L4 · 24 GB · Ada Lovelace
L4 rental prices across providers
As of 12 November 2026, the lowest listed on-demand price for a L4 among 5 providers is $0.59 per GPU-hour at RunPod. The median of each provider's lowest price is $0.80 and the highest is $1.36.
- Lowest listed
- $0.59
- Median
- $0.80
- Highest
- $1.36
- Providers
- 5
Vast.ai, per GPU-hour
of each provider’s lowest price
Runcrate
21 configurations
By provider
L4 price by provider
- Vast.ai$0.10/GPU-hr
- RunPod$0.59/GPU-hr
- Google Cloud$0.71/GPU-hr
- Amazon Web Services$0.80/GPU-hr
- OVHcloud$1.00/GPU-hr
- Runcrateours$1.36/GPU-hr
Every listing
All L4 configurations we track
| Configuration | Billing | Region | Source | ||||
|---|---|---|---|---|---|---|---|
| Vast.aimarketplace | 1× · Marketplace lowest listed (L4) | not stated | $0.10 | $0.10 | not stated | 2026-11-12 | page |
| Vast.aimarketplace | 1× · Marketplace median (L4) | not stated | $0.35 | $0.35 | not stated | 2026-11-12 | page |
| RunPod | 1× · Secure Cloud L4 | per second | $0.59 | $0.59 | not stated | 2026-11-12 | page |
| Google Cloud | 1× · g2-standard-4 (4 vCPU, 16GiB RAM) | not stated | $0.71 | $0.71 | not stated | 2026-11-12 | page |
| Amazon Web Services | 1× · g6.xlarge | per second | $0.80 | $0.80 | us-east-1 | 2026-11-12 | page |
| Google Cloud | 1× · g2-standard-8 (8 vCPU, 32GiB RAM) | not stated | $0.85 | $0.85 | not stated | 2026-11-12 | page |
| Amazon Web Services | 1× · g6.2xlarge | per second | $0.98 | $0.98 | us-east-1 | 2026-11-12 | page |
| OVHcloud | 1× · l4-90 | per hour | $1.00 | $1.00 | not stated | 2026-11-12 | page |
| OVHcloud | 2× · l4-180 | per hour | $1.00 | $2.00 | not stated | 2026-11-12 | page |
| OVHcloud | 4× · l4-360 | per hour | $1.00 | $4.00 | not stated | 2026-11-12 | page |
| Google Cloud | 1× · g2-standard-12 (12 vCPU, 48GiB RAM) | not stated | $1.00 | $1.00 | not stated | 2026-11-12 | page |
| Google Cloud | 2× · g2-standard-24 (24 vCPU, 96GiB RAM) | not stated | $1.00 | $2.00 | not stated | 2026-11-12 | page |
| Google Cloud | 4× · g2-standard-48 (48 vCPU, 192GiB RAM) | not stated | $1.00 | $4.00 | not stated | 2026-11-12 | page |
| Google Cloud | 8× · g2-standard-96 (96 vCPU, 384GiB RAM) | not stated | $1.00 | $8.00 | not stated | 2026-11-12 | page |
| Google Cloud | 1× · g2-standard-16 (16 vCPU, 64GiB RAM) | not stated | $1.15 | $1.15 | not stated | 2026-11-12 | page |
| Amazon Web Services | 4× · g6.12xlarge | per second | $1.15 | $4.60 | us-east-1 | 2026-11-12 | page |
| Amazon Web Services | 1× · g6.4xlarge | per second | $1.32 | $1.32 | us-east-1 | 2026-11-12 | page |
| Runcrateours, live | 1× | per second | $1.36 | $1.36 | Warsaw, Poland | 2026-11-12 | page |
| Amazon Web Services | 4× · g6.24xlarge | per second | $1.67 | $6.68 | us-east-1 | 2026-11-12 | page |
| Amazon Web Services | 8× · g6.48xlarge | per second | $1.67 | $13.35 | us-east-1 | 2026-11-12 | page |
| Google Cloud | 1× · g2-standard-32 (32 vCPU, 128GiB RAM) | not stated | $1.73 | $1.73 | not stated | 2026-11-12 | page |
| Amazon Web Services | 1× · g6.8xlarge | per second | $2.01 | $2.01 | us-east-1 | 2026-11-12 | page |
| Amazon Web Services | 1× · g6.16xlarge | per second | $3.40 | $3.40 | us-east-1 | 2026-11-12 | page |
Questions
L4 rental: common questions
What is the lowest L4 price per hour?
As of 12 November 2026, the lowest listed on-demand price for a L4 among 5 providers is $0.59 per GPU-hour at RunPod. The median of each provider's lowest price is $0.80 and the highest is $1.36.
How much does an 8-GPU L4 server cost per hour?
The lowest 8-GPU on-demand configuration in our data is Google Cloud at $1.00 per GPU, $8.00 per hour for the server (read 2026-11-12).
Which providers bill L4 time by the second?
RunPod, Amazon Web Services, and Runcrate state per-second billing for their lowest-priced L4 listing.
Is the price per GPU or per server?
Per GPU per hour. The total column multiplies by the number of GPUs in that configuration. Multi-GPU configurations often cost a little more per GPU.
How current is this data?
Prices are read from each provider's public pricing page; the table shows the date each was read, and the latest read is 12 November 2026. Runcrate's own price comes live from runcrate.ai.
Billing as stated on each provider's page, per second: RunPod, Amazon Web Services, and Runcrate; per hour: OVHcloud. Providers that do not state it are not listed here.
Disclosure
Provider Index is published by the Runcrate team, who also run Runcrate, an AI cloud. Runcrate is listed in the table for L4, marked "ours, live". It is sorted by price like every other row, with no pinned position. Other providers' prices are read from their own public pricing pages. We have no paid placement.