How much does the RTX 4090 cost per hour?

As of September 8, 2026, the median on-demand price is $0.44 per GPU per hour across 15 providers with a priced on-demand config. On-demand: 99 configs, median $0.44, cheapest $0.29 (in stock, GPU.ai) Reserved: 94 configs, median $0.37, cheapest $0.24 (48 mo, in stock, Vast.ai) Spot: 54 configs, median $0.17, cheapest $0.15 (in stock, Vast.ai)

Who has the cheapest RTX 4090?

As of September 8, 2026, the cheapest verified in-stock on-demand RTX 4090 tracked by GetDeploying is $0.29 per GPU per hour from GPU.ai. Cheapest verified in stock on other billing types: reserved $0.24 (48 mo) and spot $0.15, both from Vast.ai.

How much does the RTX 4090 cost per month?

As of September 8, 2026, at 720 hours per month, one RTX 4090 costs an estimated $317 at the median on-demand price. Cheapest verified in stock: $209 per month on-demand, $173 reserved (48 mo), $108 spot.

Where can I rent an RTX 4090?

GetDeploying currently tracks RTX 4090 configs from 17 providers. The cheapest verified in-stock on-demand configs come from GPU.ai, Vast.ai, Novita and Runpod. See the full price comparison above for every provider and config.

Are RTX 4090 prices going up or down?

As of September 8, 2026, the median on-demand price has fallen about 11% over the past 90 days to $0.44 per GPU per hour, and about 14% over the past 12 months.

How many RTX 4090 GPUs do I need?

One RTX 4090 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 RTX 4090?

24GB GDDR6X with Ada Lovelace FP8 Tensor Cores. Highest-performing consumer GPU of the Ada generation. Can run 13B parameter models at FP16 or 30B+ quantized. Popular for AI research and Stable Diffusion.

When is the RTX 4090 not a good fit?

Consumer GeForce GPU. No ECC memory. 24GB VRAM is limiting for larger LLMs. Subject to Nvidia's consumer EULA, which may restrict data center use. For production inference, consider the L40S.

Nvidia RTX 4090

Top Ada Lovelace consumer GPU for local AI research and rendering.

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 RTX 4090 price history (JSON).

At a glance

Hardware

Architecture: Ada Lovelace
Memory per GPU: 24 GB GDDR6X
Memory bandwidth: 1,010 GB/s
Release date: Q4 2022

Market Updated 2 minutes ago

Cheapest in stock: $0.29 / GPU / hr; on-demand · 2x · GPU.ai
Median price: $0.44 / GPU / hr; on-demand
90-day trend: −11%; median on-demand
Coverage: 17 providers; 192 of 247 configs in stock

RTX 4090 Pricing and Availability

17 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 7 configs 1x-8x checked <30m ago

On-Demand from $0.34 Reserved on request

From $0.34 / GPU / hr On-Demand Visit website


1x RTX 4090 Community Cloud	24GB	10	30GB	On-Demand	$0.34	$0.34	In stock
2x RTX 4090 Community Cloud	48GB	20	60GB	On-Demand	$0.34	$0.68	In stock
1x RTX 4090 Secure Cloud	24GB	10	30GB	On-Demand	$0.74	$0.74	In stock
4x RTX 4090 Community Cloud	96GB	40	120GB	On-Demand	$0.34	$1.36	In stock
2x RTX 4090 Secure Cloud	48GB	20	60GB	On-Demand	$0.74	$1.48	In stock
4x RTX 4090 Secure Cloud	96GB	40	120GB	On-Demand	$0.74	$2.96	In stock
8x RTX 4090 Secure Cloud	192GB	80	240GB	Reservation	Custom	Custom	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T06:00Z. Not reported means we could not confirm availability.

Vast.ai

In stock

USA 151 configs 1x-16x checked <30m ago

On-Demand from $0.30 Reserved from $0.24 Spot from $0.15

From $0.30 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x RTX 4090 NL	24GB	16	126GB	Reserved (48mo)	$0.24	$0.24	In stock
1x RTX 4090 US	24GB	24	63GB	On-Demand	$0.30	$0.30	In stock
2x RTX 4090 TR	48GB	32	62GB	Spot	$0.15	$0.30	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T06:02Z. Not reported means we could not confirm availability.

