How much does the L4 cost per hour?

As of September 8, 2026, the median on-demand price is $0.90 per GPU per hour across 15 providers with a priced on-demand config. On-demand: 72 configs, median $0.90, cheapest $0.27 (in stock, GPU.ai) Reserved: 63 configs, median $0.52, cheapest $0.27 (3 mo, in stock, Vast.ai) Spot: 24 configs, median $0.48, cheapest $0.14 (in stock, Vast.ai)

Who has the cheapest L4?

As of September 8, 2026, the cheapest verified in-stock on-demand L4 tracked by GetDeploying is $0.27 per GPU per hour from GPU.ai. Cheapest verified in stock on other billing types: reserved $0.27 (3 mo) and spot $0.14, both from Vast.ai.

How much does the L4 cost per month?

As of September 8, 2026, at 720 hours per month, one L4 costs an estimated $648 at the median on-demand price. Cheapest verified in stock: $194 per month on-demand, $194 reserved (3 mo), $101 spot.

Where can I rent an L4?

GetDeploying currently tracks L4 configs from 18 providers. The cheapest verified in-stock on-demand configs come from GPU.ai, Vast.ai, UpCloud and Scaleway. See the full price comparison above for every provider and config.

Are L4 prices going up or down?

As of September 8, 2026, the median on-demand price has been flat over the past 90 days, at about $0.90 per GPU per hour, though it is about 7% below where it was a year ago.

How many L4 GPUs do I need?

One L4 runs models up to roughly 28B parameters at 4-bit quantization or 6B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.

24GB GDDR6 in a low-power 72W form factor. FP8 support for efficient inference. Excellent performance-per-watt for deploying AI models at scale in cost-sensitive environments.

When is the L4 not a good fit?

Limited VRAM caps model sizes at ~13B parameters (FP16). Built for inference, not training. Low memory bandwidth (300 GB/s) may limit throughput on memory-bound workloads.

Nvidia L4

Low-power inference accelerator for cost-sensitive cloud deployments.

Jump to: At a glance Pricing AI models Specs FAQ Alternatives

Compare vs other GPUs →

Aggregating historical prices...

Weekly median price per GPU per hour. Nvidia L4 price history (JSON).

At a glance

Hardware

Architecture: Ada Lovelace
Memory per GPU: 24 GB GDDR6
Memory bandwidth: 300 GB/s
Release date: Q1 2023

Market Updated 11 minutes ago

Cheapest in stock: $0.27 / GPU / hr; on-demand · 1x · GPU.ai
Median price: $0.90 / GPU / hr; on-demand
90-day trend: Flat; median on-demand
Coverage: 18 providers; 46 of 159 configs in stock

L4 Pricing and Availability

18 providers

How this list works

The two views

By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.

Order

What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.

Within a group, five factors set the order:

Location: datacenter proximity, blended with provider HQ.
Price: hourly price, per GPU and in total.
Billing type: reserved ahead of spot, spot ahead of quote-only.
Specs: more VRAM, vCPUs and RAM.
Provider diversity: a provider's repeat rows rank slightly lower, so one company can't take all the top spots.

Search

We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.

Transparency and funding

Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.

Runpod

Our sponsor

USA 2 configs 1x-8x checked <15m ago

On-Demand from $0.49 Reserved on request

Pricing On request Reservation Visit website


1x L4 Secure Cloud	24GB	4	24GB	On-Demand	$0.49	$0.49	Out of stock
8x L4 Secure Cloud	192GB	32	192GB	Reservation	Custom	Custom	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T05:15Z. Not reported means we could not confirm availability.

Vast.ai

In stock

USA 13 configs 1x-5x checked <15m ago

On-Demand from $0.31 Reserved from $0.27 Spot from $0.14

From $0.31 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x L4 CZ	24GB	20	63GB	Spot	$0.14	$0.14	In stock
1x L4 CZ	24GB	20	63GB	Reserved (3mo)	$0.27	$0.27	In stock
1x L4 US	24GB	16	46GB	On-Demand	$0.31	$0.31	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T05:17Z. Not reported means we could not confirm availability.

Loading 10 more configs...

Runcrate

In stock

USA 1 config 1x checked <1h ago

On-Demand from $1.05

From $1.05 / GPU / hr On-Demand PCIe Visit website


1x L4 PCIe	24GB	8	48GB	On-Demand	$1.05	$1.05	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T04:40Z. Not reported means we could not confirm availability.

