GPU Rental Prices
SearchCtrl K

L4 rental price: from $0.44/hr

The cheapest on-demand L4 is $0.44 an hour at Jarvislabs, checked 21 November 2026; the typical provider charges $0.69.

Cheapest on-demand · 24 GB · checked 21 November 2026$0.44/GPU-hourJarvislabs
  • Spot $0.10 AWS, interruptible
  • Serverless $0.70 Koyeb, per second
  • Provider median $0.69
  • Highest on-demand $1.67
  • 15 offers
  • 11 providers
  • Cheapest the same as 90 days ago
  • Same offers, 90 days: +12.1%
  • Source jarvislabs.ai

L4 offers: 15 configurations from 11 providers

More filters: provider, memory, node size, stock, place, CPU and RAM, sort, price unit

“Machines in” filters the 7 of 15 offers whose provider says where the machine is; the others are under “Place not stated”.

“vCPUs per GPU” and “RAM per GPU” use the 5 of 15 offers whose provider publishes the machine's vCPUs or RAM for a stated number of GPUs (AWS and RunPod); an offer that does not publish them never matches a minimum. A GiB counts as 1.07 GB.

15 offers; rates are per GPU and the node total is for the smallest listed node.

7 providers with on-demand offers, fresh prices first, then cheapest; out-of-stock offers last. Tap a provider for its configurations.

GPU / providerBilling$/GPU-hourNode · total per hourRent
L4 · Jarvislabs24 GBon-demand$0.44–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

L4 · Google Cloud24 GBon-demand$0.56–Rent →
checked 21 NovDetails
Region
US Central (Iowa)
Checked
21 November 2026
Credit offer
$300 welcome credit (90 days) · eligibility applies; checked 2026-10-31

Source price ↗ · Report this price

L4 · Runcrate24 GB · L4; lowest live rate; billed per secondon-demandStarting rate$0.58–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

L4 · AWS24 GB · g6.xlargeon-demand$0.801× $0.80Rent →
checked 21 NovDetails
CPU
4 vCPU
RAM
16 GiB
Disk
1 x 250 GB NVMe SSD
Region
US East (N. Virginia)
Checked
21 November 2026
Credit offer
Up to $200 credits for new customers (6 months) · eligibility applies; checked 2026-10-31

Source price ↗ · Report this price

L4 · Scaleway24 GBon-demand$0.87−2.2% in 30 days–Rent →
checked 21 NovDetails
Region
Paris, France
Checked
21 November 2026

Source price ↗ · Report this price

L4 · OVHcloud24 GBon-demand$1.001× $1.00Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

L4 · AWS24 GB · g6.48xlargeon-demand$1.678× $13.35Rent →
checked 21 NovDetails
CPU
192 vCPU for 8 GPUs (24 per GPU)
RAM
768 GiB for 8 GPUs (96 GiB per GPU)
Disk
8 x 940 NVMe SSD
Region
US East (N. Virginia)
Checked
21 November 2026
Credit offer
Up to $200 credits for new customers (6 months) · eligibility applies; checked 2026-10-31

Source price ↗ · Report this price

L4 · RunPod24 GBsecure cloud$0.69+16.9% in 30 days–Out of stock
checked 21 NovDetails
CPU
12 vCPU
RAM
50 GB RAM
Checked
21 November 2026

Source price ↗ · Report this price

L4 · AWS24 GB · g6.xlargespot / interruptible$0.101× $0.10Rent →
checked 21 NovDetails
CPU
4 vCPU
RAM
16 GiB
Disk
1 x 250 GB NVMe SSD
Region
US East (N. Virginia)
Checked
21 November 2026
Credit offer
Up to $200 credits for new customers (6 months) · eligibility applies; checked 2026-10-31

Source price ↗ · Report this price

L4 · AWS24 GB · g6.48xlargespot / interruptible$0.228× $1.76Rent →
checked 21 NovDetails
CPU
192 vCPU for 8 GPUs (24 per GPU)
RAM
768 GiB for 8 GPUs (96 GiB per GPU)
Disk
8 x 940 NVMe SSD
Region
US East (N. Virginia)
Checked
21 November 2026
Credit offer
Up to $200 credits for new customers (6 months) · eligibility applies; checked 2026-10-31

Source price ↗ · Report this price

L4 · Google Cloud24 GBspot / interruptible$0.34–Rent →
checked 21 NovDetails
Region
US Central (Iowa)
Checked
21 November 2026
Credit offer
$300 welcome credit (90 days) · eligibility applies; checked 2026-10-31

Source price ↗ · Report this price

L4 · Koyeb24 GBserverless$0.70$0.000194/sec–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

L4 · Modal24 GBserverless$0.80$0.000222/sec–Rent →
checked 21 NovDetails
Checked
21 November 2026
Credit offer
$30/month recurring free compute (Starter), $100/month (Team) · eligibility applies; checked 2026-10-31

Source price ↗ · Report this price

L4 · Cerebrium24 GBserverless$0.80$0.000222/sec–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

L4 · Baseten24 GBserverless$0.85$0.000236/sec–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

Fresh prices come first. Within each billing type, prices run lowest first, with unavailable offers last. Commercial relationships never affect ordering. How we collect and rank prices.

Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.

Cite this data

GPU Rental Prices, "Rent NVIDIA L4 GPU, November 2026: from $0.44/GPU-hour", prices checked 21 November 2026, https://gpurentalprices.com/l4

Quote it with a link to this page. Downloads of the whole dataset are on Data & API.

On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.

L4 price history and range

Date range for the L4 chart
  • Cheapest on-demand$0.44(the same as 90 days ago)
  • Provider median$0.69
  • Cheapest spot$0.10
Daily, 2026-07-05 to 2026-11-21, from our own price checks. The provider median counts each provider's cheapest on-demand rate once and is drawn only on days with three or more providers. Missing days stay gaps.

L4 price range by billing type

Per GPU-hour, latest checked offers. Axis $0 to $2.00.

On-demand8 offers · 7 providersfrom $0.44median $0.69to $1.67
Spot & community3 offers · 2 providersfrom $0.10to $0.34
Serverless4 offers · 4 providersfrom $0.70median $0.80to $0.85

CheapestProvider median (each provider's cheapest rate counted once; shown with three or more providers)

Price changes

  • 30 days: +1.9% across 7 matching on-demand configurations since 22 October 2026.
  • 90 days: +12.1% across 3 matching on-demand configurations since 23 August 2026.

Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region (RunPod's place is where that day's stock sat, so it is not matched). New listings are not counted as price changes. Full ledger on the history hub.

