Live · refreshed hourly
Cloud GPU prices right now
What it actually costs to rent each GPU this hour — and, further down, the cheapest card that genuinely runs each open model. Real offers from the providers we track, not a marketing rate card.
Every GPU we price — cheapest first
Minimum live $/hr per provider (median in grey when it differs). Spot is interruptible; on-demand is reserved while you run it.
| GPU | VRAM | Vast.ai · spot | Runpod · on-demand | Runpod · spot | Cheapest | Rent |
|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3060 12GB | 12 GB | $0.03 · med $0.06 | — | — | $0.03/hr | Vast.ai |
| NVIDIA RTX A4000 | 16 GB | $0.06 · med $0.11 | $0.17 | $0.17 | $0.06/hr | Vast.ai |
| NVIDIA Tesla V100 32GB SXM2 | 32 GB | $0.07 · med $0.09 | $0.19 | $0.19 | $0.07/hr | Vast.ai |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16 GB | $0.07 · med $0.07 | — | — | $0.07/hr | Vast.ai |
| NVIDIA GeForce RTX 3080 12GB | 12 GB | $0.08 · med $0.12 | $0.17 | $0.17 | $0.08/hr | Vast.ai |
| NVIDIA GeForce RTX 4070 SUPER | 12 GB | $0.09 · med $0.19 | — | — | $0.09/hr | Vast.ai |
| NVIDIA GeForce RTX 5060 Ti 16GB | 16 GB | $0.10 · med $0.15 | — | — | $0.10/hr | Vast.ai |
| NVIDIA GeForce RTX 5070 Ti | 16 GB | $0.12 · med $0.25 | — | — | $0.12/hr | Vast.ai |
| NVIDIA GeForce RTX 3090 Ti | 24 GB | $0.12 · med $0.15 | $0.22 | $0.22 | $0.12/hr | Vast.ai |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16 GB | $0.16 | $0.19 | — | $0.16/hr | Vast.ai |
| NVIDIA RTX A5000 | 24 GB | $0.20 · med $0.22 | $0.16 | $0.16 | $0.16/hr | Runpod |
| NVIDIA GeForce RTX 3080 Ti | 12 GB | $0.16 · med $0.17 | $0.18 | $0.18 | $0.16/hr | Vast.ai |
| NVIDIA GeForce RTX 4070 | 12 GB | $0.18 · med $0.29 | — | — | $0.18/hr | Vast.ai |
| NVIDIA L40S | 48 GB | $0.20 | $0.44 | $0.44 | $0.20/hr | Vast.ai |
| NVIDIA GeForce RTX 4080 | 16 GB | $0.21 | — | — | $0.21/hr | Vast.ai |
| NVIDIA GeForce RTX 5080 | 16 GB | $0.22 · med $0.31 | $0.39 | $0.39 | $0.22/hr | Vast.ai |
| NVIDIA A100 80GB PCIe | 80 GB | $0.24 | — | — | $0.24/hr | Vast.ai |
| NVIDIA GeForce RTX 4080 SUPER | 16 GB | $0.28 · med $0.29 | $0.27 | $0.28 | $0.27/hr | Runpod |
| NVIDIA RTX A6000 | 48 GB | $0.36 · med $0.38 | $0.33 | $0.33 | $0.33/hr | Runpod |
| NVIDIA RTX 5000 Ada Generation | 32 GB | $0.34 · med $0.43 | $0.49 | $0.49 | $0.34/hr | Vast.ai |
| NVIDIA GeForce RTX 4090 | 24 GB | $0.35 · med $0.47 | $0.34 | $0.34 | $0.34/hr | Runpod |
| NVIDIA GeForce RTX 5090 | 32 GB | $0.37 · med $0.61 | $0.69 | $0.69 | $0.37/hr | Vast.ai |
| NVIDIA RTX 6000 Ada Generation | 48 GB | $0.54 · med $0.57 | $0.74 | $0.74 | $0.54/hr | Vast.ai |
| NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | 96 GB | — | $1.69 | $1.69 | $1.69/hr | Runpod |
| NVIDIA H100 SXM | 80 GB | $1.73 · med $2.10 | $2.69 | $2.69 | $1.73/hr | Vast.ai |
| NVIDIA H100 PCIe | 80 GB | $2.29 · med $2.44 | $1.99 | $1.99 | $1.99/hr | Runpod |
| AMD Instinct MI300X | 192 GB | — | $2.39 | — | $2.39/hr | Runpod |
| NVIDIA H200 SXM | 141 GB | $3.93 · med $4.47 | $3.59 | $3.59 | $3.59/hr | Runpod |
| NVIDIA B200 | 192 GB | $6.25 · med $8.38 | $5.98 | $5.98 | $5.98/hr | Runpod |
Cheapest way to run each model in the cloud
The cheapest live-priced GPU each model fits on at 16k context, computed from the model's own config — and what a month of it costs.