UpCloud

In stock

Finland 22 configs 1x-3x checked <1h ago

On-Demand from $0.69 Spot from $0.68

From $0.69 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x L4 GPU-SPOT-8xCPU-64GB-1xL4	24GB	8	64GB	Spot	$0.68	$0.68	In stock
1x L4 GPU-8xCPU-64GB-1xL4	24GB	8	64GB	On-Demand	$0.69	$0.69	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T04:40Z. Not reported means we could not confirm availability.

Loading 20 more configs...

Scaleway

In stock

France 4 configs 1x-8x checked <1h ago

On-Demand from $0.92

From $0.92 / GPU / hr On-Demand Visit website


1x L4 L4-1-24G	24GB	8	48GB	On-Demand	$0.92	$0.92	In stock
2x L4 L4-2-24G	48GB	16	96GB	On-Demand	$0.92	$1.83	In stock
4x L4 L4-4-24G	96GB	32	192GB	On-Demand	$0.92	$3.66	In stock
8x L4 L4-8-24G	192GB	64	384GB	On-Demand	$0.92	$7.32	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T04:40Z. Not reported means we could not confirm availability.

Sesterce

In stock

France 4 configs 1x-8x checked <15m ago

On-Demand from $1.04

From $1.04 / GPU / hr On-Demand Visit website


1x L4	24GB	8	48GB	On-Demand	$1.04	$1.04	In stock
2x L4	48GB	16	96GB	On-Demand	$1.04	$2.09	In stock
4x L4	96GB	32	192GB	On-Demand	$1.04	$4.18	In stock
8x L4	192GB	64	384GB	On-Demand	$1.04	$8.36	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T05:15Z. Not reported means we could not confirm availability.

GPU.ai

In stock

UAE 2 configs 1x-2x checked <15m ago

On-Demand from $0.27

From $0.27 / GPU / hr On-Demand Visit website


1x L4	24GB	--	--	On-Demand	$0.27	$0.27	In stock
2x L4	48GB	--	--	On-Demand	$0.34	$0.67	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T05:15Z. Not reported means we could not confirm availability.

Hexabyte

Waitlist

Sweden 4 configs 1x-2x checked 1 week ago

On-Demand from $0.42

From $0.42 / GPU / hr On-Demand Visit website


1x L4 l4.gpu1	24GB	4	16GB	On-Demand	$0.42	$0.42	Waitlist
1x L4 l4.gpu2	24GB	8	32GB	On-Demand	$0.45	$0.45	Waitlist
1x L4 l4.gpu3	24GB	16	64GB	On-Demand	$0.51	$0.51	Waitlist
2x L4 l4.dual-gpu	48GB	32	128GB	On-Demand	$0.56	$1.13	Waitlist

In-stock and out-of-stock as of our last check at 2026-08-31T19:19Z. Not reported means we could not confirm availability.

Koyeb

Waitlist

France 1 config 1x checked <1h ago

On-Demand from $0.70

From $0.70 / GPU / hr On-Demand Visit website


1x L4 gpu-nvidia-l4	24GB	6	32GB	On-Demand	$0.70	$0.70	Waitlist

In-stock and out-of-stock as of our last check at 2026-09-08T04:40Z. Not reported means we could not confirm availability.

Cerebrium

USA 4 configs 1x-8x checked <24h ago

On-Demand from $0.80

From $0.80 / GPU / hr On-Demand Visit website


1x L4 ADA_L4	24GB	--	--	On-Demand	$0.80	$0.80	Not reported
2x L4 ADA_L4	48GB	--	--	On-Demand	$0.80	$1.60	Not reported
4x L4 ADA_L4	96GB	--	--	On-Demand	$0.80	$3.20	Not reported
8x L4 ADA_L4	192GB	--	--	On-Demand	$0.80	$6.39	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T09:43Z. Not reported means we could not confirm availability.

Google Cloud

USA 32 configs 1x-8x checked <24h ago

On-Demand from $0.70 Reserved from $0.32 Spot from $0.34

From $0.70 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x L4 g2-standard-4	24GB	4	16GB	Reserved (36mo)	$0.32	$0.32	Not reported
1x L4 g2-standard-4	24GB	4	16GB	Spot	$0.34	$0.34	Not reported
1x L4 g2-standard-4	24GB	4	16GB	On-Demand	$0.70	$0.70	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T09:46Z. Not reported means we could not confirm availability.

