How much does the V100 cost per hour?

As of September 8, 2026, the median on-demand price is $0.97 per GPU per hour across 18 providers with a priced on-demand config. On-demand: 83 configs, median $0.97, cheapest $0.11 (in stock, Vast.ai) Reserved: 81 configs, median $0.97, cheapest $0.13 (24 mo, in stock, Verda) Spot: 28 configs, median $0.27, cheapest $0.09 (in stock, Verda)

Who has the cheapest V100?

As of September 8, 2026, the cheapest verified in-stock on-demand V100 tracked by GetDeploying is $0.11 per GPU per hour from Vast.ai. Cheapest verified in stock on other billing types: reserved $0.13 (24 mo) and spot $0.09, both from Verda.

How much does the V100 cost per month?

As of September 8, 2026, at 720 hours per month, one V100 costs an estimated $698 at the median on-demand price. Cheapest verified in stock: $79 per month on-demand, $94 reserved (24 mo), $65 spot.

Where can I rent a V100?

GetDeploying currently tracks V100 configs from 20 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, HyperAI, Verda and Runpod. See the full price comparison above for every provider and config.

How many V100 GPUs do I need?

One V100 runs models up to roughly 34B parameters at 4-bit quantization or 9B 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.

32GB or 16GB HBM2 with 300 GB/s NVLink. Legacy data center GPU with wide availability and low cost. FP64 support makes it useful for scientific computing.

When is the V100 not a good fit?

Volta architecture lacks BF16, TF32, and FP8 support. Significantly slower than Ampere or Hopper for AI workloads. Only consider if budget is the primary constraint.

Nvidia V100

Legacy data center GPU with FP64 support for scientific computing.

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 V100 price history (JSON).

At a glance

Hardware

Architecture: Volta
Memory per GPU: 32 GB HBM2
Memory bandwidth: 900 GB/s
Release date: Q2 2017

Market Updated 19 minutes ago

Cheapest in stock: $0.11 / GPU / hr; on-demand · 2x · Vast.ai
Median price: $0.97 / GPU / hr; on-demand
Coverage: 20 providers; 47 of 192 configs in stock

V100 Pricing and Availability

20 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 27 configs 1x-4x checked <30m ago

On-Demand from $0.11 Reserved from $0.15 Spot from $0.09

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

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x V100 US	32GB	16	94GB	Spot	$0.09	$0.09	In stock
1x V100 BG	32GB	20	94GB	Reserved (1mo)	$0.15	$0.15	In stock
2x V100 US	32GB	40	86GB	On-Demand	$0.11	$0.22	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.

Loading 24 more configs...

Runpod

In stock

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

On-Demand from $0.23

From $0.23 / GPU / hr On-Demand SXM Visit website


1x V100 SXM Community Cloud	16GB	6	30GB	On-Demand	$0.23	$0.23	In stock
2x V100 SXM Community Cloud	32GB	12	60GB	On-Demand	$0.23	$0.46	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T12:45Z. Not reported means we could not confirm availability.

Runcrate

In stock

USA 2 configs 1x checked <30m ago

On-Demand from $2.57

From $2.57 / GPU / hr On-Demand NVL Visit website


1x V100 NVL	32GB	8	30GB	On-Demand	$2.57	$2.57	In stock
1x V100 NVL	16GB	8	30GB	On-Demand	$2.57	$2.57	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T12:40Z. Not reported means we could not confirm availability.

Sesterce

In stock

France 9 configs 1x-8x checked <30m ago

On-Demand from $2.57

From $2.57 / GPU / hr On-Demand Visit website


1x V100	16GB	6	23GB	On-Demand	$0.43	$0.43	Out of stock
2x V100	32GB	10	45GB	On-Demand	$0.43	$0.86	Out of stock
4x V100	64GB	20	90GB	On-Demand	$0.43	$1.72	Out of stock
1x V100	32GB	8	30GB	On-Demand	$2.57	$2.57	In stock
1x V100	16GB	8	30GB	On-Demand	$2.57	$2.57	In stock
8x V100	128GB	48	180GB	On-Demand	$0.43	$3.43	Out of stock
2x V100	64GB	16	60GB	On-Demand	$2.57	$5.15	In stock
8x V100	128GB	92	448GB	On-Demand	$0.87	$6.95	Out of stock
4x V100	128GB	32	120GB	On-Demand	$2.57	$10.30	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T12:45Z. Not reported means we could not confirm availability.

