NVIDIA V100S rental pricing

Share this page

NVIDIA V100S rental price

A post with this link shows the card on the Image tab as its preview.

Volta architecture · 32 GB HBM2 memory · 1.1 TB/s bandwidth · 250 W board power · Released 2020

Price history

Weekly median price per GPU per hour

Last 30 days
$0$0.20$0.40$0.60$0.80$1Sep 21Sep 28Oct 5Oct 12Oct 19
On-demand
$0.88
1 provider · as of Oct 21
Community
$0.13
1 provider · as of Oct 21
Weekly median of each provider's cheapest rate, reconstructed from recorded price changes for listings currently live.

At a glance

prices checked just now
Cheapest in stock
$0.13/hr
Community · 4× V100S PCIe · Vast.ai
Median price
$0.88/hr
On-demand · 1 provider
90-day trend
Flat
Weekly median on-demand, 4 weeks
Coverage
2 providers
2 price points
$ per FP16 PFLOP-hour
$6.77
Rank 7 of 18 priced GPUs · lower is better

Every provider we track

Cheapest listing per provider and pricing type. Sold-out rows stay so you can see who normally carries it.

ProviderConfigurationPrice/GPU-hrChecked
4× V100S PCIe Community $0.13 just now View →
1× V100S PCIe $0.88 just now View →

Per GPU-hour. Spot, reserved and community pricing differ from on-demand; click through for the provider's current figure.

What can the NVIDIA V100S run?

Memory for the weights plus one sequence of context, how many GPUs hold it, and what that replica costs at the cheapest in-stock on-demand rate.

ModelParamsMemoryGPUs$/hr
gpt-oss-20b
OpenAI
20.9B· 3.6B active 20 GiB 1 $0.88
Gemma 3 27B
Google
27.4B 26 GiB 1 $0.88
Qwen3-32B
Alibaba
32.8B 32 GiB 2 $1.76
Llama 3.3 70B Instruct
Meta
70.6B 67 GiB 4 $3.52
gpt-oss-120b
OpenAI
117B· 5.1B active 109 GiB 4 $3.52
Qwen3-235B-A22B
Alibaba
235B· 22.0B active 220 GiB 8 $7.04
DeepSeek-R1
DeepSeek
684B· 37.0B active 638 GiB Over 16 —
Kimi K3
Moonshot AI
2.78T· 104B active 2.53 TiB Over 16 —

Sized for one sequence at 4K context with 16-bit KV cache and 10% of memory held back. Serving many users at once needs more; the LLM GPU calculator sizes for concurrency and throughput.

NVIDIA V100S pricing questions

How much does it cost to rent a NVIDIA V100S per hour?

The cheapest NVIDIA V100S in stock right now is $0.13 per GPU-hour community from Vast.ai for the 4× V100S PCIe configuration. The median on-demand rate across 1 provider is $0.88 per GPU-hour.

How much does a NVIDIA V100S cost per month?

Running one NVIDIA V100S around the clock for a month (730 hours) costs about $98 at the cheapest in-stock rate of $0.13 per hour. At the median on-demand rate it is about $642 a month. Reserved terms usually come in below that; ask the provider for a quote.

Which provider has the cheapest NVIDIA V100S?

Vast.ai has the cheapest NVIDIA V100S in stock right now at $0.13 per GPU-hour community for the 4× V100S PCIe configuration. That is a community rate; see the provider table for the cheapest on-demand listing. Rates change often, so check the provider table for today's figure before you commit.

Are NVIDIA V100S rental prices going up or down?

The weekly median on-demand rate for the NVIDIA V100S has been flat, moving 0.0% over the last 4 weeks, from $0.88 to $0.88 per GPU-hour.

What is the difference between on-demand, spot and reserved NVIDIA V100S pricing?

On-demand is pay-as-you-go with no commitment. Community is capacity from individual hosts on a marketplace, cheaper and less uniform. This week's median rates for the NVIDIA V100S are on-demand $0.88 (1 provider), community $0.13 (1 provider), per GPU-hour.

How many cloud providers rent the NVIDIA V100S?

We track 2 providers with 2 live prices for the NVIDIA V100S. Sold-out listings stay in the table so you can see who normally carries it, but never set the cheapest figure.

What LLMs can you run on one NVIDIA V100S?

With 8-bit weights and a single sequence of context, one NVIDIA V100S holds gpt-oss-20b (20.9B), Gemma 3 27B (27.4B). See the model fit table for the full ladder.

How does the NVIDIA V100S compare on price per PFLOP-hour?

At its cheapest in-stock on-demand rate the NVIDIA V100S delivers dense FP16 compute at $6.77 per PFLOP-hour, which ranks 7 of 18 priced GPUs we cover on that basis. Lower is better: it is the rental price divided by peak FP16 throughput.

Where does this NVIDIA V100S pricing data come from?

Prices are read daily from each provider's public price list or API and recorded whenever they change. Listings are shown per GPU-hour on-demand unless marked otherwise, and the chart covers the last 30 days. The newest listing was checked just now.

© 2026 Flopper.io - Compare the GPUs Powering AI