Loading prices…
V100 SXM2 16GB rental prices
NVIDIA · Volta · 16 GB HBM2 · SXM · 2017
10 providers · 35 configurations · prices as of Nov 11, 2026, 07:02 UTC
Lowest on-demand
$0.14per GPU·h · ≈ $99/month
at GPU.aiMedian on-demand
$0.81/GPU·h
across 10 providers
Lowest spot
$0.12/GPU·h
interruptible
FP16/BF16 cost
$1.08/PFLOP·h
#2 of 75 GPUs for value
Providers
10
35 configurations
Price history
Daily V100 SXM2 16GB 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 SXM2 16GB offer at each provider, per GPU-hour. Shorter and greener is cheaper.
GPU.ai🇺🇸$0.14best
RunPod🇺🇸$0.23+70%
Verda (DataCrunch)🇫🇮$0.24+79%
OVHcloud🇫🇷$0.795.8×
Lambda🇺🇸$0.795.9×
Exoscale🇨🇭$0.836.1×
Google Cloud🇺🇸$2.6719.8×
Oracle Cloud🇺🇸$2.9521.9×
AWS🇺🇸$3.0622.7×
T Cloud Public🇩🇪$3.4925.8×
Thin vertical line = median across providers ($0.79).
Every provider we track
Pricing
Size
Host
Provider HQ
10 providers · 35 configurations
Sort
- GPU.aicommunityOn-demand🇺🇸 HQ in United Statesvia GPU.aifrom · On-demandCheapest$0.14/GPU·hCheapest
- RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demand+70%$0.23/GPU·h+70%
- 1× GPU—$0.23 /GPU·h$0.23 /hOn-demandCommunity CloudRent ↗
- Verda (DataCrunch)On-demandSpot🇫🇮 HQ in Finlandvia Verdafrom · On-demand+79%$0.24/GPU·h+79%
- OVHcloudOn-demand🇫🇷 HQ in Francevia OVHcloud catalog APIfrom · On-demand5.8×$0.79/GPU·h5.8×
- LambdaOn-demand🇺🇸 HQ in United Statesvia Lambda pricing pagefrom · On-demand5.9×$0.79/GPU·h5.9×
- 8× GPU88 vCPU · 448 GB RAM$0.79 /GPU·h$6.32 /hOn-demandRent ↗
- ExoscaleOn-demand🇨🇭 HQ in Switzerlandvia Exoscale APIfrom · On-demand6.1×$0.83/GPU·h6.1×
- Google CloudOn-demandSpot🇺🇸 HQ in United Statesvia SkyPilot catalogfrom · On-demand19.8×$2.67/GPU·h19.8×
- Oracle CloudOn-demand🇺🇸 HQ in United Statesvia Oracle price list APIfrom · On-demand21.9×$2.95/GPU·h21.9×
- 1× GPU—$2.95 /GPU·h$2.95 /hOn-demandlist price, all regionsRent ↗
What can the V100 SXM2 16GB 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 | $0.27 at GPU.ai | $197 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 2 | $0.27 at GPU.ai | $197 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 4 | $0.54 at GPU.ai | $394 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 8 | $1.08 at GPU.ai | $788 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 8 | $1.08 at GPU.ai | $788 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 16 | $2.16 at GPU.ai | $1,577 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 64 | $8.64 at GPU.ai | $6,307 |
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 SXM2 16GB
GPUs with similar compute and memory, and their lowest on-demand price right now.
V100 SXM2 16GB pricing questions
How much does it cost to rent an V100 SXM2 16GB?
On-demand V100 SXM2 16GB prices start at $0.14 per GPU-hour (GPU.ai). The median across 10 providers is $0.81, and the most expensive is $3.49. Running one GPU around the clock costs about $99 per month at the lowest price.
Is there cheaper spot or interruptible V100 SXM2 16GB capacity?
Yes. Spot (interruptible) V100 SXM2 16GB capacity starts at $0.12 per GPU-hour, 10% 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 SXM2 16GB?
At $0.14 per hour and 0.125 PF of dense FP16/BF16, the V100 SXM2 16GB costs $1.08 per PFLOP-hour. That ranks 2 of 75 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the V100 SXM2 16GB's key specs?
16 GB HBM2 with 900 GB/s of memory bandwidth, Volta architecture (2017), SXM form factor, 300 W. Dense peak: 0.125 PF FP16 / BF16, 0.0157 PF FP32, 0.0078 PF FP64.
How current are these prices?
Prices were collected on Nov 11, 2026, 07:02 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.