Skip to content
GPU Finder

RTX 4090 GPU Rental Prices & Live Availability

Cheapest on-demand RTX 4090 confirmed in stock right now

Limited
$0.35/hr1× listing
on Lium · Greece
Visit Lium

The cheapest on-demand single RTX 4090 confirmed in stock is $0.35 per GPU-hour on Lium. Stock checked 19 November 2026 at 22:20 UTC. Limited stock was reported. 5 providers have fresh self-service on-demand stock for this size; the on-demand catalog contains 86 listings across 9 providers.

How this stock answer is checked

Evaluated . Stock checks must be no more than 6 hours old; limited stock counts as in stock. Unknown, stale, out-of-stock and sales-only offers do not qualify. Confirm capacity with the provider before renting.

Selected listing history: fully available for 10% of tracked time in the last 30 days. Limited stock is rentable now but does not count as fully available.

Coverage: 541 tracked listing-hours. Coverage can be shorter than the 30-day window; hours add up across combined regional listings. This measures reported stock, not machine uptime.

Stock and history methodology. Inspect listings and stock filters.

Stock checks run regularly where supported; collection delays can occur and the cheapest in-stock offer can change between checks. Latest stock observation on this page: at page generation; individual listings may be older. Set a price alert to get an email when the RTX 4090 price drops.

In-stock providers (all sizes):7
Catalog providers (all sizes):11
On-demand whole-node range:$0.35 — $14.72/hr
Spot price:from $0.16/hr
Instances:104
Free egress:2 providers
Updated:

Single RTX 4090 rental summary

stock checked
How have single-GPU RTX 4090 catalog prices changed?
▼ near the lowest monthly listed rate — The November 2026 catalog snapshot lists 1× RTX 4090 from $0.11/hr ($0.11/GPU-hr). Lowest listed rates ranged from $0.11 to $0.34/hr across 6 recorded monthly snapshots (June 2026–November 2026). These are historical on-demand list prices; they do not establish stock availability or predict current rental prices.
What is the cheapest single RTX 4090 on-demand cloud GPU available right now?
The cheapest on-demand single RTX 4090 confirmed in stock is $0.35 per GPU-hour on Lium. Stock checked 19 November 2026 at 22:20 UTC. Limited stock was reported.
Which providers have the strongest single RTX 4090 stock history?
For 1× RTX 4090 listings across tracked regions, the highest mean fully-available history scores within the trailing 30-day window are Salad. Coverage varies by listing. Lower fully-available history scores: Akash, Packet.

Current on-demand answers use fresh self-service stock, including limited stock; historical price trends include catalog listings and do not establish current capacity. How we compute this →

Page headline prices reflect the default offers: fresh reported stock, including limited stock, with self-service access.

In-stock price range: 35 1× RTX 4090 listings from $0.35 to $2.71 USD per physical GPU-hour. Whole-node prices for other GPU counts are not mixed into this range.

RTX 4090 rental prices by provider

Offer visibility

Choose whether to include out-of-stock or unconfirmed offers. Limited stock is included. Reported availability is not a capacity guarantee.

Stock now uses the latest provider report. History measures time reported fully available. Limited stock is rentable now but does not count as fully available. A 0% history can still have stock now.

  • 1x RTX 4090 marketplace
    Now:Limited10% fully available30d history · 541h tracked
    $0.35/hr
    1× RTX 409016 vCPU47 GBGreece
  • 1x RTX 4090 marketplace
    Now:Limited31% fully available30d history · 720h tracked
    $0.38/hr
    Interruptible $0.27−29%
    updated hourly · as of
    1× RTX 409032 vCPU63 GBFree egressTexas, US
  • rtx-4090-24gb
    Now:In stock91% fully available30d history · 720h tracked
    $0.44/hr
    Interruptible $0.16−64%
    updated daily · as of
    1× RTX 40900 GBGlobal (automatic placement)

Vast.ai marketplace: 124 more RTX 4090 listings were unavailable under our collection filters at the last check, last listed from $0.36/GPU-hr. They are hidden above; browse the provider for current offers and rental conditions.

Browse live Vast.ai offers

Get notified when RTX 4090 drops in price or reliability changes

One email per change, max once a day. We send a confirmation link first; one-click unsubscribe in every email.

How to choose an RTX 4090 rental host

Shortlist a host for the job you will actually run. A low GPU-hour rate alone does not tell you the cost of loading data, running the job and saving its output.

Confirm the allocation
For a one-card job, choose a 1× listing and confirm that checkout includes a full GPU. NVIDIA specifies 24 GB of memory for the RTX 4090; check the memory exposed to your container or VM before loading the workload.
Check the host, not just the GPU
Compare the selected region, CPU allocation, system RAM, disk space and upload/download limits. Confirm SSH or notebook access, your container image and compatible drivers. A GPU rental does not necessarily include a Windows desktop or game streaming.
Price the complete session
Confirm the minimum charge and billing increment; do not assume per-second billing. Include data transfer, image downloads and setup in billed time. Check persistent storage and egress charges, including what remains billable after the GPU stops.
Run a small trial
Measure a representative batch and save the output before committing to a longer run. Compare cost per completed job at the same quality settings. If the allocation is interruptible, keep checkpoints outside the instance and test resuming.

Hardware reference: NVIDIA RTX 4090 memory specification. This does not verify any rental host's configuration.

