How much does the T4 cost per hour?

As of September 8, 2026, the median on-demand price is $0.64 per GPU per hour across 10 providers. On-demand: 42 configs, median $0.64, cheapest $0.11 (in stock, Vast.ai) Reserved: 63 configs, median $0.43, cheapest $0.20 (36 mo) Spot: 17 configs, median $0.26, cheapest $0.06 (in stock, Vast.ai)

Who has the cheapest T4?

As of September 8, 2026, the cheapest verified in-stock on-demand T4 tracked by GetDeploying is $0.11 per GPU per hour from Vast.ai. Cheapest verified in stock on other billing types: spot $0.06, also from Vast.ai.

How much does the T4 cost per month?

As of September 8, 2026, at 720 hours per month, one T4 costs an estimated $461 at the median on-demand price. Cheapest verified in stock: $79 per month on-demand, $43 spot.

Where can I rent a T4?

GetDeploying currently tracks T4 configs from 11 providers. Vast.ai and Zenlayer have verified in-stock on-demand configs. See the full price comparison above for every provider and config.

Are T4 prices going up or down?

As of September 8, 2026, the median on-demand price has fallen about 6% over the past 90 days to $0.64 per GPU per hour, though it is about 5% above where it was a year ago.

How many T4 GPUs do I need?

One T4 runs models up to roughly 8B parameters at 4-bit quantization or 2B 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.

16GB GDDR6 in a 70W low-power form factor. Very low cost per hour across cloud providers. INT8 Tensor Cores for efficient inference on smaller models.

When is the T4 not a good fit?

Turing architecture lacks BF16 and FP8. 16GB VRAM limits model sizes. Slow for training. For production inference, the L4 offers significantly better throughput.

Nvidia T4

Low-cost inference GPU with wide cloud availability.

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 T4 price history (JSON).

At a glance

Hardware

Architecture: Turing
Memory per GPU: 16 GB GDDR6
Memory bandwidth: 300 GB/s
Release date: Q3 2018

Market Updated 5 minutes ago

Cheapest in stock: $0.11 / GPU / hr; on-demand · 1x · Vast.ai
Median price: $0.64 / GPU / hr; on-demand
90-day trend: −6%; median on-demand
Coverage: 11 providers; 5 of 122 configs in stock

T4 Pricing and Availability

11 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.

Vast.ai

Our sponsor

USA 3 configs 1x checked <30m ago

On-Demand from $0.11 Spot from $0.06

From $0.11 / GPU / hr On-Demand Visit website


1x T4 CZ	16GB	14	94GB	Spot	$0.06	$0.06	In stock
1x T4 US	16GB	36	31GB	On-Demand	$0.11	$0.11	In stock
1x T4 CZ	16GB	14	94GB	On-Demand	$0.15	$0.15	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T12:47Z. Not reported means we could not confirm availability.

Zenlayer

In stock

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

On-Demand from $0.56

From $0.56 / GPU / hr On-Demand PCIe Visit website


1x T4 PCIe z2a.g.T4.c16m64.1	16GB	16	64GB	On-Demand	$0.56	$0.56	In stock
2x T4 PCIe z2a.g.T4.c32m128.2	32GB	32	128GB	On-Demand	$0.56	$1.11	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T09:16Z. Not reported means we could not confirm availability.

Theta EdgeCloud

USA 2 configs 1x-2x checked <15m ago

On-Demand from $0.20

From $0.20 / GPU / hr On-Demand Visit website


1x T4 vm_gt1	16GB	2	8GB	On-Demand	$0.20	$0.20	Not reported
2x T4 vm_gt2	32GB	8	16GB	On-Demand	$0.20	$0.40	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T13:02Z. Not reported means we could not confirm availability.

Cerebrium

USA 4 configs 1x-8x checked <24h ago

On-Demand from $0.59

From $0.59 / GPU / hr On-Demand Visit website


1x T4 TURING_T4	16GB	--	--	On-Demand	$0.59	$0.59	Not reported
2x T4 TURING_T4	32GB	--	--	On-Demand	$0.59	$1.18	Not reported
4x T4 TURING_T4	64GB	--	--	On-Demand	$0.59	$2.36	Not reported
8x T4 TURING_T4	128GB	--	--	On-Demand	$0.59	$4.72	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:12Z. Not reported means we could not confirm availability.

