Loading prices…
L40S rental prices
NVIDIA · Ada Lovelace · 48 GB GDDR6 · PCIe · 2023
17 providers · 50 configurations · prices as of Sep 27, 2026, 01:12 UTC
Lowest on-demand
$0.60per GPU·h · ≈ $440/month
at Vast.aiMedian on-demand
$1.50/GPU·h
across 17 providers
Lowest spot
$0.38/GPU·h
Reserved from $0.82
FP16/BF16 cost
$1.66/PFLOP·h
#12 of 70 GPUs for value
Providers
17
50 configurations
Price history
Daily L40S prices per GPU-hour. The shaded period is reconstructed from the version history of SkyPilot's public price catalogs (fewer providers than live data); after that, PetaPrice's own tracking.
Lowest on-demandMedian on-demandLowest spot
Price by provider
Cheapest On-demand L40S offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Vast.ai🇺🇸$0.60best
Boost Run$0.69+15%
Latitude.sh🇺🇸$0.74+23%
RunPod🇺🇸$0.79+31%
GPU.ai🇺🇸$0.80+33%
Cudo Compute🇬🇧$0.88+46%
Massed Compute🇺🇸$0.88+46%
Seeweb🇮🇹$0.97+61%
Crusoe🇺🇸$1.502.5×
Verda (DataCrunch)🇫🇮$1.532.5×
Nebius🇳🇱$1.552.6×
DigitalOcean🇺🇸$1.572.6×
Vultr🇺🇸$1.672.8×
Scaleway🇫🇷$1.682.8×
OVHcloud🇫🇷$1.803.0×
AWS🇺🇸$1.863.1×
Oracle Cloud🇺🇸$3.505.8×
Thin vertical line = median across providers ($1.50).
Every provider we track
Pricing
Size
Host
Provider HQ
17 providers · 50 configurations
Sort
- 1× GPU43 vCPU · 336 GB RAM · 7,601 GB disk$0.60 /GPU·h$0.60 /hOn-demand🇨🇦 Quebec, CA● availableRent ↗
- 1× GPU64 vCPU · 378 GB RAM · 106 GB disk$0.73 /GPU·h$0.73 /hOn-demand🇨🇿 Czechia, CZ● availableRent ↗
- 1× GPU24 vCPU · 252 GB RAM · 269 GB disk$0.80 /GPU·h$0.80 /hOn-demand🇹🇼 Taiwan, TW● availableRent ↗
- Boost RunOn-demandHQ unknownvia Shadeformfrom · On-demand+15%$0.69/GPU·h
- 8× GPU · PCIe64 vCPU · 1,536 GB RAM · 30,720 GB disk$0.69 /GPU·h$5.52 /hOn-demand🇺🇸 US, Dallas, TX○ sold out
- 1× GPU1 vCPU · 1 GB RAM$0.88 /GPU·h$0.88 /hOn-demandno-kristiansand-1● availableRent ↗
- 1× GPU · PCIe12 vCPU · 72 GB RAM · 625 GB disk$0.88 /GPU·h$0.88 /hOn-demand🇺🇸 US, Des Moines, IA● availableRent ↗
- 4× GPU · PCIe88 vCPU · 288 GB RAM · 2,500 GB disk$0.88 /GPU·h$3.52 /hOn-demand🇺🇸 US, Kansas City, KS● availableRent ↗
- 8× GPU · PCIe142 vCPU · 768 GB RAM · 5,000 GB disk$0.88 /GPU·h$7.04 /hOn-demand🇺🇸 US, Kansas City, KS● availableRent ↗
Alternatives to the L40S
GPUs with similar compute and memory, and their lowest on-demand price right now.
- A100 SXM 40GB40 GB · 0.312 PF FP16$0.54/h$1.71/PFLOP·h
- A100 PCIe 40GB40 GB · 0.312 PF FP16$1.99/h$6.38/PFLOP·h
- A100 SXM 80GB80 GB · 0.312 PF FP16$0.81/h$2.60/PFLOP·h
- A100 PCIe 80GB80 GB · 0.312 PF FP16$1.13/h$3.62/PFLOP·h
- RTX 6000 Ada48 GB · 0.364 PF FP16$0.60/h$1.65/PFLOP·h
Gaudi 296 GB · 0.432 PF FP16$1.10/h$2.55/PFLOP·h
L40S pricing questions
How much does it cost to rent an L40S?
On-demand L40S prices start at $0.60 per GPU-hour (Vast.ai). The median across 17 providers is $1.50, and the most expensive is $3.50. Running one GPU around the clock costs about $440 per month at the lowest price.
Is there cheaper spot or interruptible L40S capacity?
Yes. Spot (interruptible) L40S capacity starts at $0.38 per GPU-hour, 37% below the cheapest on-demand price. Spot instances can be preempted at any time, so use them for checkpointed training or batch jobs.
How much compute do you get per dollar with the L40S?
At $0.60 per hour and 0.362 PF of dense FP16/BF16, the L40S costs $1.66 per PFLOP-hour. That ranks 12 of 70 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the L40S's key specs?
48 GB GDDR6 with 864 GB/s of memory bandwidth, Ada Lovelace architecture (2023), PCIe form factor, 350 W. Dense peak: 0.362 PF FP16 / BF16, 0.733 PF FP8, 0.733 PF INT8, 0.183 PF TF32, 0.0916 PF FP32, 0.0014 PF FP64.
How current are these prices?
Prices were collected on Sep 27, 2026, 01:12 UTC from provider APIs and public catalogs and refresh about every 2 hours. They are indicative list prices; always confirm on the provider's website before booking.