L4 daily figures (140 days)
DateCheapest on-demandProvider medianCheapest spot
2026-11-21$0.44$0.69$0.10
2026-11-20$0.44$0.80$0.10
2026-11-19$0.44$0.69$0.10
2026-11-18$0.44$0.69$0.10
2026-11-17$0.44$0.69$0.10
2026-11-16$0.44$0.69$0.10
2026-11-15$0.44$0.69$0.10
2026-11-14$0.44$0.80$0.10
2026-11-13$0.44$0.75$0.10
2026-11-12$0.44$0.80$0.10
2026-11-11$0.44$0.80$0.10
2026-11-10$0.44$0.70$0.10
2026-11-09$0.44$0.80$0.10
2026-11-08$0.44$0.80$0.10
2026-11-07$0.44$0.80$0.10
2026-11-06$0.44$0.70$0.10
2026-11-05$0.44$0.80$0.10
2026-11-04$0.44$0.80$0.10
2026-11-03$0.44$0.59$0.10
2026-11-02$0.44$0.59$0.10
2026-11-01$0.44$0.70$0.10
2026-10-31$0.44$0.59$0.10
2026-10-30$0.56$0.70$0.10
2026-10-29$0.56$0.80$0.10
2026-10-28$0.56$0.80$0.10
2026-10-27$0.56$0.80$0.10
2026-10-26$0.56$0.80$0.10
2026-10-25$0.44$0.70$0.10
2026-10-24$0.44$0.70$0.10
2026-10-23$0.44$0.70$0.10
2026-10-22$0.44$0.70$0.10
2026-10-21$0.44$0.70$0.10
2026-10-20$0.44$0.70$0.10
2026-10-19$0.44$0.70$0.10
2026-10-18$0.44$0.70$0.10
2026-10-17$0.44$0.70$0.10
2026-10-16$0.44$0.70$0.10
2026-10-15$0.44$0.70$0.10
2026-10-14$0.44$0.70$0.10
2026-10-13$0.44$0.70$0.10
2026-10-12$0.44$0.70$0.10
2026-10-11$0.44$0.70$0.10
2026-10-10$0.44$0.70$0.10
2026-10-09$0.44$0.70$0.10
2026-10-08$0.44$0.68$0.10
2026-10-07$0.44$0.68$0.10
2026-10-06$0.44$0.68$0.10
2026-10-05$0.44$0.68$0.10
2026-10-04$0.44$0.68$0.10
2026-10-03$0.44$0.68$0.10
2026-10-02$0.44$0.68$0.10
2026-10-01$0.44$0.68$0.10
2026-09-30$0.44$0.68$0.10
2026-09-29$0.44$0.68$0.10
2026-09-28$0.44$0.68$0.10
2026-09-27$0.44$0.56$0.34
2026-09-26$0.44$0.56$0.34
2026-09-25$0.44$0.56$0.34
2026-09-24$0.44$0.56$0.34
2026-09-23$0.44$0.56$0.34
2026-09-22$0.44$0.56$0.34
2026-09-21$0.44$0.56$0.34
2026-09-20$0.44$0.56$0.34
2026-09-19$0.44$0.56$0.34
2026-09-18$0.44$0.56$0.34
2026-09-17$0.44$0.56$0.34
2026-09-16$0.44$0.56$0.34
2026-09-15$0.44$0.56$0.34
2026-09-14$0.44$0.56$0.32
2026-09-13$0.44$0.56$0.32
2026-09-12$0.44$0.56$0.32
2026-09-11$0.44$0.56$0.32
2026-09-10$0.44$0.56$0.32
2026-09-09$0.44$0.53$0.32
2026-09-08$0.44$0.56$0.32
2026-09-07$0.44$0.56$0.34
2026-09-06$0.44$0.56$0.34
2026-09-05$0.44$0.56$0.34
2026-09-04$0.44$0.56$0.34
2026-09-03$0.44$0.56$0.34
2026-09-02$0.44$0.56$0.34
2026-09-01$0.44$0.56$0.34
2026-08-31$0.44$0.56$0.34
2026-08-30$0.44$0.56$0.34
2026-08-29$0.44$0.53$0.34
2026-08-28$0.44$0.56$0.34
2026-08-27$0.44$0.56$0.34
2026-08-26$0.44$0.56$0.34
2026-08-25$0.44$0.56$0.34
2026-08-24$0.44$0.56$0.34
2026-08-23$0.44$0.56$0.34
2026-08-22$0.44$0.56$0.34
2026-08-21$0.44$0.56$0.34
2026-08-20$0.44$0.56$0.34
2026-08-19$0.44$0.56$0.34
2026-08-18$0.44$0.56$0.34
2026-08-17$0.44$0.56$0.34
2026-08-16$0.44$0.56$0.34
2026-08-15$0.44$0.56$0.34
2026-08-14$0.44$0.56$0.34
2026-08-13$0.44$0.56$0.34
2026-08-12$0.44$0.56$0.34
2026-08-11$0.44$0.56$0.34
2026-08-10$0.44$0.56$0.33
2026-08-09$0.44$0.56$0.33
2026-08-08$0.44$0.56$0.33
2026-08-07$0.44$0.56$0.33
2026-08-06$0.44$0.56$0.33
2026-08-05$0.44$0.56$0.33
2026-08-04$0.39$0.56$0.33
2026-08-03$0.39$0.56$0.31
2026-08-02$0.39$0.56$0.31
2026-08-01$0.39$0.56$0.31
2026-07-31$0.39$0.56$0.31
2026-07-30$0.39$0.56$0.31
2026-07-29$0.39$0.56$0.31
2026-07-28$0.39$0.56$0.31
2026-07-27$0.39$0.56$0.31
2026-07-26$0.39$0.56$0.31
2026-07-25$0.39$0.56$0.31
2026-07-24$0.39$0.56$0.31
2026-07-23$0.39$0.56$0.31
2026-07-22$0.39$0.56$0.31
2026-07-21$0.39$0.56$0.31
2026-07-20$0.39$0.56$0.31
2026-07-19$0.39$0.44$0.44
2026-07-18$0.39$0.44$0.44
2026-07-17$0.39$0.44$0.44
2026-07-16$0.39$0.44$0.44
2026-07-15$0.39$0.44$0.44
2026-07-14$0.39$0.44$0.44
2026-07-13$0.39$0.44$0.44
2026-07-12$0.39$0.44$0.44
2026-07-11$0.39$0.44$0.44
2026-07-10$0.39–$0.44
2026-07-09$0.39$0.44$0.44
2026-07-08$0.39$0.44$0.44
2026-07-07$0.39$0.44$0.44
2026-07-06$0.39$0.44$0.44
2026-07-05$0.39–$0.44

L4 prices by provider and billing type

Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its L4 page with node sizes, fees and its own history.

ProviderOn-demandSpot & communityServerless
Jarvislabs$0.44––
Google Cloud$0.56$0.34–
Runcrate$0.58––
RunPod$0.69––
AWS$0.80$0.10–
Scaleway$0.87––
OVHcloud$1.00––
Koyeb––$0.70
Modal––$0.80
Cerebrium––$0.80
Baseten––$0.85

L4 hardware specs

L4 hardware specifications
ArchitectureAda Lovelace
VRAM24 GB
FP16 TFLOPS (dense)121
Memory bandwidth300 GB/s
TDP72 W
InterconnectPCIe Gen4
Launched2023

Manufacturer datasheet figures for the L4. Source: www.nvidia.com.

LLM memory estimates for this GPU

Qwen3 8B at 16-bit weights
20.4GB
Weights 16.4 GB · cache 0.6 GB · headroom 3.4 GB. Capacity line: 24 GB.

