GPU cloud pricing
NVIDIA L4 price per hour: cheapest cloud
6 clouds rent out the L4. JarvisLabs is cheapest at $0.44 per GPU-hour; OVHcloud charges 2.3× as much.
- On-demand from$0.44per GPU-hour · JarvisLabs
- One GPU, all month$321.20730 hours on-demand
- Spot from$0.2907per GPU-hour · Google Cloud
- Price gap2.3×across 6 clouds
- Memory24 GBlargest version listed
On-demand list prices per GPU-hour in USD · checked Nov 17, 2026 · How we compare GPU prices
Ranked for your usage
Monthly L4 cost by cloud
Cheapest for your volume
L4 at JarvisLabs
6 options · most expensive $720.00, 2.3× this price
| Cloud | Estimated / month | Per GPU-hour | Spot / GPU-hour |
|---|---|---|---|
1 JarvisLabsGPU cloud · L4Pricing pageChecked | $316.80 | $0.44 | not listed |
2 RunPod (Secure Cloud)GPU cloud · L4Pricing pageChecked | $496.80 | $0.69 | not listed |
3 Google CloudHyperscaler · L4 · g2-standard-4, us-east4Pricing pageChecked | $507.24 | $0.7045 | $0.2907 |
4 AWSHyperscaler · L4 · g6.xlarge, us-east-1Pricing pageChecked | $579.46 | $0.8048 | not listed |
5 ScalewayGPU cloud · L4Pricing pageChecked | $626.62 | $0.8703 | not listed |
6 OVHcloudGPU cloud · L4Pricing pageChecked | $720.00 | $1.00 | not listed |
1 GPU × 24 h × 30 days = 720 GPU-hours at list price. Storage, network egress, taxes and reserved-capacity discounts are not included.
On-demand and spot list prices per GPU-hour in USD, checked daily (last Nov 17, 2026). Sources: GPU Rental Prices and Cloud GPU List Prices (AWS, Google Cloud and Azure price APIs), both CC BY 4.0; every row links the cloud's own pricing page. Order depends on price only. How we compare GPU prices.
Serverless L4: pay only while it runs
Billed per second of use, usually with a cold start; cheaper than renting for spiky traffic, dearer around the clock.
| Platform | Per GPU-hour of use | Source |
|---|---|---|
| Koyeb L4 | $0.70 | Pricing page |
| Cerebrium L4 | $0.7992 | Pricing page |
| Modal L4 | $0.7992 | Pricing page |
Before you rent
Rates are per GPU-hour; an instance with several GPUs bills all of them. Hyperscalers often sell this chip only in 8-GPU instances, so check the smallest size before comparing.
Running one L4 around the clock costs $321.20 a month at JarvisLabs and $730.00 at OVHcloud. Availability, regions and network speed differ, so check capacity before you commit.
Serving an open model? Compare per-token API prices first: below a steady load, paying per token is often cheaper than a rented GPU.