L40 pricing on Hyperstack
Every Hyperstack L40 offering we track, normalized to a per-GPU hourly rate and ranked against 18 providers with current L40 pricing.
The cheapest L40 we currently track is $0.297/hr on Meshive.
Hyperstack L40 rates
Hourly prices per GPU. Multi-GPU rows show the per-GPU rate, not the instance total.
| Price / GPU-hr | Type | GPUs |
|---|---|---|
| $0.700 | Reserved | 1 |
| $0.800 | Spot | 1 |
| $1.00 | On-demand | 1 |
L40 specifications
- VRAM
- 40GB
- Architecture
- Ada Lovelace
- CUDA Cores
- 18,176
- Tensor Cores
- 568
- Memory Bandwidth
- 864 GB/s
- TDP
- 300W
L40 on other providers
- Meshive$0.297/hr
- Vast.ai$0.457/hr
- IO.NET$0.661/hr
- Runpod$0.690/hr
- Massed Compute$0.772/hr
- gpu.ai$0.780/hr
- Thunder Compute$0.790/hr
- Aquanode$0.850/hr
- Shadeform$0.880/hr
- Omega Gradient$0.930/hr
- QuantaCloud$0.938/hr
- Sesterce$0.968/hr
- Fluence Cloud$1.03/hr
- Oblivus$1.05/hr
- Runcrate$1.14/hr
- CoreWeave$1.25/hr
- Together AI$1.49/hr
About Hyperstack
Hyperstack offers on-demand, reserved and spot NVIDIA GPU VMs (B300, B200, H200, H100, A100, L40 and more) billed per minute, plus AI Studio for token-billed inference and fine-tuning.
Frequently Asked Questions
How much does the L40 cost on Hyperstack?
Hyperstack lists the L40 from $0.700 per GPU-hour across 3 tracked configurations. Prices are collected daily — see the table above for the current rates.
Is Hyperstack the cheapest place to rent the L40?
Hyperstack ranks #5 of 18 providers we track with current L40 pricing. The cheapest right now is Meshive. Price is only one factor — region availability, network, and storage costs differ between providers.
Which L40 configurations does Hyperstack offer?
We currently track 3 L40 offerings from Hyperstack, 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.