These models have an estimated inference footprint within 24 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.

Model16-bit GB8-bit GB4-bit GB
Qwen2.5 32B79.9 40.6 20.9 ✓
Qwen2.5 Coder 32B79.9 40.6 20.9 ✓
DeepSeek R1 Distill Qwen 32B79.9 40.6 20.9 ✓
QwQ 32B79.9 40.6 20.9 ✓
Qwen3 32B79.9 40.6 20.9 ✓
Qwen3 30B A3B73.8 37.1 18.8 ✓
Qwen3 30B A3B 250773.8 37.1 18.8 ✓
Qwen3 Coder 30B A3B73.8 37.1 18.8 ✓
Mistral Small 3.2 24B 250658.4 29.6 15.2 ✓
Mistral Small 24B 250157.4 29.1 14.9 ✓
Devstral Small 250757.4 29.1 14.9 ✓
Qwen2.5 14B36.4 18.7 ✓9.8 ✓
Qwen2.5 Coder 14B36.4 18.7 ✓9.8 ✓
DeepSeek R1 Distill Qwen 14B36.4 18.7 ✓9.8 ✓
Qwen3 14B36.2 18.5 ✓9.7 ✓
phi 436.2 18.6 ✓9.8 ✓
Phi 4 reasoning36.2 18.6 ✓9.8 ✓
Phi 4 reasoning plus36.2 18.6 ✓9.8 ✓
Mistral Nemo 240730.2 15.5 ✓8.2 ✓
Qwen3 8B20.4 ✓10.6 ✓5.6 ✓
DeepSeek R1 Distill Llama 8B19.9 ✓10.3 ✓5.5 ✓
Qwen2.5 7B18.6 ✓9.4 ✓4.9 ✓
Qwen2.5 Coder 7B18.6 ✓9.4 ✓4.9 ✓
DeepSeek R1 Distill Qwen 7B18.6 ✓9.4 ✓4.9 ✓
Mistral 7B v0.318.0 ✓9.3 ✓5.0 ✓
Qwen3 4B10.4 ✓5.6 ✓3.1 ✓
Qwen3 4B 250710.4 ✓5.6 ✓3.1 ✓
Qwen2.5 3B7.6 ✓3.9 ✓2.0 ✓
Qwen2.5 Coder 3B7.6 ✓3.9 ✓2.0 ✓
Qwen3 1.7B5.4 ✓3.0 ✓1.8 ✓
DeepSeek R1 Distill Qwen 1.5B4.4 ✓2.3 ✓1.2 ✓
Qwen2.5 1.5B3.8 ✓2.0 ✓1.1 ✓
Qwen2.5 Coder 1.5B3.8 ✓2.0 ✓1.1 ✓
Qwen3 0.6B2.4 ✓1.5 ✓1.0 ✓
Qwen2.5 0.5B1.2 ✓0.7 ✓0.4 ✓
Qwen2.5 Coder 0.5B1.2 ✓0.7 ✓0.4 ✓

Models that need more than one L4

Compare model memory requirements or change context and memory assumptions on a model's page.

When to choose the L4, and what to pick instead

Start from memory: your model, its context and your batch must fit in 24 GB (the model-fit table above estimates it). Then the L4 is the right card unless one of these fits your job better.

Our workload guides recommend the L4 for self-hosted AI agents, computer vision, text embeddings, Jupyter notebooks and speech recognition. Each compares it with the other cards that suit that job, at today's prices.

Rent or buy the L4

Confirmed L4 purchase listings start at $4,367 (L4 24GB, SabrePC, checked 21 November 2026, out of stock). That sum rents about 9,925 GPU-hours at the cheapest on-demand rate of $0.44 (checked 21 November 2026), about 4.8 years at 40 hours a week, before electricity, hosting and resale.

Compare L4 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.

L4 questions

How much does it cost to rent a L4?
The cheapest L4 rental we have is $0.44 per GPU-hour on Jarvislabs (on-demand), checked 21 November 2026. The median of each provider's cheapest on-demand rate is $0.69 across 7 providers.
How much VRAM does a L4 have?
24 GB.
Where is the L4 cheapest right now?
Jarvislabs has the cheapest checked on-demand rate on 21 November 2026 at $0.44 per GPU-hour; interruptible spot or community capacity starts at $0.10 (AWS).

GPUs near the L4

Related

All 24 GB+ GPUs · GPUs under $1/hr · Price movers this week · Jarvislabs review · L4 vs L40S · A10 vs L4 · A30 vs L4 · Cloud GPU for self-hosted AI agents · Best Cloud GPU for Computer Vision

Compare your offers

Saved prices keep their original dates. Confirm the configuration, terms and availability at the source.

Select up to three offers to compare their rates and terms.

Type a GPU, a provider, a model or a question.