Loading 148 more configs...

Packet·ai

In stock

USA 1 config 1x checked <24h ago

On-Demand from $0.39

From $0.39 / GPU / hr On-Demand Visit website


1x RTX 4090 nvidia-rtx-4090-1gpu-dedicated	24GB	--	--	On-Demand	$0.39	$0.39	In stock

In-stock and out-of-stock as of our last check at 2026-09-07T09:48Z. Not reported means we could not confirm availability.

Novita

In stock

USA 20 configs 1x-8x checked <5m ago

On-Demand from $0.33 Reserved from $0.27 Spot from $0.17

From $0.33 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x RTX 4090	24GB	16	62GB	Spot	$0.17	$0.17	In stock
1x RTX 4090	24GB	16	62GB	On-Demand	$0.33	$0.33	In stock
4x RTX 4090	96GB	64	248GB	Reserved (12mo)	$0.27	$1.09	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T06:15Z. Not reported means we could not confirm availability.

Loading 17 more configs...

Oblivus

In stock

USA 28 configs 1x-8x checked <1h ago

On-Demand from $0.64 Reserved from $0.44

From $0.64 / GPU / hr On-Demand PCIe Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x RTX 4090 PCIe RTX_4090_x1	24GB	12	70GB	Reserved (36mo)	$0.44	$0.44	Not reported
1x RTX 4090 PCIe RTX_4090_x1	24GB	12	70GB	On-Demand	$0.64	$0.64	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T05:40Z. Not reported means we could not confirm availability.

Loading 26 more configs...

Runcrate

In stock

USA 1 config 1x checked <1h ago

On-Demand from $0.66

From $0.66 / GPU / hr On-Demand PCIe Visit website


1x RTX 4090 PCIe	24GB	12	70GB	On-Demand	$0.66	$0.66	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T05:40Z. Not reported means we could not confirm availability.

Sesterce

In stock

France 7 configs 1x-8x checked <30m ago

On-Demand from $0.66

From $0.66 / GPU / hr On-Demand Visit website


1x RTX 4090	24GB	12	70GB	On-Demand	$0.66	$0.66	In stock
2x RTX 4090	48GB	24	140GB	On-Demand	$0.66	$1.32	Out of stock
4x RTX 4090	96GB	60	352GB	On-Demand	$0.66	$2.64	In stock
8x RTX 4090	192GB	48	256GB	On-Demand	$0.44	$3.52	Out of stock
8x RTX 4090	192GB	88	228GB	On-Demand	$0.44	$3.52	Out of stock
8x RTX 4090	192GB	64	512GB	On-Demand	$0.54	$4.31	Out of stock
8x RTX 4090	192GB	120	706GB	On-Demand	$0.66	$5.28	Out of stock

In-stock and out-of-stock as of our last check at 2026-09-08T06:00Z. Not reported means we could not confirm availability.

GPU.ai

In stock

UAE 6 configs 1x-12x checked <5m ago

On-Demand from $0.29

From $0.29 / GPU / hr On-Demand Visit website


1x RTX 4090	24GB	--	--	On-Demand	$0.32	$0.32	In stock
2x RTX 4090	48GB	--	--	On-Demand	$0.29	$0.59	In stock
4x RTX 4090	96GB	--	--	On-Demand	$0.31	$1.24	In stock
8x RTX 4090	192GB	--	--	On-Demand	$0.34	$2.68	In stock
6x RTX 4090	144GB	--	--	On-Demand	$0.95	$5.68	In stock
12x RTX 4090	288GB	--	--	On-Demand	$0.72	$8.63	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T06:15Z. Not reported means we could not confirm availability.

Spheron

In stock

Singapore 2 configs 1x-2x checked <30m ago

On-Demand from $0.77

From $0.77 / GPU / hr On-Demand PCIe Visit website


1x RTX 4090 PCIe RTX_4090_x1__OSL1	24GB	12	70GB	On-Demand	$0.77	$0.77	In stock
2x RTX 4090 PCIe RTX_4090_x2__OSL1	48GB	24	140GB	On-Demand	$0.77	$1.54	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T06:00Z. Not reported means we could not confirm availability.

