NVIDIA L40S rental pricing
Ada Lovelace architecture · 48 GB memory · 0.9 TB/s bandwidth · 350 W board power · Released 2023
Price history
Weekly median price per GPU per hour
At a glance
prices checked 5h ago- Cheapest in stock
- $0.76/hr
- On-demand · 1× L40S 48GB · Sesterce
- Median price
- $1.50/hr
- On-demand · 23 providers
- 90-day trend
- Flat
- Weekly median on-demand, 4 weeks
- Coverage
- 24 providers
- 41 price points
- $ per FP8 PFLOP-hour
- $1.04
- Rank 8 of 31 priced GPUs · lower is better
Every provider we track
Cheapest listing per provider and pricing type. Sold-out rows stay so you can see who normally carries it.
| Provider | Configuration | Price/GPU-hr | Checked | |
|---|---|---|---|---|
| 1× L40S 48GB | $0.76 | 8d ago | View → | |
Beam | 1× L40S 48GB | $0.76 | 5h ago | View → |
| 1× L40S 48GB Community | $0.79 | 5h ago | View → | |
GPU.ai | 1× L40S 48GB Community | $0.79 | 5h ago | View → |
GPU.ai | 1× L40S 48GB | $0.80 | 5h ago | View → |
| 4× L40S 48GB Community | $0.80 | 5h ago | View → | |
| 1× L40S 48GB Spot | $0.86 | 5h ago | View → | |
| 1× L40S 48GB | $0.87 | 5h ago | View → | |
Shadeform Massed Compute capacity | 1× L40S 48GB | $0.88 | 5h ago | View → |
Civo | 1× L40S 48GB Reserved | $0.89 | 5h ago | View → |
Spheron | 1× L40S 48GB | $0.96 | 5h ago | View → |
| 8× L40S 48GB Spot | $0.98 | 5h ago | View → | |
| 1× L40S 48GB | $1.09 | 5h ago | View → | |
Lyceum | 1× L40S 48GB | $1.19 | 11d ago | View → |
Koyeb | 1× L40S 48GB | $1.20 | 5h ago | View → |
Civo | 1× L40S 48GB | $1.29 | 5h ago | View → |
Gcore | 1× L40S 48GB | $1.43 | 5h ago | View → |
| 1× L40S 48GB | $1.50 | 5h ago | View → | |
| 1× L40S 48GB | $1.50 | 5h ago | View → | |
| 1× L40S 48GB | $1.55 | 4d ago | View → | |
| 1× L40S 48GB | $1.57 | 5h ago | View → | |
| 1× L40S 48GB | $1.67 | 5h ago | View → | |
| 1× L40S 48GB | $1.72 | 5h ago | View → | |
| 4× L40S 48GB | $1.80 | 5h ago | View → | |
| 1× L40S 48GB | $1.86 | 5h ago | View → | |
| 1× L40S 48GB | $1.95 | 15d ago | View → | |
Cerebrium | 1× L40S 48GB | $1.95 | 5h ago | View → |
| 8× L40S 48GB | $2.25 | 5h ago | View → | |
Replicate | 1× L40S 48GB | $3.51 | 5h ago | View → |
Replicate | 4× L40S 48GB Reserved | $3.51 | 5h ago | View → |
Per GPU-hour. Spot, reserved and community pricing differ from on-demand; click through for the provider's current figure.
What can the NVIDIA L40S run?
Memory for the weights plus one 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 |
|---|---|---|---|---|
| gpt-oss-20b OpenAI | 20.9B· 3.6B active | 20 GiB | 1 | $0.76 |
| Gemma 3 27B Google | 27.4B | 26 GiB | 1 | $0.76 |
| Qwen3-32B Alibaba | 32.8B | 32 GiB | 1 | $0.76 |
| Llama 3.3 70B Instruct Meta | 70.6B | 67 GiB | 2 | $1.52 |
| gpt-oss-120b OpenAI | 117B· 5.1B active | 109 GiB | 4 | $3.04 |
| Qwen3-235B-A22B Alibaba | 235B· 22.0B active | 220 GiB | 8 | $6.08 |
| DeepSeek-R1 DeepSeek | 684B· 37.0B active | 638 GiB | 16 | $12.16 |
| Kimi K3 Moonshot AI | 2.78T· 104B active | 2.53 TiB | Over 16 | — |
Sized for one sequence at 4K context with 16-bit KV cache and 10% of memory held back. Serving many users at once needs more; the LLM GPU calculator sizes for concurrency and throughput.
NVIDIA L40S pricing questions
How much does it cost to rent a NVIDIA L40S per hour?
The cheapest NVIDIA L40S in stock right now is $0.76 per GPU-hour on-demand from Sesterce for the 1× L40S 48GB configuration. The median on-demand rate across 23 providers is $1.50 per GPU-hour.
How much does a NVIDIA L40S cost per month?
Running one NVIDIA L40S around the clock for a month (730 hours) costs about $555 at the cheapest in-stock rate of $0.76 per hour. At the median on-demand rate it is about $1,092 a month. Reserved terms usually come in below that; ask the provider for a quote.
Which provider has the cheapest NVIDIA L40S?
Sesterce has the cheapest NVIDIA L40S in stock right now at $0.76 per GPU-hour on-demand for the 1× L40S 48GB configuration. Rates change often, so check the provider table for today's figure before you commit.
Are NVIDIA L40S rental prices going up or down?
The weekly median on-demand rate for the NVIDIA L40S has been flat, moving 1.9% over the last 4 weeks, from $1.53 to $1.50 per GPU-hour.
What is the difference between on-demand, spot and reserved NVIDIA L40S pricing?
On-demand is pay-as-you-go with no commitment. Spot is spare capacity sold at a discount that the provider can reclaim at short notice. Reserved is a committed term, usually months, in exchange for a lower rate. Community is capacity from individual hosts on a marketplace, cheaper and less uniform. This week's median rates for the NVIDIA L40S are on-demand $1.50 (23 providers), spot $0.91 (2 providers), reserved $2.20 (2 providers), community $0.79 (3 providers), per GPU-hour.
How many cloud providers rent the NVIDIA L40S?
We track 24 providers with 41 live prices for the NVIDIA L40S. Sold-out listings stay in the table so you can see who normally carries it, but never set the cheapest figure.
What LLMs can you run on one NVIDIA L40S?
With 8-bit weights and a single sequence of context, one NVIDIA L40S holds gpt-oss-20b (20.9B), Gemma 3 27B (27.4B), Qwen3-32B (32.8B). See the model fit table for the full ladder.
How does the NVIDIA L40S compare on price per PFLOP-hour?
At its cheapest in-stock on-demand rate the NVIDIA L40S delivers dense FP8 compute at $1.04 per PFLOP-hour, which ranks 8 of 31 priced GPUs we cover on that basis. Lower is better: it is the rental price divided by peak FP8 throughput.
Where does this NVIDIA L40S pricing data come from?
Prices are read daily from each provider's public price list or API and recorded whenever they change. Listings are shown per GPU-hour on-demand unless marked otherwise, and the chart covers the last 30 days. The newest listing was checked 5h ago.