NVIDIA L40 rental pricing
Ada Lovelace architecture · 48 GB GDDR6 memory · 0.9 TB/s bandwidth · 300 W board power · Released 2023
Price history by provider
Every provider's cheapest daily on-demand rate for the NVIDIA L40, last 30 days
One line per provider, reconstructed from recorded price changes for listings currently live. Click a name in the key to hide or show it.
At a glance
prices checked just now- Cheapest in stock
- $0.46/hr
- Community · 1× L40 48GB · Vast.ai
- Median price
- $0.88/hr
- On-demand · 7 providers
- 90-day trend
- Flat
- Weekly median on-demand, 4 weeks
- Coverage
- 8 providers
- 16 price points
- $ per FP8 PFLOP-hour
- $2.15
- Rank 23 of 30 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× L40 48GB Community | $0.46 | just now | View → | |
| 1× L40 48GB Community | $0.69 | just now | View → | |
 Oblivus | 1× L40 48GB Reserved | $0.74 | just now | View → |
 GPU.ai | 1× L40 48GB | $0.78 | just now | View → |
| 8× L40 48GB Spot | $0.78 | just now | View → | |
 Thunder Compute | 1× L40 48GB | $0.79 | 24d ago | View → |
| 1× L40 48GB Spot | $0.80 | just now | View → | |
| 1× L40 48GB | $0.82 | just now | View → | |
 Shadeform Massed Compute capacity | 1× L40 48GB | $0.88 | just now | View → |
| 1× L40 48GB | $1.00 | just now | View → | |
| Oblivus | 1× L40 48GB | $1.05 | just now | View → |
| 8× L40 48GB | $1.25 | just now | 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 L40 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 | $0.78 |
| Gemma 3 27B Google | 27.4B | 26 GiB | 1 | $0.78 |
| Qwen3-32B Alibaba | 32.8B | 32 GiB | 1 | $0.78 |
| Llama 3.3 70B Instruct Meta | 70.6B | 67 GiB | 2 | $1.56 |
| gpt-oss-120b OpenAI | 117B· 5.1B active | 109 GiB | 4 | $3.12 |
| Qwen3-235B-A22B Alibaba | 235B· 22.0B active | 220 GiB | 8 | $6.24 |
| DeepSeek-R1 DeepSeek | 684B· 37.0B active | 638 GiB | 16 | $12.48 |
| 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 L40 pricing questions
How much does it cost to rent a NVIDIA L40 per hour?
The cheapest NVIDIA L40 in stock right now is $0.46 per GPU-hour community from Vast.ai for the 1× L40 48GB configuration. The median on-demand rate across 7 providers is $0.88 per GPU-hour.
How much does a NVIDIA L40 cost per month?
Running one NVIDIA L40 around the clock for a month (730 hours) costs about $334 at the cheapest in-stock rate of $0.46 per hour. At the median on-demand rate it is about $642 a month. Reserved terms usually come in below that; ask the provider for a quote.
Which provider has the cheapest NVIDIA L40?
Vast.ai has the cheapest NVIDIA L40 in stock right now at $0.46 per GPU-hour community for the 1× L40 48GB configuration. That is a community rate; see the provider table for the cheapest on-demand listing. Rates change often, so check the provider table for today's figure before you commit.
Are NVIDIA L40 rental prices going up or down?
The weekly median on-demand rate for the NVIDIA L40 has been flat, moving 0.0% over the last 4 weeks, from $0.88 to $0.88 per GPU-hour.
What is the difference between on-demand, spot and reserved NVIDIA L40 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 L40 are on-demand $0.88 (7 providers), spot $0.79 (2 providers), reserved $0.74 (1 provider), community $0.59 (2 providers), per GPU-hour.
How many cloud providers rent the NVIDIA L40?
We track 8 providers with 16 live prices for the NVIDIA L40. 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 L40?
With 8-bit weights and a single sequence of context, one NVIDIA L40 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 L40 compare on price per PFLOP-hour?
At its cheapest in-stock on-demand rate the NVIDIA L40 delivers dense FP8 compute at $2.15 per PFLOP-hour, which ranks 23 of 30 priced GPUs we cover on that basis. Lower is better: it is the rental price divided by peak FP8 throughput.
Where does this NVIDIA L40 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 just now.