Loading page
L4 pricing on Runpod
Every Runpod L4 offering we track, normalized to a per-GPU hourly rate and ranked against 20 providers with current L4 pricing.
From / GPU-hr
$0.490
Price rank
#10 of 20
Configurations
4
Last updated
September 18, 2026
The cheapest L4 we currently track is $0.130/hr on GPU Outlet.
Runpod L4 rates
Hourly prices per GPU. Multi-GPU rows show the per-GPU rate, not the instance total.
| Price / GPU-hr | Type | GPUs |
|---|---|---|
| $0.490 | On-demand | 1 |
| $0.490 | On-demand | 2 |
| $0.490 | On-demand | 3 |
| $0.490 | On-demand | 4 |
L4 specifications
- VRAM
- 24GB
- Architecture
- Ada Lovelace
- CUDA Cores
- 7,424
- Tensor Cores
- 232
- Memory Bandwidth
- 300 GB/s
- TDP
- 72W
L4 on other providers
- GPU Outlet$0.130/hr
- Lium.io$0.270/hr
- gpu.ai$0.320/hr
- Vast.ai$0.325/hr
- Omega Gradient$0.330/hr
- Seeweb$0.436/hr
- AtmosCompute$0.440/hr
- Jarvis Labs$0.440/hr
- Google Cloud$0.450/hr
- AceCloud$0.662/hr
- UpCloud$0.670/hr
- Modal$0.799/hr
- Amazon AWS$0.805/hr
- Scaleway$0.904/hr
- Shadeform$0.950/hr
- IO.NET$1.04/hr
- Sesterce$1.04/hr
- Runcrate$1.05/hr
- Hinode$1.75/hr
About Runpod
Runpod is an AI developer cloud for building, deploying, and scaling AI workloads. It offers on‑demand GPU pods across 31 regions in two tiers — data‑center‑hosted Secure Cloud and lower‑cost Community Cloud — plus serverless endpoints and multi‑node clusters, with B300, B200, and H100/H200 alongside A100, L40S, RTX PRO 6000, and RTX classes.
Frequently Asked Questions
How much does the L4 cost on Runpod?
Runpod lists the L4 from $0.490 per GPU-hour across 4 tracked configurations. Prices are collected daily — see the table above for the current rates.
Is Runpod the cheapest place to rent the L4?
Runpod ranks #10 of 20 providers we track with current L4 pricing. The cheapest right now is GPU Outlet. Price is only one factor — region availability, network, and storage costs differ between providers.
Which L4 configurations does Runpod offer?
We currently track 4 L4 offerings from Runpod, covering the GPU counts, pricing types, and regions listed in the table above. Every price is normalized to a per-GPU hourly rate so it can be compared across providers.