- Services
Live per-GPU prices from Vast.ai and Vultr, side by side. 0 GPU models are listed on both. Prices come from each provider’s own pricing data and refresh hourly where the provider has a pricing API.
TL;DR
Vast.ai and Vultr share no GPU models right now, so the choice comes down to which card you need. Vast.ai lists 28 GPU models and Vultr lists 0.
Advertising disclosure: we earn commissions when you shop through the links below.
Prices refreshed:
The cheapest current per-GPU rate on each provider. The lower price is highlighted. Spot rates are interruptible and shown underneath. Click a price to open the provider.
Methodology: Prices for Vast.ai and Vultr are refreshed hourly and normalized to per-GPU USD/hr. No affiliate weighting. Vast.ai figures come from its marketplace API and cover verified hosts only. Vultr prices come from its plans API. Fractional GPU slices and out-of-stock plans are left out.
Price is one input. The hosting model, reliability and day-to-day experience decide whether a provider fits your team and workload.
The cheapest single GPU on each provider with enough memory to run the model at 4-bit quantization. Models that need several GPUs are left out.
| Model | VRAM at Q4 | Vast.ai | Vultr |
|---|---|---|---|
| Mistral 7B Instruct | 7 GB | $0.06/hrNVIDIA GeForce RTX 3060 | No single GPU fits |
| Gemma 4 E4B IT | 7 GB | $0.06/hrNVIDIA GeForce RTX 3060 | No single GPU fits |
| Qwen3.6 35B-A3B | 9 GB | $0.06/hrNVIDIA GeForce RTX 3060 | No single GPU fits |
| Qwen3.5-35B-A3B | 9 GB | $0.06/hrNVIDIA GeForce RTX 3060 | No single GPU fits |
| Gemma 4 26B-A4B IT | 12 GB | $0.06/hrNVIDIA GeForce RTX 3060 | No single GPU fits |
| Llama 3.1 8B Instruct | 14 GB | $0.09/hrNVIDIA Tesla V100 16GB | No single GPU fits |
| Gemma 4 12B | 33 GB | $0.40/hrNVIDIA RTX A6000 | No single GPU fits |
| DeepSeek-R1 | 60 GB | $0.44/hrNVIDIA A100 80GB SXM | No single GPU fits |
| DeepSeek-V3 | 60 GB | $0.44/hrNVIDIA A100 80GB SXM | No single GPU fits |
| DeepSeek-V3.2 | 60 GB | $0.44/hrNVIDIA A100 80GB SXM | No single GPU fits |
| Qwen3.6-27B | 73 GB | $0.44/hrNVIDIA A100 80GB SXM | No single GPU fits |
| Gemma 4 31B IT | 82 GB | $2.66/hrNVIDIA H100 NVL | No single GPU fits |
34 vs 28 GPU models listed
See the comparison34 vs 0 GPU models listed
See the comparison17 vs 28 GPU models listed
See the comparison10 vs 28 GPU models listed
See the comparison17 vs 0 GPU models listed
See the comparison10 vs 0 GPU models listed
See the comparisonStraight answers to the questions we hear most often.
Can't find what you're looking for? Book a Discovery Call
Right now Vast.ai lists these GPU models that Vultr does not: NVIDIA B200, NVIDIA H200 NVL, NVIDIA H200 SXM, NVIDIA H100 NVL, NVIDIA A100 80GB PCIe, NVIDIA A100 80GB SXM, NVIDIA H100 SXM, NVIDIA A40, NVIDIA L40, NVIDIA L40S, NVIDIA RTX A6000, and NVIDIA RTX PRO 5000 Blackwell.
Vast.ai has spot pricing on 28 GPU models and Vultr on 0. Spot instances are the cheapest way to rent but can be reclaimed at short notice, so use them for jobs that checkpoint and resume.
Vast.ai is best for Vultr is best for
Vast.ai: Vultr:
Every hour for providers with a pricing API. GPU Mart has none, so its rate card is updated by hand. We normalize the GPU names and convert multi-GPU instances to a per-GPU rate so the two columns compare like for like.
Rates vary by region, host and availability. We show the cheapest per-GPU rate currently rentable on each provider. Marketplace hosts change their prices often, so the provider page may show a different default.