Verda

In stock

Finland 28 configs 1x-8x checked <30m ago

On-Demand from $0.17 Reserved from $0.13 Spot from $0.09

From $0.17 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x V100 1V100.6V	16GB	6	23GB	Spot	$0.09	$0.09	In stock
8x V100 8V100.48V	128GB	48	180GB	Reserved (24mo)	$0.13	$1.02	In stock
8x V100 8V100.48V	128GB	48	180GB	On-Demand	$0.17	$1.36	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.

Loading 25 more configs...

HyperAI

In stock

Hong Kong 4 configs 1x-8x checked <30m ago

On-Demand from $0.14

From $0.14 / GPU / hr On-Demand Visit website


1x V100 v100-32	32GB	8	32GB	On-Demand	$0.14	$0.14	In stock
2x V100 v100-32-2	64GB	16	64GB	On-Demand	$0.14	$0.28	In stock
4x V100 v100-32-4	128GB	32	128GB	On-Demand	$0.14	$0.56	In stock
8x V100 v100-32-8	256GB	64	256GB	On-Demand	$0.14	$1.12	In stock

In-stock and out-of-stock as of our last check at 2026-09-08T12:40Z. Not reported means we could not confirm availability.

TensorDock

USA 1 config 1x checked 2 weeks ago

On-Demand from $0.28

From $0.28 / GPU / hr On-Demand SXM Visit website


1x V100 SXM	16GB	16	32GB	On-Demand	$0.28	$0.28	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.

Geodd

USA 3 configs 1x-4x checked <30m ago

On-Demand from $0.16

From $0.16 / GPU / hr On-Demand Visit website


1x V100 gpu_1x_v100	32GB	16	48GB	On-Demand	$0.16	$0.16	Out of stock
2x V100 gpu_2x_v100	64GB	32	96GB	On-Demand	$0.16	$0.32	Out of stock
4x V100 gpu_4x_v100	128GB	--	--	On-Demand	$0.16	$0.64	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T12:45Z. Not reported means we could not confirm availability.

Theta EdgeCloud

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

On-Demand from $0.99

From $0.99 / GPU / hr On-Demand Visit website


1x V100 vm_gv1	16GB	4	16GB	On-Demand	$0.99	$0.99	Not reported
2x V100 vm_gv2	32GB	8	32GB	On-Demand	$0.99	$1.98	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T12:45Z. Not reported means we could not confirm availability.

Paperspace

USA 3 configs 1x-4x checked <24h ago

On-Demand from $2.30

From $2.30 / GPU / hr On-Demand Visit website


1x V100 V100	16GB	8	30GB	On-Demand	$2.30	$2.30	Not reported
1x V100 V100-32G	32GB	8	30GB	On-Demand	$2.30	$2.30	Not reported
4x V100 V100-32G x4	128GB	--	--	On-Demand	$2.30	$9.20	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.

Oracle Cloud

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

On-Demand from $2.95

From $2.95 / GPU / hr On-Demand Visit website


1x V100 VM.GPU3.1	16GB	--	--	On-Demand	$2.95	$2.95	Not reported
2x V100 VM.GPU3.2	32GB	--	--	On-Demand	$2.95	$5.90	Not reported
4x V100 VM.GPU3.4	64GB	--	--	On-Demand	$2.95	$11.80	Not reported
8x V100 BM.GPU3.8	128GB	--	--	On-Demand	$2.95	$23.60	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.

OVH

France 3 configs 1x-4x checked <24h ago

On-Demand from $0.77

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


1x V100 t1-le-45	16GB	8	45GB	On-Demand	$0.77	$0.77	Not reported
2x V100 t1-le-90	32GB	16	90GB	On-Demand	$0.78	$1.55	Not reported
4x V100 t1-le-180	64GB	32	180GB	On-Demand	$0.78	$3.10	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.

