GPU Rental PricesGPU Rental Prices / GPU prices
Download data

RTX 4090 rental prices: cheapest $/hr today

The cheapest on-demand RTX 4090 rental today is $0.35/hr on TensorDock, updated 2026-10-06. 24 GB VRAM, NVIDIA.

Salad prices use its Lowest priority tier: workloads can be interrupted. These rates suit retryable batch jobs; they do not guarantee availability or uninterrupted runtime. Compare Salad priority tiers.

$0.35/hr
cheapest on-demand rate (spot/community from $0.16) · TensorDock (on-demand) · source: www.tensordock.com
Rent on TensorDock →
community cloud · salad · $0.16/hr · 2026-10-06community cloud · runpod · $0.34/hr · 2026-10-06on-demand · tensordock · $0.35/hr · 2026-10-06spot / interruptible · daytona · $0.57/hr · 2026-10-06on-demand · spheron · $0.58/hr · 2026-10-06secure cloud · runpod · $0.74/hr · 2026-10-06on-demand · daytona · $0.99/hr · 2026-10-06serverless · runpod · $1.10/hr · 2026-10-06
$0.16/hr$1.10/hr
8 offers · dashed line: $0.575 median per offer · 2026-10-06. ● On-demand · ◆ Spot/community · ■ Reserved · ○ Serverless.

Pricing at a glance

$0.35
cheapest on-demand $/hr
$0.66
median on-demand $/hr, each provider counted once
$0.99
max on-demand $/hr
8
live offers
5
providers

All current RTX 4090 offers

Provider, memory & availability

8 offers. Rates are per GPU; total is for the smallest listed node.

GPU / providerBilling$/GPU-hourGPUs / total per hourAvailability / details
RTX 4090SaladCloud24 GB VRAMcommunity cloud$0.16per GPU-hour+0.0% over 30 daysNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
vCPU not reported
RAM
RAM not reported
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

RTX 4090RunPod24 GB VRAMcommunity cloud$0.34per GPU-hour+0.0% over 30 daysNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
vCPU not reported
RAM
RAM not reported
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

RTX 4090TensorDock24 GB VRAMon-demand$0.35per GPU-hour+0.0% over 30 daysNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
vCPU not reported
RAM
RAM not reported
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

RTX 4090Daytona24 GB VRAMRTX 4090; GPU rate only, CPU/memory/disk billed separatelyspot / interruptible$0.57per GPU-hour30-day comparison unavailableNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
vCPU not reported
RAM
RAM not reported
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

RTX 4090Spheron24 GB VRAMon-demand$0.58per GPU-hour-24.7% over 30 daysNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
vCPU not reported
RAM
RAM not reported
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

RTX 4090RunPod24 GB VRAMsecure cloud$0.74per GPU-hour+0.0% over 30 daysNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
6 vCPU
RAM
41 GB RAM
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

RTX 4090Daytona24 GB VRAMRTX 4090; GPU rate only, CPU/memory/disk billed separatelyon-demand$0.99per GPU-hour30-day comparison unavailableNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
vCPU not reported
RAM
RAM not reported
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

RTX 4090RunPod24 GB VRAMFlex workerserverless$1.10per GPU-hour$0.000306/sec30-day comparison unavailableNode minimum and total not reportedNot reportedView provider
2026-10-06Details
CPU
vCPU not reported
RAM
RAM not reported
Disk
Disk not reported
Region
Not reported
Updated
2026-10-06

Source price ↗ · Report this price

Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.

On-demand and secure rates do not require a reservation. Community and spot capacity can be interrupted. Prices are per GPU per hour, before storage/egress. Every row shows its update date.

RTX 4090 hardware specs

RTX 4090 hardware specifications
ArchitectureAda Lovelace
VRAM24 GB
FP16 TFLOPS (dense)165
Memory bandwidth1008 GB/s
TDP450 W
InterconnectPCIe Gen4
Launched2022

Datasheet spec for the RTX 4090 variant. Source: www.nvidia.com.

Compare RTX 4090 configurations

RTX 4090 purchase prices · Rent or buy calculator · Compare two GPUs

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

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

When to choose RTX 4090

Use the model memory estimates above to check whether your weights, context and batch size fit within 24 GB. Then compare the exact variant, node size and software support. Capacity alone does not establish inference speed or training throughput.

If your workload fits within 16 GB, compare RTX A4000 rental prices from $0.10/GPU-hour. The smaller memory budget is the trade-off; price alone does not make the cards interchangeable.

RTX 4090 price changes

Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region. New listings are not counted as price changes.

Price history

on-demand rate per day · median on-demand rate per day (dashed), since 2026-07-05: $0.34 low · $0.69 high. Full ledger on the history hub.

FAQ

How much does it cost to rent a RTX 4090?

The cheapest RTX 4090 rental we have is $0.35 per GPU-hour on TensorDock (on-demand), updated 2026-10-06.

How much VRAM does a RTX 4090 have?

24 GB.

Where is the RTX 4090 cheapest right now?

TensorDock has the cheapest verified on-demand rate today at $0.35 per GPU-hour; interruptible spot/community capacity starts at $0.16. Verified 2026-10-06.

Related

All 24 GB+ GPUs · GPUs under $1/hr · Price movers this week · TensorDock review · RTX 4090 vs RTX 5090 · RTX 4090 vs A100 · RTX 3090 vs RTX 4090 · Cloud GPU for speech recognition · Cloud GPU for cloud gaming and game streaming · How much does an RTX 4090 cost to rent?

Should you rent or buy?

Compare RTX 4090 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 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.