. |
| Hyperstack | specialist | — | — | Not offered. |
| Lambda | specialist | — | — | Not offered. |
| Microsoft Azure | hyperscaler | — | — | Not offered. |
| Nebius | specialist | — | — | Not listed. |
| Paperspace (DigitalOcean) | specialist | — | — | Not on GPU Droplets list. |
| Together AI | specialist | — | — | Not offered. |
| Verda (formerly DataCrunch) | specialist | — | — | Not listed. |
| Vultr Cloud GPU | specialist | — | — | Not offered. |
Source: Provider pricing pages. Data as of June 2026.
Sorted cheapest on-demand first; "—" means the provider does not publish a price for this GPU (see the note). Snapshot June 2026 — cloud GPU prices change weekly; verify on the provider's pricing page before relying on a figure.
About the NVIDIA L4
Low-cost, low-power inference and video/AI serving. 72W single-slot card; the cheapest datacenter GPU for steady inference at scale.
- VRAM: 24GB GDDR6
- Architecture: Ada Lovelace
- Released: 2023
- Cheapest on-demand: $0.33/hr on Vast.ai
- Cheapest spot/community: $0.33/hr on Google Cloud
Frequently asked questions
How much does it cost to rent an NVIDIA L4 per hour?
The cheapest on-demand NVIDIA L4 we track is $0.33/hr on Vast.ai, with 4 providers publishing a price. Spot/community rates go as low as $0.33/hr. Snapshot June 2026 — cloud GPU prices change weekly; verify on the provider's pricing page before relying on a figure.
Which provider is cheapest for the NVIDIA L4?
Vast.ai at $0.33/hr is the cheapest on-demand option in our June 2026 snapshot. Specialist neoclouds and marketplaces usually beat the hyperscalers (AWS/GCP/Azure) by 2-4x on the same GPU.
What is the NVIDIA L4 good for?
Low-cost, low-power inference and video/AI serving. 72W single-slot card; the cheapest datacenter GPU for steady inference at scale. It has 24GB GDDR6 of VRAM and uses the Ada Lovelace architecture (released 2023).
Is spot or on-demand cheaper for the NVIDIA L4?
Spot, community and interruptible tiers can cut the NVIDIA L4 price roughly in half — the cheapest discounted rate we track is $0.33/hr versus $0.33/hr on-demand. The trade-off is your instance can be reclaimed, so use spot for fault-tolerant or checkpointed jobs.
Related GPUs
- NVIDIA L40S (48GB GDDR6)
- NVIDIA RTX 6000 Ada (48GB GDDR6)
- NVIDIA RTX A6000 (48GB GDDR6)
Keep exploring
Source & accuracy
Figures are a dated snapshot from each provider's published pricing page (as of June 2026). Hyperscaler per-GPU prices are derived from 8-GPU instance prices (instance price / 8) and include bundled vCPU/RAM; marketplace (Vast.ai) figures are moving medians, not list prices. We do not invent numbers — where a value is unknown we show "—" with a reason. See our methodology. This is an informational comparison, not a quote.
Last updated: 2026-06-21