Salad

USA 2 configs 1x checked <24h ago

On-Demand from $0.30 Spot from $0.16

From $0.30 / GPU / hr On-Demand Visit website


1x RTX 4090 Lowest priority	24GB	4	8GB	Spot	$0.16	$0.16	Not reported
1x RTX 4090 High priority	24GB	4	8GB	On-Demand	$0.30	$0.30	Not reported

In-stock and out-of-stock as of our last check at 2026-09-07T09:48Z. Not reported means we could not confirm availability.

BreezeHost

USA 1 config 1x checked 1 week ago

On-Demand from $0.35

From $0.35 / GPU / hr On-Demand Visit website


1x RTX 4090 GPU Instance RTX 4090	24GB	16	28GB	On-Demand	$0.35	$0.35	Not reported

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

Beam

USA 1 config 1x checked <24h ago

On-Demand from $0.44

From $0.44 / GPU / hr On-Demand PCIe Visit website


1x RTX 4090 PCIe	24GB	8	64GB	On-Demand	$0.44	$0.44	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.

TensorDock

USA 1 config 1x checked 2 weeks ago

On-Demand from $0.46

From $0.46 / GPU / hr On-Demand Visit website


1x RTX 4090	24GB	16	32GB	On-Demand	$0.46	$0.46	Not reported

In-stock and out-of-stock as of our last check at 2026-08-21T20:03Z. Not reported means we could not confirm availability.

SwissGPU

Switzerland 1 config 1x checked 1 week ago

On-Demand from $0.49

From $0.49 / GPU / hr On-Demand Visit website


1x RTX 4090	24GB	16	32GB	On-Demand	$0.49	$0.49	Not reported

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

GPUhub

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

On-Demand from $0.44

From $0.44 / GPU / hr On-Demand Visit website


1x RTX 4090	48GB	10	96GB	On-Demand	$0.44	$0.44	Not reported
2x RTX 4090	96GB	20	192GB	On-Demand	$0.44	$0.87	Not reported
4x RTX 4090	192GB	40	384GB	On-Demand	$0.44	$1.75	Not reported
8x RTX 4090	384GB	80	768GB	On-Demand	$0.44	$3.50	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T05:40Z. Not reported means we could not confirm availability.

Database Mart

USA 8 configs 1x-2x checked <24h ago

Reserved from $0.30

From $0.30 / GPU / hr Reserved (24mo) Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
2x RTX 4090	48GB	36	256GB	Reserved (24mo)	$0.30	$0.60	Not reported

Cloudzy

Out of stock

UAE 6 configs 1x-4x checked <1h ago

On-Demand from $1.16 Reserved from $1.08

From $1.16 / GPU / hr On-Demand PCIe Visit website


1x RTX 4090 PCIe	24GB	24	256GB	Reserved (1mo)	$1.08	$1.08	Out of stock
1x RTX 4090 PCIe	24GB	24	256GB	On-Demand	$1.16	$1.16	Out of stock
2x RTX 4090 PCIe	48GB	48	512GB	Reserved (1mo)	$1.08	$2.17	Out of stock
2x RTX 4090 PCIe	48GB	48	512GB	On-Demand	$1.16	$2.32	Out of stock
4x RTX 4090 PCIe	96GB	64	768GB	Reserved (1mo)	$1.08	$4.33	Out of stock
4x RTX 4090 PCIe	96GB	64	768GB	On-Demand	$1.16	$4.64	Out of stock

In-stock and out-of-stock as of our last check at 2026-09-08T05:40Z. Not reported means we could not confirm availability.

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 RTX 4090 run?

One RTX 4090 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 · $317/mo	2 GPUs 30 GB VRAM · $634/mo	4 GPUs 58 GB VRAM · $1,267/mo
Gemma 4 31B	30.7B	1 GPU 22 GB VRAM · $317/mo	2 GPUs 35 GB VRAM · $634/mo	4 GPUs 69 GB VRAM · $1,267/mo
GPT-OSS-120B	117B 5.1B active	4 GPUs 67 GB VRAM · $1,267/mo	6 GPUs 120 GB VRAM · $1,901/mo	11 GPUs 237 GB VRAM
DeepSeek V4 Flash	284B 13B active	8 GPUs 160 GB VRAM · $2,534/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 RTX 4090 · Per GPU

