Loading prices…
V100 PCIe rental prices
NVIDIA · Volta · 16 GB HBM2 · PCIe · 2017
4 providers · 9 configurations · prices as of Nov 11, 2026, 05:01 UTC
Lowest on-demand
$0.19per GPU·h · ≈ $139/month
at RunPodMedian on-demand
$2.46/GPU·h
across 4 providers
Lowest spot
$0.57/GPU·h
interruptible
FP16/BF16 cost
$1.70/PFLOP·h
#11 of 72 GPUs for value
Providers
4
9 configurations
Price history
Daily V100 PCIe prices per GPU-hour. The shaded period is reconstructed from public archives: the version history of SkyPilot's price catalogs, Internet Archive copies of providers' pricing pages and the open gpu-price-feed project (fewer providers than live data). After that, PetaPrice's own tracking.
Lowest on-demandMedian on-demandLowest spot
Price by provider
Cheapest On-demand V100 PCIe offer at each provider, per GPU-hour. Shorter and greener is cheaper.
RunPod🇺🇸$0.19best
Paperspace🇺🇸$2.3412.3×
Sesterce🇫🇷$2.5713.5×
Azure🇺🇸$3.0616.1×
Thin vertical line = median across providers ($2.34).
Every provider we track
Pricing
Size
Host
Provider HQ
4 providers · 9 configurations
Sort
- RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demandCheapest$0.19/GPU·hCheapest
- 1× GPU—$0.19 /GPU·h$0.19 /hOn-demandCommunity CloudRent ↗
- PaperspaceOn-demand🇺🇸 HQ in United Statesvia Shadeformfrom · On-demand12.3×$2.34/GPU·h12.3×
- 1× GPU · PCIe8 vCPU · 30 GB RAM · 250 GB disk$2.34 /GPU·h$2.34 /hOn-demand🇺🇸 US, New York, NY● availableRent ↗
- SesterceOn-demand🇫🇷 HQ in Francevia Sestercefrom · On-demand13.5×$2.57/GPU·h13.5×
- 1× GPU · PCIe8 vCPU · 30 GB RAM · 250 GB disk$2.57 /GPU·h$2.57 /hOn-demandUSA-NewYork-1● availableRent ↗
- AzureOn-demandSpot🇺🇸 HQ in United Statesvia Azure Retail APIfrom · On-demand16.1×$3.06/GPU·h16.1×
What can the V100 PCIe run?
Memory for the weights plus one 32K-token sequence of context, how many GPUs hold it, and what that replica costs at the cheapest in-stock on-demand rate.
| Model | Params | Memory | GPUs | $/hr | $/mo |
|---|---|---|---|---|---|
gpt-oss-20b OpenAI · 20.9B | 20.9B · 3.6B active | 20 GiB | 2 | $0.38 at RunPod | $277 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 2 | $0.38 at RunPod | $277 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 4 | $0.76 at RunPod | $555 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 8 | $1.52 at RunPod | $1,110 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 8 | $1.52 at RunPod | $1,110 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 16 | $3.04 at RunPod | $2,219 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 64 | $12.16 at RunPod | $8,877 |
Kimi K3 Moonshot AI · 2.78T | 2.78T · 104B active | 2.53 TiB | 64+ | — | — |
Assumes 90% of each GPU's memory is usable and rounds up to 1, 2, 4, 8… GPUs for tensor parallelism (up to 64). $/hr is the GPU count times the cheapest in-stock on-demand rate per GPU; check that the provider rents instances that large. Serving many requests at once needs more memory for context.
Alternatives to the V100 PCIe
GPUs with similar compute and memory, and their lowest on-demand price right now.
- V100 SXM2 16GB16 GB · 0.125 PF FP16$0.23/h$1.84/PFLOP·h
- V100 PCIe 32GB32 GB · 0.112 PF FP16$2.34/h$20.9/PFLOP·h
- V100 SXM2 32GB32 GB · 0.125 PF FP16$3.90/h$31.2/PFLOP·h
- V100S PCIe32 GB · 0.13 PF FP16$0.90/h$6.90/PFLOP·h
- L424 GB · 0.121 PF FP16$0.27/h$2.26/PFLOP·h
- A1024 GB · 0.125 PF FP16$0.85/h$6.82/PFLOP·h
V100 PCIe pricing questions
How much does it cost to rent an V100 PCIe?
On-demand V100 PCIe prices start at $0.19 per GPU-hour (RunPod). The median across 4 providers is $2.46, and the most expensive is $3.06. Running one GPU around the clock costs about $139 per month at the lowest price.
Is there cheaper spot or interruptible V100 PCIe capacity?
Yes. Spot (interruptible) V100 PCIe capacity starts at $0.57 per GPU-hour, -198% below the cheapest on-demand price. Spot instances can be preempted at any time, so use them for checkpointed training or batch jobs.
How much compute do you get per dollar with the V100 PCIe?
At $0.19 per hour and 0.112 PF of dense FP16/BF16, the V100 PCIe costs $1.70 per PFLOP-hour. That ranks 11 of 72 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the V100 PCIe's key specs?
16 GB HBM2 with 900 GB/s of memory bandwidth, Volta architecture (2017), PCIe form factor, 250 W. Dense peak: 0.112 PF FP16 / BF16, 0.014 PF FP32, 0.007 PF FP64.
How current are these prices?
Prices were collected on Nov 11, 2026, 05:01 UTC from provider APIs and public catalogs and refresh about every 2 hours. They are indicative list prices; always confirm on the provider's website before booking.