L40S pricing on Modal
Every Modal L40S offering we track, normalized to a per-GPU hourly rate and ranked against 21 providers with current L40S pricing.
The cheapest L40S we currently track is $0.479/hr on Verda.
Modal L40S rates
Hourly prices per GPU. Multi-GPU rows show the per-GPU rate, not the instance total.
| Price / GPU-hr | Type | GPUs |
|---|---|---|
| $1.95 | On-demand | 1 |
L40S specifications
- VRAM
- 48GB
- Architecture
- Ada Lovelace
- CUDA Cores
- 18,176
- Tensor Cores
- 568
- Memory Bandwidth
- 864 GB/s
- TDP
- 350W
L40S on other providers
- Verda$0.479/hr
- Packet AI$0.540/hr
- Beam$0.720/hr
- Latitude.sh$0.740/hr
- Sesterce$0.759/hr
- Runpod$0.790/hr
- IO.NET$0.840/hr
- Cudo Compute$0.870/hr
- Massed Compute$0.880/hr
- Civo$0.890/hr
- Seeweb$0.981/hr
- CoreWeave$0.985/hr
- Koyeb$1.20/hr
- Crusoe$1.45/hr
- AceCloud$1.50/hr
- DigitalOcean$1.57/hr
- Scaleway$1.70/hr
- Amazon AWS$1.86/hr
- Together AI$2.10/hr
- Oracle Cloud$3.50/hr
About Modal
Modal is a serverless GPU platform that lets developers run Python functions, jobs and inference endpoints on NVIDIA GPUs with per-second billing and scale-to-zero.
Frequently Asked Questions
How much does the L40S cost on Modal?
Modal lists the L40S from $1.95 per GPU-hour across 1 tracked configuration. Prices are collected daily — see the table above for the current rates.
Is Modal the cheapest place to rent the L40S?
Modal ranks #19 of 21 providers we track with current L40S pricing. The cheapest right now is Verda. Price is only one factor — region availability, network, and storage costs differ between providers.
Which L40S configurations does Modal offer?
We currently track 1 L40S offering from Modal, 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.