Google Cloud

USA 48 configs 1x-8x checked <24h ago

On-Demand from $2.53 Reserved from $1.34 Spot from $1.37

From $2.53 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x V100 n1-standard-8-v100-8	128GB	8	30GB	Reserved (36mo)	$1.34	$10.74	Not reported
8x V100 n1-standard-8-v100-8	128GB	8	30GB	Spot	$1.37	$10.95	Not reported
8x V100 n1-standard-8-v100-8	128GB	8	30GB	On-Demand	$2.53	$20.22	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...

AWS

USA 6 configs 1x-8x checked <24h ago

On-Demand from $3.06 Reserved from $1.30

From $3.06 / GPU / hr On-Demand Visit website


1x V100 p3.2xlarge	16GB	8	61GB	On-Demand	$3.06	$3.06	Not reported
8x V100 p3dn.24xlarge	256GB	96	768GB	Reserved (36mo)	$1.30	$10.42	Not reported
4x V100 p3.8xlarge	64GB	32	244GB	On-Demand	$3.06	$12.24	Not reported
8x V100 p3dn.24xlarge	256GB	96	768GB	Reserved (12mo)	$2.40	$19.21	Not reported
8x V100 p3.16xlarge	128GB	64	488GB	On-Demand	$3.06	$24.48	Not reported
8x V100 p3dn.24xlarge	256GB	96	768GB	On-Demand	$3.90	$31.21	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.

Azure

USA 6 configs 8x checked <24h ago

On-Demand from $1.53 Reserved from $1.35 Spot from $0.31

From $1.53 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x V100 NDSv2	256GB	40	672GB	Spot	$0.31	$2.45	Not reported
8x V100 NDrSv2	256GB	40	672GB	Reserved (12mo)	$1.35	$10.80	Not reported
8x V100 NDSv2	256GB	40	672GB	On-Demand	$1.53	$12.24	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 3 more configs...

Exoscale

Switzerland 4 configs 1x-4x checked <24h ago

On-Demand from $0.83

From $0.83 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
4x V100	64GB	48	225GB	On-Demand	$0.83	$3.32	Not reported

Alibaba Cloud

Singapore 14 configs 1x-8x checked <24h ago

On-Demand from $2.70 Reserved from $1.51

From $2.70 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
1x V100 ecs.gn6v-c8g1.2xlarge	16GB	8	42GB	On-Demand	$2.70	$2.70	Not reported
4x V100 ecs.gn6v-c8g1.8xlarge	64GB	32	168GB	Reserved (12mo)	$1.51	$6.03	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 12 more configs...

Cyfuture AI

India 16 configs 1x-8x checked <24h ago

On-Demand from $0.55 Reserved from $0.38

From $0.55 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x V100 8V100.128v.2048m-12mo	256GB	128	2.0TB	Reserved (12mo)	$0.38	$3.07	Not reported
8x V100 8V100.128v.2048m	256GB	128	2.0TB	On-Demand	$0.55	$4.42	Not reported

In-stock and out-of-stock as of our last check at 2026-09-08T09:13Z. Not reported means we could not confirm availability.

Loading 14 more configs...

Database Mart

USA 8 configs 1x-3x checked <24h ago

Reserved from $0.22

From $0.22 / GPU / hr Reserved (24mo) Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
3x V100	48GB	36	256GB	Reserved (24mo)	$0.22	$0.65	Not reported

Lambda Labs

Out of stock

USA 2 configs 8x checked <30m ago

On-Demand from $0.79

From $0.79 / GPU / hr On-Demand Visit website

Configuration	Total VRAM	vCPUs	RAM	Billing	Per GPU/h	Total/h	Availability
8x V100 gpu_8x_v100	128GB	92	448GB	On-Demand	$0.79	$6.32	Out of stock

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 V100 run?

