Loading prices…
L40 rental prices
NVIDIA · Ada Lovelace · 48 GB GDDR6 · PCIe · 2022
9 providers · 25 configurations · prices as of Nov 10, 2026, 03:03 UTC
Lowest on-demand
$0.33per GPU·h · ≈ $241/month
at LiumMedian on-demand
$0.86/GPU·h
across 9 providers
Lowest spot
$0.78/GPU·h
Reserved from $0.70
FP16/BF16 cost
$1.82/PFLOP·h
#12 of 74 GPUs for value
Providers
9
25 configurations
Price history
Daily L40 prices per GPU-hour. The shaded period is reconstructed from public archives: the version history of SkyPilot's price catalogs, Internet Archive copies of providers' pricing pages and the open gpu-price-feed project (fewer providers than live data). After that, PetaPrice's own tracking.
Lowest on-demandMedian on-demandLowest spot
Price by provider
Cheapest On-demand L40 offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Lium$0.33best
RunPod🇺🇸$0.692.1×
EmpirioLabs AI🇺🇸$0.702.1×
GPU.ai🇺🇸$0.862.6×
Massed Compute🇺🇸$0.862.6×
Sesterce🇫🇷$0.972.9×
Hyperstack🇬🇧$1.003.0×
Oblivus🇬🇧$1.053.2×
CoreWeave🇺🇸$1.253.8×
Thin vertical line = median across providers ($0.86).
Every provider we track
Pricing
Size
Host
Provider HQ
9 providers · 25 configurations
Sort
- LiumcommunityOn-demandHQ unknownvia Liumfrom · On-demandCheapest$0.33/GPU·hCheapest
- 2× GPU25 vCPU · 142 GB RAM · 1,229 GB disk$0.33 /GPU·h$0.66 /hOn-demand🇺🇸 Des Moines, US● availableRent ↗
- RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demand2.1×$0.69/GPU·h2.1×
- EmpirioLabs AIOn-demand🇺🇸 HQ in United Statesvia EmpirioLabs APIfrom · On-demand2.1×$0.70/GPU·h2.1×
- GPU.aiOn-demand🇺🇸 HQ in United Statesvia GPU.aifrom · On-demand2.6×$0.86/GPU·h2.6×
- Massed ComputeOn-demand🇺🇸 HQ in United Statesvia Massed Compute pricing pagefrom · On-demand2.6×$0.86/GPU·h2.6×
- SesterceOn-demand🇫🇷 HQ in Francevia Sestercefrom · On-demand2.9×$0.97/GPU·h2.9×
- HyperstackOn-demandReservedSpot🇬🇧 HQ in United Kingdomvia Hyperstack pricing pagefrom · On-demand3.0×$1.00/GPU·h3.0×
- OblivusOn-demandReserved🇬🇧 HQ in United Kingdomvia Oblivus pricing pagefrom · On-demand3.2×$1.05/GPU·h3.2×
What can the L40 run?
Memory for the weights plus one 32K-token sequence of context, how many GPUs hold it, and what that replica costs at the cheapest in-stock on-demand rate.
| Model | Params | Memory | GPUs | $/hr | $/mo |
|---|---|---|---|---|---|
gpt-oss-20b OpenAI · 20.9B | 20.9B · 3.6B active | 20 GiB | 1 | $0.33 at Lium | $241 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 1 | $0.33 at Lium | $241 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 1 | $0.33 at Lium | $241 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 2 | $0.66 at Lium | $482 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 4 | $1.32 at Lium | $964 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 8 | $2.64 at Lium | $1,927 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 16 | $5.28 at Lium | $3,854 |
Kimi K3 Moonshot AI · 2.78T | 2.78T · 104B active | 2.53 TiB | 64 | $21.12 at Lium | $15,418 |
Assumes 90% of each GPU's memory is usable and rounds up to 1, 2, 4, 8… GPUs for tensor parallelism (up to 64). $/hr is the GPU count times the cheapest in-stock on-demand rate per GPU; check that the provider rents instances that large. Serving many requests at once needs more memory for context.
Alternatives to the L40
GPUs with similar compute and memory, and their lowest on-demand price right now.
L40 pricing questions
How much does it cost to rent an L40?
On-demand L40 prices start at $0.33 per GPU-hour (Lium). The median across 9 providers is $0.86, and the most expensive is $1.25. Running one GPU around the clock costs about $241 per month at the lowest price.
Is there cheaper spot or interruptible L40 capacity?
Yes. Spot (interruptible) L40 capacity starts at $0.78 per GPU-hour, -137% 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 L40?
At $0.33 per hour and 0.181 PF of dense FP16/BF16, the L40 costs $1.82 per PFLOP-hour. That ranks 12 of 74 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the L40's key specs?
48 GB GDDR6 with 864 GB/s of memory bandwidth, Ada Lovelace architecture (2022), PCIe form factor, 300 W. Dense peak: 0.181 PF FP16 / BF16, 0.362 PF FP8, 0.362 PF INT8, 0.0905 PF TF32, 0.0905 PF FP32, 0.0014 PF FP64.
How current are these prices?
Prices were collected on Nov 10, 2026, 03:03 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.