NVIDIA L4 rental pricing
Ada Lovelace architecture · 24 GB memory · 0.3 TB/s bandwidth · 72 W board power · Released 2023
Price history by provider
Every provider's cheapest daily on-demand rate for the NVIDIA L4, 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 3h ago- Cheapest in stock
- $0.36/hr
- Community · 2× L4 24GB · Vast.ai
- Median price
- $0.80/hr
- On-demand · 9 providers
- 90-day trend
- Flat
- Weekly median on-demand, 4 weeks
- Coverage
- 10 providers
- 18 price points
- $ per FP8 PFLOP-hour
- $2.43
- Rank 25 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 | |
|---|---|---|---|---|
| 2× L4 24GB Community | $0.36 | 3h ago | View → | |
| 1× L4 24GB Community | $0.44 | 3h ago | View → | |
| 1× L4 24GB | $0.59 | 3h ago | View → | |
| 1× L4 24GB | $0.66 | 3h ago | View → | |
 Koyeb | 1× L4 24GB | $0.70 | 3h ago | View → |
| 1× L4 24GB | $0.80 | 22d ago | View → | |
 Cerebrium | 1× L4 24GB | $0.80 | 3h ago | View → |
| 1× L4 24GB | $0.80 | 3h ago | View → | |
| 1× L4 24GB | $0.85 | 3h ago | View → | |
| 1× L4 24GB | $0.88 | 3h ago | View → | |
| 2× L4 24GB | $1.00 | 3h 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 L4 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 | $0.59 |
| Gemma 3 27B Google | 27.4B | 26 GiB | 2 | $1.18 |
| Qwen3-32B Alibaba | 32.8B | 32 GiB | 2 | $1.18 |
| Llama 3.3 70B Instruct Meta | 70.6B | 67 GiB | 4 | $2.36 |
| gpt-oss-120b OpenAI | 117B· 5.1B active | 109 GiB | 8 | $4.72 |
| Qwen3-235B-A22B Alibaba | 235B· 22.0B active | 220 GiB | 16 | $9.44 |
| DeepSeek-R1 DeepSeek | 684B· 37.0B active | 638 GiB | Over 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 L4 pricing questions
How much does it cost to rent a NVIDIA L4 per hour?
The cheapest NVIDIA L4 in stock right now is $0.36 per GPU-hour community from Vast.ai for the 2× L4 24GB configuration. The median on-demand rate across 9 providers is $0.80 per GPU-hour.
How much does a NVIDIA L4 cost per month?
Running one NVIDIA L4 around the clock for a month (730 hours) costs about $263 at the cheapest in-stock rate of $0.36 per hour. At the median on-demand rate it is about $583 a month. Reserved terms usually come in below that; ask the provider for a quote.
Which provider has the cheapest NVIDIA L4?
Vast.ai has the cheapest NVIDIA L4 in stock right now at $0.36 per GPU-hour community for the 2× L4 24GB 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 L4 rental prices going up or down?
The weekly median on-demand rate for the NVIDIA L4 has been flat, moving 0.0% over the last 4 weeks, from $0.80 to $0.80 per GPU-hour.
What is the difference between on-demand, spot and reserved NVIDIA L4 pricing?
On-demand is pay-as-you-go with no commitment. Community is capacity from individual hosts on a marketplace, cheaper and less uniform. This week's median rates for the NVIDIA L4 are on-demand $0.80 (9 providers), community $0.40 (2 providers), per GPU-hour.
How many cloud providers rent the NVIDIA L4?
We track 10 providers with 18 live prices for the NVIDIA L4. 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 L4?
With 8-bit weights and a single sequence of context, one NVIDIA L4 holds gpt-oss-20b (20.9B). See the model fit table for the full ladder.
How does the NVIDIA L4 compare on price per PFLOP-hour?
At its cheapest in-stock on-demand rate the NVIDIA L4 delivers dense FP8 compute at $2.43 per PFLOP-hour, which ranks 25 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 L4 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 3h ago.