Rent NVIDIA L4
per GPU-hour
📊 Pricing at a Glance
NVIDIA L4 on-demand pricing, in stock right now, ranges from $0.89/GPU/hr to $0.93/GPU/hr across 2 offers from 2 providers with live stock tracking (updated October 2026). A further 24 tracked listings are shown below as listed / last-seen pricing.
Looking for a specific provider? See Scaleway NVIDIA L4, Vast.ai NVIDIA L4, or JarvisLabs NVIDIA L4.
Available Offers
The 5 cheapest on-demand offers reported in stock right now, from 2 providers with live stock tracking.
Other Tracked Listings (Last-Seen Pricing)
24 further listings GPUPerHour tracks for this GPU. These catalog rows do not qualify as current secure on-demand offers; stock observations may be missing or old. They are not confirmed in stock; check availability with the provider.
| Provider | Listed per GPU / hr | Pricing type | Availability |
|---|---|---|---|
| Vast.ai | $0.33 | on-demand | Check provider |
| Vast.ai | $0.33 | on-demand | Check provider |
| Vast.ai | $0.33 | on-demand | Check provider |
| Vast.ai | $0.33 | on-demand | Check provider |
| Vast.ai | $0.33 | on-demand | Check provider |
| Vast.ai | $0.33 | on-demand | Check provider |
| JarvisLabs | $0.44 | on-demand | Check provider |
| RunPod | $0.59 | on-demand | Check provider |
| Scaleway | $0.89 | on-demand | Check provider |
| Scaleway | $0.89 | on-demand | Check provider |
L4 Availability Now
2 providers report L4 in stock on-demand right now (2 offers across 2 regions). Last stock observation: .
| Region | Cheapest $/GPU-hr | Provider | Offers in stock |
|---|---|---|---|
| Paris, France (PAR1) | $0.89 | Scaleway | 1 |
| lille-4 | $0.93 | Ori | 1 |
Regions are as the providers name them. Prices on this page were observed on (UTC) and are quoted for that day; they are rechecked every minute and can change before booking.
L4 Price History (daily)
Over the last 14 days the cheapest on-demand L4 ranged from $0.49 to $0.59 per GPU-hour across up to 3 providers with stock.
| Date (UTC) | Cheapest $/GPU-hr | Median $/GPU-hr | Offers in stock | Providers with stock |
|---|---|---|---|---|
| $0.59 | $0.89 | 4 | 2 | |
| $0.59 | $0.89 | 4 | 2 | |
| $0.59 | $0.88 | 5 | 2 | |
| $0.59 | $0.88 | 4 | 2 | |
| $0.59 | $0.88 | 4 | 2 | |
| $0.59 | $0.88 | 3 | 2 | |
| $0.59 | $0.88 | 3 | 2 | |
| $0.59 | $0.88 | 5 | 3 | |
| $0.59 | $0.88 | 5 | 3 | |
| $0.59 | $0.88 | 4 | 3 | |
| $0.59 | $0.88 | 4 | 3 | |
| $0.49 | $0.89 | 5 | 2 | |
| $0.49 | $0.88 | 4 | 3 | |
| $0.49 | $0.88 | 5 | 3 |
One row per captured day (00:05 UTC). Cheapest is the lowest secure on-demand price per GPU-hour reported in stock by a provider with live stock tracking; median is the median of those offers. Days without a capture are not shown. Method and full series: Cloud GPU Price Index.
L4 Price by Provider
Cheapest on-demand offer per provider that is reported in stock right now. Prices are per GPU per hour; multi-GPU instances show the whole-instance price alongside. Deploy opens the DeployGPU console for providers on the platform, otherwise the provider's own site.
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| Scaleway | Paris, France (PAR1) | 1 | $0.89 | $0.89 | Deploy this GPU |
| Ori | lille-4 | 1 | $0.93 | $0.93 | Deploy this GPU |
Notify me when L4 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.89/GPU-hr.
L4 Catalog Listing History (30 days)
Catalog listings, not live prices.
These averages are of every tracked catalog listing, including spot, reserved, out-of-stock and older rows. They do not measure live on-demand prices or availability (the daily price history table above does that) and cannot establish savings against the current offers. Each day averages its recorded catalog snapshots; the median gives each day equal weight. Missing days are excluded.
| Lowest daily catalog average | $0.55/GPU/hr |
|---|---|
| Median of daily catalog averages | $0.56/GPU/hr |
| Days with recorded catalog prices | 30 of 30 |
| Latest catalog snapshot | October 19, 2026 |
QuantaCloud
Need GPUs at scale?
Building out an inference fleet or training cluster? QuantaCloud brokers reserved capacity across multiple data center partners. 16+ GPUs, flexible terms, custom quote in 24 hours.
Technical Specifications
Strengths & Limitations
- Energy-efficient design suitable for dense server deployments.
- Strong performance for AI inference workloads.
- Excellent video transcoding capabilities with support for multiple codecs.
- Supports virtual workstations for remote graphics-intensive applications.
- Single-slot, low-profile form factor for broad server compatibility.
- Lower raw compute performance compared to higher-end GPUs like the A100 or H100.
- GDDR6 memory offers lower bandwidth than HBM2 or HBM3 found in more powerful GPUs.
- Limited suitability for large-scale AI training due to memory capacity and compute limitations.
Top Use Cases
Ideal for deploying AI models at scale for tasks such as image recognition, natural language processing, and recommendation systems. The L4's Tensor Cores accelerate inference operations, providing low latency and high throughput.
Accelerates video encoding and decoding for various formats, enabling real-time video processing and streaming applications. Supports popular codecs like H.264, H.265 (HEVC), and AV1.
Provides the necessary graphics performance for virtual workstations, allowing users to access demanding applications remotely with a smooth and responsive experience. Supports NVIDIA virtual GPU (vGPU) software.
Real-World Benchmark
Market Analysis
Generated market commentary, not current pricing. Live prices and stock are in the sections above.
The NVIDIA L4 occupies a strategic position in the data center GPU market, targeting applications that require a balance of performance, efficiency, and cost-effectiveness. It competes with other mid-range GPUs like the NVIDIA A10 and Tesla T4, offering a compelling alternative for users who need strong inference and video transcoding capabilities without the high cost of flagship GPUs. The L4's energy efficiency and single-slot form factor make it particularly attractive for deployments in space-constrained environments.
Frequently Asked Questions
What is the typical power consumption of the NVIDIA L4?â–¾
The NVIDIA L4 has a typical power consumption of 72W, making it an energy-efficient option for data centers.
Does the NVIDIA L4 support NVIDIA vGPU software?â–¾
Yes, the NVIDIA L4 supports NVIDIA vGPU software, enabling virtual workstation deployments.
What is the maximum memory capacity of the NVIDIA L4?â–¾
The NVIDIA L4 is equipped with 24 GB of GDDR6 memory.
Alternative GPUs
Journalists, bloggers, and researchers: You're welcome to cite our data in your articles with attribution. Our pricing database is checked periodically from 5 cloud providers tracking this GPU.