Not for AI workloads

Nvidia Tesla V100 cannot run modern AI models.

Its Volta architecture is below the compute capability current inference runtimes require, so PyTorch and vLLM will not run on it. Rental pricing below is still accurate for other workloads. Browse GPUs that can →

datacenter

Nvidia logo Rent Nvidia Tesla V100.

Volta 16GB VRAM From $0.018/hr
Per hour
$0.018
Per day
$0.42
Per week
$2.96
Per month
$13
Provider spread 2 providers · up to 91% cheaper at the low end
Cheapest · $0.018/hr on Vast.ai Median $0.10/hr Most expensive · $0.19/hr on RunPod
Price history

Daily median across providers.

Loading...
Where to rent it

All providers carrying this GPU.

Provider $/hr
$0.018/hr Launch ↗
$0.19/hr Launch ↗
FAQ

Frequently asked.

How much does it cost to rent the Nvidia Tesla V100 right now?
The cheapest current listing is $0.018/hr on Vast.ai, and the median across the 2 providers listing it is $0.19/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $13.
What AI models can the Nvidia Tesla V100 run?
The Nvidia Tesla V100 isn't supported by current AI inference runtimes (vLLM, llama.cpp, PyTorch builds for modern CUDA/ROCm), so we don't recommend it for AI workloads. For a similar budget, a 16–24 GB consumer card from the RTX 30 or 40 series is the usual choice.
Why does the Nvidia Tesla V100 cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia Tesla V100 price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.