Compare listings and visit a provider →Estimate compute and egress →

RTX 4090 (1× GPU) availability history — last 7 days

1 of 10 providers kept 1× RTX 4090 ≥80% fully available all week. Polled hourly · 10 providers tracked · 7-day window.

≥80%50–80%<50%No data

Percentages show tracked time reported fully available. Limited stock can still be rented, but does not count as fully available here. Missing data is not 0%; this history is not machine uptime.

View:
Provider
13
14
15
16
17
18
19
Week
Salad100%
EmpirioLabs86%
Shadeform41%
Lium15%
Runpod12%
Vast1%
AceCloud0%
Akash0%
Packet0%
Theta EdgeCloud0%

30-day stock history

For RTX 4090, history is the share of tracked time each listing was reported fully available within the last 30 days. Limited stock is rentable now but does not count as fully available. This measures reported stock, not machine uptime. How we compute this →

103
listings with a history percentage
99%
of listings on this page have enough history
720h
most tracked listing-hours for one row

Highest fully-available shares: Salad (91% fully available; 720h tracked), Lium (71% fully available; 720h tracked), EmpirioLabs (52% fully available; 509h tracked).

Coverage can be shorter than the 30-day window. Tracked listing-hours add time across combined regional listings, so they can exceed elapsed calendar time. Percentages stay hidden below 48 tracked listing-hours. Unknown periods are missing data, not time with no stock. Confirm current capacity with the provider.

Price History & Comparison: 1× RTX 4090

Full RTX 4090 price history (8 months) →
Loading chart...

Spot pricing decision guide

Treat spot as a risk-adjusted capacity decision, not just a cheaper number.

Cheap but risky
On-demand floor
$0.35

per GPU-hour

Spot / interruptible floor
$0.16

54% below on-demand floor

7-day trend
flat

daily median for the same offers with complete history

Volatility
stable

median $0.39/GPU-hr

Cheapest trusted spot / interruptible capacity is on Salad; 3 providers currently report spot or interruptible stock (512 units/signals visible).

Salad has kept spot or interruptible capacity in stock most reliably over the last 30 days (91%). See the availability section for the broader stock history.

The discount is visible, but availability, reliability, or volatility argues for more caution.

Good fit: checkpointed batch jobs, flexible training, and experiments that can restart. Avoid for production serving, deadline-bound runs, or jobs that cannot tolerate eviction.

Source caveat: Runpod exposes explicit spot fields; Vast is labeled interruptible/bid-floor. Lambda is treated as on-demand-only unless a verified spot field is added.

RTX 4090 spot, preemptible and interruptible pricing

The cheapest RTX 4090 spot price per GPU from each provider that publishes one, ordered by price. Each card uses the provider’s own term and shows how the price is set; the provider can reclaim this capacity. Spot prices for every GPU

SaladInterruptible

$0.16/GPU-hr

vs on-demand $0.44/GPU-hr · 64% below on-demand · 1× in Global (automatic placement)

VastInterruptible

$0.24/GPU-hr

vs on-demand $0.39/GPU-hr · 38% below on-demand · 4× in Michigan, US

If interrupted: Paused; resumes when it regains priority

Lium

$0.40/GPU-hr

vs on-demand $0.45/GPU-hr · 11% below on-demand · 2× in United States

RTX 4090 spot pricing FAQ

Who has RTX 4090 spot GPU pricing?

3 providers list RTX 4090 spot, preemptible or interruptible prices on GPU Finder right now, cheapest per GPU first: Salad $0.16/GPU-hr (interruptible), Vast $0.24/GPU-hr (interruptible), Lium $0.40/GPU-hr (spot). Each provider's own term is shown.

What happens when the provider reclaims RTX 4090 spot capacity?

It depends on the provider: Vast: paused; resumes when it regains priority. Save checkpoints to storage that survives the instance.

Should I choose the cheapest RTX 4090 spot offer?

Only if the workload can tolerate interruption. RTX 4090 spot, preemptible and interruptible prices are best for checkpointed batch jobs, flexible training and experiments. Avoid them for production serving, deadline-bound runs or jobs that cannot restart.

About the RTX 4090

The NVIDIA RTX 4090 is an Ada Lovelace consumer GPU with 24 GB of GDDR6X memory. Renting one can support inference, image generation and experiments whose memory requirements fit the card. The host's CPU, RAM, storage and software environment also affect whether a workload runs well; the GPU model alone does not establish performance per dollar.

Key Specifications

ArchitectureAda Lovelace (AD102)
GPU Memory24 GB GDDR6X
Memory Bandwidth1,008 GB/s
FP16 Tensor Core330 TFLOPS
TDP450W
InterconnectPCIe Gen4 x16
Release Year2022

Cloud Pricing Context

Compare current RTX 4090 listings by GPU count, region and stock status, then confirm the host's minimum charge and billing increment. For short sessions, setup and data transfer can matter as much as the advertised hourly rate. Use a representative trial to compare total job cost against other GPUs; a lower hourly price does not guarantee a cheaper completed job.

Best For

  • Fine-tuning 7B-parameter models with LoRA/QLoRA adapters
  • Local-quality inference for Llama, Mistral, and similar models
  • Rapid prototyping where cost matters more than ECC
  • Stable Diffusion, ComfyUI, and image generation workloads

RTX 4090 by node size

How does the RTX 4090 compare on price? The cheapest cloud GPU prices per hour rank every model we track by its lowest per-GPU-hour rate and the cheapest listing in stock. For the most-compared training GPU, see H100 cloud pricing across every provider.

Providers listing this GPU