Hugging Face

USA 2 configs 1x checked <24h ago

On-Demand from $0.40

From $0.40 / GPU / hr On-Demand Visit website


1x T4 t4-small	16GB	4	15GB	On-Demand	$0.40	$0.40	Not reported
1x T4 t4-medium	16GB	8	30GB	On-Demand	$0.60	$0.60	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:14Z. Not reported means we could not confirm availability.

Azure

USA 16 configs 1x-4x checked <24h ago

On-Demand from $0.53 Reserved from $0.20 Spot from $0.10

From $0.53 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x T4 NCasT4 v3	16GB	4	28GB	Spot	$0.10	$0.10	Not reported
1x T4 NCasT4 v3	16GB	4	28GB	Reserved (36mo)	$0.20	$0.20	Not reported
1x T4 NCasT4 v3	16GB	4	28GB	On-Demand	$0.53	$0.53	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:11Z. Not reported means we could not confirm availability.

Loading 13 more configs...

AWS

USA 21 configs 1x-8x checked <24h ago

On-Demand from $0.53 Reserved from $0.23

From $0.53 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x T4 g4dn.xlarge	16GB	4	16GB	Reserved (36mo)	$0.23	$0.23	Not reported
1x T4 g4dn.xlarge	16GB	4	16GB	On-Demand	$0.53	$0.53	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:11Z. Not reported means we could not confirm availability.

Loading 19 more configs...

Google Cloud

USA 48 configs 1x-4x checked <24h ago

On-Demand from $0.42 Reserved from $0.21 Spot from $0.21

From $0.42 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
4x T4 n1-standard-4-t4-4	64GB	4	15GB	Spot	$0.21	$0.85	Not reported
4x T4 n1-standard-4-t4-4	64GB	4	15GB	Reserved (36mo)	$0.21	$0.86	Not reported
4x T4 n1-standard-4-t4-4	64GB	4	15GB	On-Demand	$0.42	$1.69	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:14Z. Not reported means we could not confirm availability.

Loading 45 more configs...

Replicate

USA 1 config 1x checked <24h ago

On-Demand from $0.81

From $0.81 / GPU / hr On-Demand Visit website


1x T4 gpu-t4	16GB	4	16GB	On-Demand	$0.81	$0.81	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:16Z. Not reported means we could not confirm availability.

Alibaba Cloud

Singapore 12 configs 1x-4x checked <24h ago

On-Demand from $1.12 Reserved from $0.62

From $1.12 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x T4 ecs.gn6i-c4g1.xlarge	16GB	4	15GB	Reserved (12mo)	$0.62	$0.62	Not reported
1x T4 ecs.gn6i-c4g1.xlarge	16GB	4	15GB	On-Demand	$1.12	$1.12	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:10Z. Not reported means we could not confirm availability.

Loading 10 more configs...

Leaseweb

Netherlands 11 configs 1x-2x checked <24h ago

Reserved from $0.23

From $0.23 / GPU / hr Reserved (1mo) Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
2x T4 VOLUME_R730XD-12LFF-E52650v4-2xT4	32GB	24	128GB	Reserved (1mo)	$0.23	$0.45	Not reported

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 T4 run?

One T4 has 16 GB of VRAM. In practice, that's enough memory for roughly 8B parameters at 4-bit or 2B 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	2 GPUs 19 GB VRAM · $922/mo	4 GPUs 31 GB VRAM · $1,843/mo	8 GPUs 58 GB VRAM · $3,686/mo
Gemma 4 31B	30.7B	2 GPUs 24 GB VRAM · $922/mo	4 GPUs 38 GB VRAM · $1,843/mo	8 GPUs 69 GB VRAM · $3,686/mo
GPT-OSS-120B	117B 5.1B active	8 GPUs 68 GB VRAM · $3,686/mo	9 GPUs 120 GB VRAM	17 GPUs 237 GB VRAM
DeepSeek V4 Flash	284B 13B active	12 GPUs 161 GB VRAM	21 GPUs 289 GB VRAM	40 GPUs 573 GB VRAM
GLM-5.3-Flash	320B 18B active	13 GPUs 178 GB VRAM	23 GPUs 322 GB VRAM	45 GPUs 642 GB VRAM
MiniMax-M3	428B 23B active	17 GPUs 241 GB VRAM	31 GPUs 434 GB VRAM	60 GPUs 862 GB VRAM
Kimi K3	2.8T 104B active	108 GPUs 1,545 GB VRAM	195 GPUs 2,805 GB VRAM	390 GPUs 5,605 GB VRAM

Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. 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 T4 · Per GPU

Compute · dense
FP16 / BF16	65 TFLOPS
INT8	130 TOPS
FP32	8.1 TFLOPS
Precision support	FP16FP32INT4INT8

Memory
Capacity	16 GB GDDR6
Bandwidth	300 GB/s
Bus width	256-bit
ECC	Yes

Silicon
Architecture	Turing
Process	TSMC 12nm FFN
Transistors	13.6 billion
Shader cores	2,560 CUDA cores
Matrix cores	320 Tensor cores
Compute units	40 SMs

Fabric and host
Host interface	PCIe 3.0 x16

Power
Board power	70 W
Cooling	Passive

Source: official Nvidia T4 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 T4 cost per hour?: As of September 8, 2026, the median on-demand price is $0.64 per GPU per hour across 10 providers.

Billing type Configs Median / GPU / hr Cheapest

On-demand 42 $0.64 $0.11 (in stock, Vast.ai)

Reserved 63 $0.43 $0.20 (36 mo)

Spot 17 $0.26 $0.06 (in stock, Vast.ai)
Who has the cheapest T4?: As of September 8, 2026, the cheapest verified in-stock on-demand T4 tracked by GetDeploying is $0.11 per GPU per hour from Vast.ai. Cheapest verified in stock on other billing types: spot $0.06, also from Vast.ai.
How much does the T4 cost per month?: As of September 8, 2026, at 720 hours per month, one T4 costs an estimated $461 at the median on-demand price. Cheapest verified in stock: $79 per month on-demand, $43 spot.
Where can I rent a T4?: GetDeploying currently tracks T4 configs from 11 providers. Vast.ai and Zenlayer have verified in-stock on-demand configs. See the full price comparison above for every provider and config.
Are T4 prices going up or down?: As of September 8, 2026, the median on-demand price has fallen about 6% over the past 90 days to $0.64 per GPU per hour, though it is about 5% above where it was a year ago.
How many T4 GPUs do I need?: One T4 runs models up to roughly 8B parameters at 4-bit quantization or 2B 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 T4?: 16GB GDDR6 in a 70W low-power form factor. Very low cost per hour across cloud providers. INT8 Tensor Cores for efficient inference on smaller models.
When is the T4 not a good fit?: Turing architecture lacks BF16 and FP8. 16GB VRAM limits model sizes. Slow for training. For production inference, the L4 offers significantly better throughput.

Billing type	Configs	Median / GPU / hr	Cheapest
On-demand	42	$0.64	$0.11 (in stock, Vast.ai)
Reserved	63	$0.43	$0.20 (36 mo)
Spot	17	$0.26	$0.06 (in stock, Vast.ai)

Alternatives to Nvidia T4

Browse all GPUs

Last updated Sept. 8, 2026

Nvidia T4

At a glance

Hardware

Market Updated 5 minutes ago

T4 Pricing and Availability

How this list works

The two views

Order

Search

Transparency and funding

Vast.ai

Zenlayer

Theta EdgeCloud

Cerebrium

Hugging Face

Azure

AWS

Google Cloud

Replicate

Alibaba Cloud

Leaseweb

What size AI models can the T4 run?

Technical Specifications

Frequently Asked Questions

How much does the T4 cost per hour?

Who has the cheapest T4?

How much does the T4 cost per month?

Where can I rent a T4?

Are T4 prices going up or down?

How many T4 GPUs do I need?

Why choose the T4?

When is the T4 not a good fit?

Alternatives to Nvidia T4

Nvidia L40S

Nvidia L4

Nvidia A10