- Services
Live per-GPU prices from RunPod and Vast.ai, side by side. 22 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 is cheaper on 17 of the 22 GPU models both providers list. RunPod lists 34 GPU models and Vast.ai lists 28.
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 RunPod and Vast.ai are refreshed hourly and normalized to per-GPU USD/hr. No affiliate weighting. RunPod prices come from its public GraphQL pricing API. Vast.ai figures come from its marketplace API and cover verified hosts only.
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 | RunPod | Vast.ai |
|---|---|---|---|
| Mistral 7B Instruct | 7 GB | $0.13/hrNVIDIA GeForce RTX 3070 | $0.06/hrNVIDIA GeForce RTX 3060 |
| Gemma 4 E4B IT | 7 GB | $0.13/hrNVIDIA GeForce RTX 3070 | $0.06/hrNVIDIA GeForce RTX 3060 |
| Qwen3.6 35B-A3B | 9 GB | $0.16/hrNVIDIA RTX A5000 | $0.06/hrNVIDIA GeForce RTX 3060 |
| Qwen3.5-35B-A3B | 9 GB | $0.16/hrNVIDIA RTX A5000 | $0.06/hrNVIDIA GeForce RTX 3060 |
| Gemma 4 26B-A4B IT | 12 GB | $0.16/hrNVIDIA RTX A5000 | $0.06/hrNVIDIA GeForce RTX 3060 |
| Llama 3.1 8B Instruct | 14 GB | $0.16/hrNVIDIA RTX A5000 | $0.09/hrNVIDIA Tesla V100 16GB |
| Gemma 4 12B | 33 GB | $0.33/hrNVIDIA RTX A6000 | $0.40/hrNVIDIA RTX A6000 |
| DeepSeek-R1 | 60 GB | $1.19/hrNVIDIA A100 80GB PCIe | $0.44/hrNVIDIA A100 80GB SXM |
| DeepSeek-V3 | 60 GB | $1.19/hrNVIDIA A100 80GB PCIe | $0.44/hrNVIDIA A100 80GB SXM |
| DeepSeek-V3.2 | 60 GB | $1.19/hrNVIDIA A100 80GB PCIe | $0.44/hrNVIDIA A100 80GB SXM |
| Qwen3.6-27B | 73 GB | $1.19/hrNVIDIA A100 80GB PCIe | $0.44/hrNVIDIA A100 80GB SXM |
| Gemma 4 31B IT | 82 GB | $1.69/hrNVIDIA RTX PRO 6000 Blackwell | $2.66/hrNVIDIA H100 NVL |
17 vs 34 GPU models listed
See the comparison10 vs 34 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 comparison28 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 has the lower per-GPU rate on 17 of the 22 GPU models both providers list, and RunPod on 5. Prices move every hour, so check the matrix above for the card you need.
Vast.ai lists the NVIDIA H100 SXM at $1.73 per GPU-hour (on-demand), against $2.69 on RunPod. That is 36% less, or about $698 saved per month on a GPU that runs around the clock.
Vast.ai lists the NVIDIA A100 80GB SXM at $0.44 per GPU-hour (on-demand), against $1.39 on RunPod. That is 68% less, or about $692 saved per month on a GPU that runs around the clock.
RunPod lists the NVIDIA GeForce RTX 4090 at $0.34 per GPU-hour (community), against $0.41 on Vast.ai. That is 17% less, or about $49 saved per month on a GPU that runs around the clock.
Vast.ai lists the NVIDIA GeForce RTX 5090 at $0.53 per GPU-hour (on-demand), against $0.69 on RunPod. That is 23% less, or about $114 saved per month on a GPU that runs around the clock.
Right now RunPod lists these GPU models that Vast.ai does not: AMD Instinct MI350X, NVIDIA B300, AMD Instinct MI300X, NVIDIA RTX PRO 6000 Blackwell, NVIDIA H100 PCIe, NVIDIA RTX 6000 Ada, NVIDIA L4, NVIDIA RTX 4000 Ada, NVIDIA GeForce RTX 4080, NVIDIA GeForce RTX 4080 SUPER, NVIDIA GeForce RTX 4070 Ti, and NVIDIA GeForce RTX 3070.
Right now Vast.ai lists these GPU models that RunPod does not: NVIDIA GeForce RTX 5060 Ti, NVIDIA GeForce RTX 5070 Ti, NVIDIA GeForce RTX 3060, NVIDIA GeForce RTX 4070, NVIDIA GeForce RTX 5070, and NVIDIA GeForce RTX 4060 Ti.
RunPod has spot pricing on 0 GPU models and Vast.ai on 28. Spot instances are the cheapest way to rent but can be reclaimed at short notice, so use them for jobs that checkpoint and resume.
RunPod is best for Vast.ai is best for
RunPod: Vast.ai:
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.
