GPU Rental Prices
SearchCtrl K

RunPod RTX 4090 pricing

RunPod's on-demand RTX 4090 starts at $0.89/GPU-hour. Check the minimum GPU count: the node total is the amount billed each hour.

In our check of 21 November 2026: RunPod is the 4th cheapest of 5 providers for an on-demand RTX 4090, $0.54 an hour above TensorDock at $0.35. Its rate is unchanged since 14 November 2026.

RunPod's cheapest on-demand RTX 4090 · checked 21 November 2026$0.89/GPU-hourRTX 4090 · RunPod

All RunPod RTX 4090 offers

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

“Machines in” filters the 1 of 3 offers whose provider says where the machine is; the others are under “Place not stated”.

“vCPUs per GPU” and “RAM per GPU” use the 1 of 3 offers whose provider publishes the machine's vCPUs or RAM for a stated number of GPUs (RunPod); an offer that does not publish them never matches a minimum. A GiB counts as 1.07 GB.

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

GPU / providerBilling$/GPU-hourNode · total per hourRent
RTX 4090 · RunPod24 GBsecure cloud$0.89–In stock: mediumRent →
checked 21 NovDetails
CPU
6 vCPU
RAM
41 GB RAM
Stock in
Europe, United States
Checked
21 November 2026

Source price ↗ · Report this price

RTX 4090 · RunPod24 GBcommunity cloud$0.34–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

RTX 4090 · RunPod24 GB · Flex workerserverless$1.34$0.000372/sec+21.8% in 30 days–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, "RunPod RTX 4090 pricing: rates and node costs", prices checked 21 November 2026, https://gpurentalprices.com/providers/runpod/rtx-4090

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

The market median on-demand rate for RTX 4090 is $0.52/GPU-hour, the middle of every provider's cheapest on-demand rate. RunPod's lowest listed on-demand rate is 71.2% above it. Configurations and minimum node sizes differ.

RunPod RTX 4090 stock, day by day

At the 30 daily checks since 23 October 2026, RunPod reported RTX 4090 in stock at 27 of them.

Every check as a table
CheckStock
21 November 2026In stock
20 November 2026In stock
19 November 2026In stock
18 November 2026In stock
17 November 2026Out of stock
16 November 2026In stock
15 November 2026In stock
14 November 2026In stock
13 November 2026In stock
12 November 2026In stock
11 November 2026In stock
10 November 2026In stock
9 November 2026In stock
8 November 2026In stock
7 November 2026In stock
6 November 2026Out of stock
5 November 2026In stock
4 November 2026In stock
3 November 2026Out of stock
2 November 2026In stock
1 November 2026In stock
31 October 2026In stock
30 October 2026In stock
29 October 2026In stock
28 October 2026In stock
27 October 2026In stock
26 October 2026In stock
25 October 2026In stock
24 October 2026In stock
23 October 2026In stock

One reading a day, at the daily price check, of the stock RunPod itself publishes. Stock between checks is not recorded, and stock on past days is no promise of stock today. A failed check is shown as no reading.

What the RunPod bill includes

Billing incrementper-second · checked 16 October 2026
Minimum depositno fixed deposit; balance must cover at least one hour of the chosen Pod to deploy · checked 16 October 2026
Minimum purchasenot published · checked 16 October 2026
Data egressfree · checked 16 October 2026
Storage$0.10/GB/month for container or volume disk on a running Pod; $0.20/GB/month for volume disk on a stopped Pod; network volumes $0.07/GB/month under 1TB, $0.05/GB/month over 1TB · checked 16 October 2026
When stoppedstorage only: volume disk at $0.20/GB/month and network volumes at their usual rate; container disk is erased, not charged · checked 16 October 2026

Billing terms checked 7 July 2026 unless a row shows a later date; confirm terms before renting. The GPU rate does not automatically include storage or data transfer.

Other RTX 4090 providers

More filters: provider, memory, node size, stock, sort, price unit

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

GPU / providerBilling$/GPU-hourNode · total per hourRent
RTX 4090 · TensorDock24 GBon-demand$0.35–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

RTX 4090 · Spheron24 GBon-demand$0.48−17.2% in 30 days–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

RTX 4090 · Runcrate24 GB · RTX 4090; lowest live rate; billed per secondon-demandStarting rate$0.52–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

RTX 4090 · Daytona24 GB · RTX 4090; GPU rate only, CPU/memory/disk billed separatelyon-demand$0.99–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, "RunPod RTX 4090 pricing: rates and node costs", prices checked 21 November 2026, https://gpurentalprices.com/providers/runpod/rtx-4090

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

All RTX 4090 rental rates · All RunPod GPUs · Estimate the total job cost

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.