Loading 29 more configs...

Hugging Face

USA 2 configs 1x-4x checked <24h ago

On-Demand from $0.80

From $0.80 / GPU / hr On-Demand Visit website


1x L4 l4x1	24GB	8	30GB	On-Demand	$0.80	$0.80	Not reported
4x L4 l4x4	96GB	48	186GB	On-Demand	$0.95	$3.80	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T09:46Z. Not reported means we could not confirm availability.

AWS

USA 30 configs 1x-8x checked <24h ago

On-Demand from $0.80 Reserved from $0.37

From $0.80 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x L4 g6.xlarge	24GB	4	16GB	Reserved (36mo)	$0.37	$0.37	Not reported
1x L4 g6.xlarge	24GB	4	16GB	On-Demand	$0.80	$0.80	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T09:43Z. Not reported means we could not confirm availability.

Loading 28 more configs...

OVH

France 3 configs 1x-4x checked <24h ago

On-Demand from $1.00

From $1.00 / GPU / hr On-Demand Visit website


1x L4 l4-90	24GB	22	90GB	On-Demand	$1.00	$1.00	Not reported
2x L4 l4-180	48GB	45	180GB	On-Demand	$1.00	$2.00	Not reported
4x L4 l4-360	96GB	90	360GB	On-Demand	$1.00	$4.00	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T09:47Z. Not reported means we could not confirm availability.

Leaseweb

Netherlands 18 configs 1x-4x checked <24h ago

On-Demand from $0.45 Reserved from $0.42

From $0.45 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x L4 PREMIUM_R7525-16SFF8NVME-7413-L4	24GB	48	128GB	Reserved (1mo)	$0.42	$0.42	Not reported
1x L4 LSW.G6.XLARGE	24GB	4	16GB	On-Demand	$0.45	$0.45	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T09:47Z. Not reported means we could not confirm availability.

Loading 16 more configs...

Elastx

Sweden 1 config 1x checked 1 week ago

On-Demand from $1.03

From $1.03 / GPU / hr On-Demand Visit website


1x L4 g2-c6-m90-d800-g24	24GB	6	90GB	On-Demand	$1.03	$1.03	Not reported

In-stock and out-of-stock as of our last check at 2026-08-31T22:15Z. Not reported means we could not confirm availability.

Utho

India 1 config 1x checked <24h ago

Reserved from $0.33

From $0.33 / GPU / hr Reserved (36mo) Visit website


1x L4	24GB	8	32GB	Reserved (36mo)	$0.33	$0.33	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T16:06Z. Not reported means we could not confirm availability.

AceCloud

India 15 configs 1x-4x checked <24h ago

Reserved from $0.60

From $0.60 / GPU / hr Reserved (12mo) Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x L4 N.L4.32	24GB	8	32GB	Reserved (12mo)	$0.60	$0.60	Not reported

Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.

What size AI models can the L4 run?

One L4 has 24 GB of VRAM. In practice, that's enough memory for roughly 28B parameters at 4-bit or 6B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.

Model	Parameters	4-bitINT4 / FP4	8-bitFP8 / INT8	16-bitFP16 / BF16
Qwen3.8-27B	27B	1 GPU 18 GB VRAM · $648/mo	2 GPUs 30 GB VRAM · $1,296/mo	4 GPUs 58 GB VRAM · $2,592/mo
Gemma 4 31B	30.7B	1 GPU 22 GB VRAM · $648/mo	2 GPUs 35 GB VRAM · $1,296/mo	4 GPUs 69 GB VRAM · $2,592/mo
GPT-OSS-120B	117B 5.1B active	4 GPUs 67 GB VRAM · $2,592/mo	8 GPUs 120 GB VRAM · $5,184/mo	11 GPUs 237 GB VRAM
DeepSeek V4 Flash	284B 13B active	8 GPUs 160 GB VRAM · $5,184/mo	14 GPUs 287 GB VRAM	27 GPUs 573 GB VRAM
GLM-5.3-Flash	320B 18B active	9 GPUs 178 GB VRAM	15 GPUs 322 GB VRAM	30 GPUs 642 GB VRAM
MiniMax-M3	428B 23B active	12 GPUs 239 GB VRAM	20 GPUs 432 GB VRAM	40 GPUs 862 GB VRAM
Kimi K3	2.8T 104B active	72 GPUs 1,544 GB VRAM	130 GPUs 2,804 GB VRAM	260 GPUs 5,605 GB VRAM

Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Technical Specifications

Nvidia L4 · Per GPU

Compute · dense
FP8	242 TFLOPS 485 with sparsity
FP16 / BF16	121 TFLOPS 242 with sparsity
INT8	242 TOPS 485 with sparsity
FP32	30.3 TFLOPS
Precision support	FP8FP16BF16TF32FP32INT4INT8

Memory
Capacity	24 GB GDDR6
Bandwidth	300 GB/s
Bus width	192-bit
ECC	Yes

Silicon
Architecture	Ada Lovelace
Process	TSMC 4N
Shader cores	7,424 CUDA cores
Matrix cores	232 Tensor cores
Compute units	58 SMs

Fabric and host
Host interface	PCIe 4.0 x16

Power
Board power	72 W
Cooling	Passive

Source: official Nvidia L4 datasheet.

Thunder Compute

Our sponsor

NVIDIA H100 from $1.38/hr, A100 80GB from $0.78/hr, RTX A6000 from $0.27/hr

No commitments, billed per minute, SOC 2 and GDPR compliant

Hot swappable hardware, templates for ComfyUI and Ollama

One-click connection to VS Code or Cursor, simple CLI to connect without SSH

Try now

Frequently Asked Questions

How much does the L4 cost per hour?: As of September 8, 2026, the median on-demand price is $0.90 per GPU per hour across 15 providers with a priced on-demand config.

Billing type Configs Median / GPU / hr Cheapest

On-demand 72 $0.90 $0.27 (in stock, GPU.ai)

Reserved 63 $0.52 $0.27 (3 mo, in stock, Vast.ai)

Spot 24 $0.48 $0.14 (in stock, Vast.ai)
Who has the cheapest L4?: As of September 8, 2026, the cheapest verified in-stock on-demand L4 tracked by GetDeploying is $0.27 per GPU per hour from GPU.ai. Cheapest verified in stock on other billing types: reserved $0.27 (3 mo) and spot $0.14, both from Vast.ai.
How much does the L4 cost per month?: As of September 8, 2026, at 720 hours per month, one L4 costs an estimated $648 at the median on-demand price. Cheapest verified in stock: $194 per month on-demand, $194 reserved (3 mo), $101 spot.
Where can I rent an L4?: GetDeploying currently tracks L4 configs from 18 providers. The cheapest verified in-stock on-demand configs come from GPU.ai, Vast.ai, UpCloud and Scaleway. See the full price comparison above for every provider and config.
Are L4 prices going up or down?: As of September 8, 2026, the median on-demand price has been flat over the past 90 days, at about $0.90 per GPU per hour, though it is about 7% below where it was a year ago.
How many L4 GPUs do I need?: One L4 runs models up to roughly 28B parameters at 4-bit quantization or 6B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
Why choose the L4?: 24GB GDDR6 in a low-power 72W form factor. FP8 support for efficient inference. Excellent performance-per-watt for deploying AI models at scale in cost-sensitive environments.
When is the L4 not a good fit?: Limited VRAM caps model sizes at ~13B parameters (FP16). Built for inference, not training. Low memory bandwidth (300 GB/s) may limit throughput on memory-bound workloads.

Billing type	Configs	Median / GPU / hr	Cheapest
On-demand	72	$0.90	$0.27 (in stock, GPU.ai)
Reserved	63	$0.52	$0.27 (3 mo, in stock, Vast.ai)
Spot	24	$0.48	$0.14 (in stock, Vast.ai)

Alternatives to Nvidia L4

Browse all GPUs

Last updated Sept. 8, 2026

At a glance

Hardware

Market Updated 11 minutes ago

L4 Pricing and Availability

How this list works

The two views

Order

Search

Transparency and funding

What size AI models can the L4 run?

Technical Specifications

Frequently Asked Questions

How much does the L4 cost per hour?

Who has the cheapest L4?

How much does the L4 cost per month?

Where can I rent an L4?

Are L4 prices going up or down?

How many L4 GPUs do I need?

Why choose the L4?

When is the L4 not a good fit?

Alternatives to Nvidia L4

Nvidia T4

Nvidia A10

Nvidia L40