NVIDIA L40S cloud GPU prices
Compare L40S cloud prices for inference, rendering and workloads that fit its available memory. Provider host resources can differ even when the GPU model is the same.
Source publication dates in this view: Sep 26, 2026–Sep 26, 2026. Publication is date-level; the time each price was observed is not supplied.
Catalog generated: . This is not a source or deployment timestamp.
Lowest listed on-demand rate
$1.09/GPU·hr
RunPod · L40S · Unspecified · 48 GB per GPU · 1 GPUs · $1.09/instance·hr · US-IL-1
Lowest listed spot / interruptible rate
$0.377/GPU·hr
AWS · L40S · Unspecified · 44.703125 GB per GPU · 4 GPUs · $1.51/instance·hr · us-east-1
Compare rental prices
Lowest listed offer for each provider, model, reported variant, GPU count, VRAM and pricing type across listed regions. This is a summary of our coverage, not a market-wide minimum or a performance ranking. Use the comparison filters for regional configurations.
Links marked affiliate may earn us a commission or compute credits. This does not affect price ordering. Affiliate disclosure.
| Provider / GPU / variant | VRAM per GPU | Pricing | Per GPU / hr | Full instance / hr | Region | Source / published date |
|---|---|---|---|---|---|---|
| AWS L40S · Unspecified Instance: g6e.24xlarge Link to offer | 44.703125 GB | Spot / interruptible | $0.377 | $1.51 4 GPUs | us-east-1 | Check provider priceSource snapshot (ZIP)Published |
| AWS L40S · Unspecified Instance: g6e.4xlarge Link to offer | 44.703125 GB | Spot / interruptible | $0.581 | $0.581 1 GPUs | eu-central-1 | Check provider priceSource snapshot (ZIP)Published |
| Nebius L40S · Unspecified Instance: gpu-l40s-a 1gpu-8vcpu-32gb Link to offer | 48 GB | Spot / interruptible | $0.749 | $0.749 1 GPUs | eu-north1 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 1L40S.20V Link to offer | 48 GB | Spot / interruptible | $0.756 | $0.756 1 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 2L40S.40V Link to offer | 48 GB | Spot / interruptible | $0.756 | $1.51 2 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 4L40S.80V Link to offer | 48 GB | Spot / interruptible | $0.756 | $3.03 4 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 8L40S.160V Link to offer | 48 GB | Spot / interruptible | $0.756 | $6.05 8 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| AWS L40S · Unspecified Instance: g6e.48xlarge Link to offer | 44.703125 GB | Spot / interruptible | $0.862 | $6.89 8 GPUs | us-east-1 | Check provider priceSource snapshot (ZIP)Published |
| RunPod L40S · Unspecified Instance: NVIDIA L40S Link to offer | 48 GB | On-demand | $1.09 | $1.09 1 GPUs | US-IL-1 | Check provider priceSource snapshot (ZIP)Published |
| Nebius L40S · Unspecified Instance: gpu-l40s-d 2gpu-64vcpu-384gb Link to offer | 48 GB | Spot / interruptible | $1.12 | $2.23 2 GPUs | eu-north1 | Check provider priceSource snapshot (ZIP)Published |
| Nebius L40S · Unspecified Instance: gpu-l40s-d 4gpu-128vcpu-768gb Link to offer | 48 GB | Spot / interruptible | $1.12 | $4.47 4 GPUs | eu-north1 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 8L40S.160V Link to offer | 48 GB | On-demand | $1.51 | $12.10 8 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 1L40S.20V Link to offer | 48 GB | On-demand | $1.51 | $1.51 1 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 2L40S.40V Link to offer | 48 GB | On-demand | $1.51 | $3.03 2 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| DataCrunch L40S · Unspecified Instance: 4L40S.80V Link to offer | 48 GB | On-demand | $1.51 | $6.05 4 GPUs | FIN-01 | Check provider priceSource snapshot (ZIP)Published |
| Nebius L40S · Unspecified Instance: gpu-l40s-a 1gpu-8vcpu-32gb Link to offer | 48 GB | On-demand | $1.55 | $1.55 1 GPUs | eu-north1 | Check provider priceSource snapshot (ZIP)Published |
| AWS L40S · Unspecified Instance: g6e.xlarge Link to offer | 44.703125 GB | On-demand | $1.86 | $1.86 1 GPUs | us-east-1 | Check provider priceSource snapshot (ZIP)Published |
| Nebius L40S · Unspecified Instance: gpu-l40s-d 2gpu-64vcpu-384gb Link to offer | 48 GB | On-demand | $2.28 | $4.57 2 GPUs | eu-north1 | Check provider priceSource snapshot (ZIP)Published |
| Nebius L40S · Unspecified Instance: gpu-l40s-d 4gpu-128vcpu-768gb Link to offer | 48 GB | On-demand | $2.28 | $9.14 4 GPUs | eu-north1 | Check provider priceSource snapshot (ZIP)Published |
| AWS L40S · Unspecified Instance: g6e.12xlarge Link to offer | 44.703125 GB | On-demand | $2.62 | $10.49 4 GPUs | us-east-1 | Check provider priceSource snapshot (ZIP)Published |
| Oracle Cloud L40S · Unspecified Instance: BM.GPU.L40S.4 Link to offer | 48 GB | On-demand | $3.50 | $14.00 4 GPUs | af-casablanca-1 | Check provider priceSource snapshot (ZIP)Published |
| AWS L40S · Unspecified Instance: g6e.48xlarge Link to offer | 44.703125 GB | On-demand | $3.77 | $30.13 8 GPUs | us-east-1 | Check provider priceSource snapshot (ZIP)Published |
Manufacturer specifications, with conditions
Reviewed September 26, 2026 against NVIDIA documentation. These are hardware specifications and theoretical peaks, not NVGPU measurements or third-party benchmark results. Sparse Tensor Core peaks require supported structured sparsity; they are not expected dense training throughput.
| Reference variant | Memory | Memory bandwidth | FP16 Tensor Core peak | Conditions and source |
|---|---|---|---|---|
| L40S | 48 GB GDDR6 ECC | 864 GB/s | 733 TFLOPS with sparsity | No NVLink. Check PCIe communication overhead for workloads split across GPUs. NVIDIA source |
NVGPU has not run application benchmarks for these comparisons. To assess a third-party result, require the model and revision, precision, batch size, sequence lengths, GPU count and variant, software versions, interconnect, test date and methodology.
Before you rent
- Check CPU, system RAM and disk requirements as well as GPU memory.
- Benchmark throughput and latency with the precision and batch size your application needs.
- Check persistence and storage billing before stopping an instance between jobs.
What is included in these prices?
These are compute rates from the gpuhunt pricing catalog. The instance shown is the configuration being priced, not evidence of the provider's smallest available rental. Storage, data transfer, tax, licenses and support can be additional. Reserved contracts, commitment discounts and serverless per-request charges are not compared. Listed spot capacity can disappear or be interrupted.
Normalization and exclusionsDoes a low hourly rate mean a cheaper job?
No. Multiply the full-instance hourly rate by measured billed hours, then add storage, transfer and other applicable charges. Compare the same workload and quality target. NVGPU has not measured the throughput or uptime of these rentals.