Compute · dense
FP8	330.3 TFLOPS 660.6 with sparsity
FP16 / BF16	165.2 TFLOPS 330.4 with sparsity
INT8	660.6 TOPS 1,321.2 with sparsity
FP32	82.6 TFLOPS
Precision support	FP8FP16BF16TF32FP32INT4INT8

Memory
Capacity	24 GB GDDR6X
Bandwidth	1,010 GB/s
Bus width	384-bit
ECC	No

Silicon
Architecture	Ada Lovelace
Process	TSMC 4N
Transistors	76.3 billion
Shader cores	16,384 CUDA cores
Matrix cores	512 Tensor cores
Compute units	128 SMs

Fabric and host
Host interface	PCIe 4.0

Power
Board power	450 W
Cooling	Active

Source: official Nvidia RTX 4090 datasheet.

Runpod

Our sponsor

Spin Up a GPU in Seconds - No Setup Required

Deploy AI Models Globally in 30+ Regions

Scale from 0 to 1000 GPUs on Demand

PyTorch, Tensorflow & Docker Ready

Learn more

Frequently Asked Questions

How much does the RTX 4090 cost per hour?: As of September 8, 2026, the median on-demand price is $0.44 per GPU per hour across 15 providers with a priced on-demand config.

Billing type Configs Median / GPU / hr Cheapest

On-demand 99 $0.44 $0.29 (in stock, GPU.ai)

Reserved 94 $0.37 $0.24 (48 mo, in stock, Vast.ai)

Spot 54 $0.17 $0.15 (in stock, Vast.ai)
Who has the cheapest RTX 4090?: As of September 8, 2026, the cheapest verified in-stock on-demand RTX 4090 tracked by GetDeploying is $0.29 per GPU per hour from GPU.ai. Cheapest verified in stock on other billing types: reserved $0.24 (48 mo) and spot $0.15, both from Vast.ai.
How much does the RTX 4090 cost per month?: As of September 8, 2026, at 720 hours per month, one RTX 4090 costs an estimated $317 at the median on-demand price. Cheapest verified in stock: $209 per month on-demand, $173 reserved (48 mo), $108 spot.
Where can I rent an RTX 4090?: GetDeploying currently tracks RTX 4090 configs from 17 providers. The cheapest verified in-stock on-demand configs come from GPU.ai, Vast.ai, Novita and Runpod. See the full price comparison above for every provider and config.
Are RTX 4090 prices going up or down?: As of September 8, 2026, the median on-demand price has fallen about 11% over the past 90 days to $0.44 per GPU per hour, and about 14% over the past 12 months.
How many RTX 4090 GPUs do I need?: One RTX 4090 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 RTX 4090?: 24GB GDDR6X with Ada Lovelace FP8 Tensor Cores. Highest-performing consumer GPU of the Ada generation. Can run 13B parameter models at FP16 or 30B+ quantized. Popular for AI research and Stable Diffusion.
When is the RTX 4090 not a good fit?: Consumer GeForce GPU. No ECC memory. 24GB VRAM is limiting for larger LLMs. Subject to Nvidia's consumer EULA, which may restrict data center use. For production inference, consider the L40S.

Billing type	Configs	Median / GPU / hr	Cheapest
On-demand	99	$0.44	$0.29 (in stock, GPU.ai)
Reserved	94	$0.37	$0.24 (48 mo, in stock, Vast.ai)
Spot	54	$0.17	$0.15 (in stock, Vast.ai)

Alternatives to Nvidia RTX 4090

Browse all GPUs

Last updated Sept. 8, 2026

At a glance

Hardware

Market Updated 2 minutes ago

RTX 4090 Pricing and Availability

How this list works

The two views

Order

Search

Transparency and funding

What size AI models can the RTX 4090 run?

Technical Specifications

Frequently Asked Questions

How much does the RTX 4090 cost per hour?

Who has the cheapest RTX 4090?

How much does the RTX 4090 cost per month?

Where can I rent an RTX 4090?

Are RTX 4090 prices going up or down?

How many RTX 4090 GPUs do I need?

Why choose the RTX 4090?

When is the RTX 4090 not a good fit?

Alternatives to Nvidia RTX 4090

Nvidia RTX 5090

Nvidia L40S

Nvidia RTX 3090