Tesla V100 rental price: from $0.17/hr today

Tesla V100 offers: 8 configurations from 6 providers

On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.

Tesla V100 price history and range

Tesla V100 prices by provider and billing type

Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its Tesla V100 page with node sizes, fees and its own history.

Tesla V100 hardware specs, by variant

Manufacturer datasheet figures. Source: images.nvidia.com.

Tesla V100 variants

LLM memory estimates for this GPU

These models have an estimated inference footprint within 16 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.

Models that need more than one Tesla V100

• Mixtral 8x7B v0.1 at 16-bit needs about 113 GB with the same context and headroom, so at least 8 cards. The cheapest Tesla V100 node with a published size that holds it: 8× at $6.32/hr (Lambda, $0.79 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• Qwen2.5 32B at 16-bit needs about 80 GB with the same context and headroom, so at least 5 cards. The cheapest Tesla V100 node with a published size that holds it: 8× at $6.32/hr (Lambda, $0.79 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.
• Qwen2.5 Coder 32B at 16-bit needs about 80 GB with the same context and headroom, so at least 5 cards. The cheapest Tesla V100 node with a published size that holds it: 8× at $6.32/hr (Lambda, $0.79 per GPU-hour). At 8 or 4 bit it needs less; the model page recalculates.

Compare model memory requirements or change context and memory assumptions on a model's page.

When to choose the Tesla V100, and what to pick instead

Start from memory: your model, its context and your batch must fit in 16 GB (the model-fit table above estimates it). Then the Tesla V100 is the right card unless one of these fits your job better.

• Pick the A30 (24 GB, from $0.35/hr) when the model or its cache does not fit in 16 GB, or finishing sooner is worth paying more: it has 1.3 times the Tesla V100's 16-bit compute.

Rent or buy the Tesla V100

We have no confirmed Tesla V100 purchase price from the stores we check; renting starts at $0.17 per GPU-hour. A seller quote entered in the calculator gives the break-even.

Compare Tesla V100 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.

Tesla V100 questions

How much does it cost to rent a Tesla V100?

The cheapest Tesla V100 rental we have is $0.17 per GPU-hour on TensorDock (on-demand), checked 22 October 2026. The median of each provider's cheapest on-demand rate is $0.77 across 5 providers.

How much VRAM does a Tesla V100 have?

16 GB depending on the variant (Tesla V100 PCIe: 16 GB, Tesla V100 SXM2: 16 GB, Tesla V100: 16 GB).

Where is the Tesla V100 cheapest right now?

TensorDock has the cheapest checked on-demand rate today at $0.17 per GPU-hour; interruptible spot or community capacity starts at $1.40 (Google Cloud).

GPUs near the Tesla V100

• RTX 2000 Ada16 GB$0.24/hrcheapest on-demand
• RTX A400016 GB$0.10/hrcheapest on-demand
• RTX A450020 GB$0.25/hrcheapest on-demand
• Tesla T416 GB$0.35/hrcheapest on-demand
• A3024 GB$0.35/hrcheapest on-demand

Related

All 24 GB+ GPUs · GPUs under $1/hr · Price movers this week · TensorDock review · Tesla V100 vs A100 · A10 vs Tesla V100 · A30 vs Tesla V100