One V100 has 32 GB of VRAM. In practice, that's enough memory for roughly 34B parameters at 4-bit or 9B 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 19 GB VRAM · $698/mo	2 GPUs 31 GB VRAM · $1,397/mo	3 GPUs 58 GB VRAM · $2,095/mo
Gemma 4 31B	30.7B	1 GPU 24 GB VRAM · $698/mo	2 GPUs 38 GB VRAM · $1,397/mo	3 GPUs 69 GB VRAM · $2,095/mo
GPT-OSS-120B	117B 5.1B active	3 GPUs 68 GB VRAM · $2,095/mo	8 GPUs 120 GB VRAM · $5,587/mo	9 GPUs 237 GB VRAM
DeepSeek V4 Flash	284B 13B active	8 GPUs 161 GB VRAM · $5,587/mo	11 GPUs 289 GB VRAM	20 GPUs 573 GB VRAM
GLM-5.3-Flash	320B 18B active	8 GPUs 178 GB VRAM · $5,587/mo	12 GPUs 322 GB VRAM	23 GPUs 642 GB VRAM
MiniMax-M3	428B 23B active	9 GPUs 241 GB VRAM	16 GPUs 434 GB VRAM	30 GPUs 862 GB VRAM
Kimi K3	2.8T 104B active	54 GPUs 1,545 GB VRAM	98 GPUs 2,805 GB VRAM	195 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 V100 · Per GPU

Compute · dense
FP16 / BF16	125 TFLOPS
FP32	15.7 TFLOPS
FP64	7.8 TFLOPS
Precision support	FP16FP32FP64INT8

Memory
Capacity	32 GB HBM2
Bandwidth	900 GB/s
Bus width	4,096-bit
ECC	Yes

Silicon
Architecture	Volta
Process	TSMC 12nm FFN
Transistors	21.1 billion
Shader cores	5,120 CUDA cores
Matrix cores	640 Tensor cores
Compute units	80 SMs

Fabric and host
GPU interconnect	NVLink 300 GB/s
Host interface	PCIe 3.0

Power
Board power	300 W
Cooling	Passive

Source: official Nvidia V100 datasheet.

GPUhub

Our sponsor

Fully Dedicated GPU Servers

No Virtualization. No Shared GPUs

Stable Performance for AI Training & Inference

Full Control for Production Workloads

Learn more

Frequently Asked Questions

How much does the V100 cost per hour?: As of September 8, 2026, the median on-demand price is $0.97 per GPU per hour across 18 providers with a priced on-demand config.

Billing type Configs Median / GPU / hr Cheapest

On-demand 83 $0.97 $0.11 (in stock, Vast.ai)

Reserved 81 $0.97 $0.13 (24 mo, in stock, Verda)

Spot 28 $0.27 $0.09 (in stock, Verda)
Who has the cheapest V100?: As of September 8, 2026, the cheapest verified in-stock on-demand V100 tracked by GetDeploying is $0.11 per GPU per hour from Vast.ai. Cheapest verified in stock on other billing types: reserved $0.13 (24 mo) and spot $0.09, both from Verda.
How much does the V100 cost per month?: As of September 8, 2026, at 720 hours per month, one V100 costs an estimated $698 at the median on-demand price. Cheapest verified in stock: $79 per month on-demand, $94 reserved (24 mo), $65 spot.
Where can I rent a V100?: GetDeploying currently tracks V100 configs from 20 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, HyperAI, Verda and Runpod. See the full price comparison above for every provider and config.
How many V100 GPUs do I need?: One V100 runs models up to roughly 34B parameters at 4-bit quantization or 9B 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 V100?: 32GB or 16GB HBM2 with 300 GB/s NVLink. Legacy data center GPU with wide availability and low cost. FP64 support makes it useful for scientific computing.
When is the V100 not a good fit?: Volta architecture lacks BF16, TF32, and FP8 support. Significantly slower than Ampere or Hopper for AI workloads. Only consider if budget is the primary constraint.

Billing type	Configs	Median / GPU / hr	Cheapest
On-demand	83	$0.97	$0.11 (in stock, Vast.ai)
Reserved	81	$0.97	$0.13 (24 mo, in stock, Verda)
Spot	28	$0.27	$0.09 (in stock, Verda)

Alternatives to Nvidia V100

Browse all GPUs

Last updated Sept. 8, 2026

At a glance

Hardware

Market Updated 19 minutes ago

V100 Pricing and Availability

How this list works

The two views

Order

Search

Transparency and funding

What size AI models can the V100 run?

Technical Specifications

Frequently Asked Questions

How much does the V100 cost per hour?

Who has the cheapest V100?

How much does the V100 cost per month?

Where can I rent a V100?

How many V100 GPUs do I need?

Why choose the V100?

When is the V100 not a good fit?

Alternatives to Nvidia V100

Nvidia H100

Nvidia RTX 5090

Nvidia A100

Nvidia RTX 4090

Nvidia L40S