| Model | Cheapest GPU that fits | Quant | $/hr | 8h/day · mo | 24/7 · mo |
|---|---|---|---|---|---|
| Qwen3 235B-A22B (MoE) | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GBRunpod | Q2_K95 GB | $1.69 | $406 | $1217 |
| Qwen3.5 122B-A10B (MoE) | NVIDIA A100 80GB PCIe · 80 GBVast.ai | Q4_K_M72 GB | $0.24 | $58 | $175 |
| gpt-oss 120B (MoE) | NVIDIA L40S · 48 GBVast.ai | Q2_K47 GB | $0.20 | $48 | $144 |
| Llama 4 Scout 17B-16E (MoE) | NVIDIA L40S · 48 GBVast.ai | Q2_K44 GB | $0.20 | $48 | $144 |
| GLM-4.5-Air (MoE) | NVIDIA L40S · 48 GBVast.ai | Q2_K45 GB | $0.20 | $48 | $144 |
| Qwen3-Next 80B-A3B (MoE) | NVIDIA Tesla V100 32GB SXM2 · 32 GBVast.ai | IQ3_XS32 GB | $0.07 | $16 | $48 |
| Qwen3-Coder-Next 80B-A3B (MoE) | NVIDIA Tesla V100 32GB SXM2 · 32 GBVast.ai | IQ3_XS32 GB | $0.07 | $16 | $48 |
| DeepSeek R1 Distill 70B | NVIDIA L40S · 48 GBVast.ai | Q4_K_M46 GB | $0.20 | $48 | $144 |
| Mixtral 8x7B (MoE) | NVIDIA Tesla V100 32GB SXM2 · 32 GBVast.ai | Q4_K_M29 GB | $0.07 | $16 | $48 |
| Qwen3.5 35B-A3B (MoE) | NVIDIA RTX A4000 · 16 GBVast.ai | Q2_K15 GB | $0.06 | $15 | $45 |
| Qwen3.6 35B-A3B (MoE) | NVIDIA RTX A4000 · 16 GBVast.ai | Q2_K15 GB | $0.06 | $15 | $45 |
| Qwen2.5 Coder 32B | NVIDIA Tesla V100 32GB SXM2 · 32 GBVast.ai | Q6_K30 GB | $0.07 | $16 | $48 |
| DeepSeek R1 Distill 32B | NVIDIA Tesla V100 32GB SXM2 · 32 GBVast.ai | Q6_K30 GB | $0.07 | $16 | $48 |
| Qwen3 32B | NVIDIA Tesla V100 32GB SXM2 · 32 GBVast.ai | Q6_K30 GB | $0.07 | $16 | $48 |
| Gemma 4 31B | NVIDIA RTX A4000 · 16 GBVast.ai | Q2_K15 GB | $0.06 | $15 | $45 |
| Qwen3-Coder 30B-A3B (MoE) | NVIDIA RTX A4000 · 16 GBVast.ai | Q2_K14 GB | $0.06 | $15 | $45 |
| Qwen3 30B-A3B (MoE) | NVIDIA RTX A4000 · 16 GBVast.ai | Q2_K14 GB | $0.06 | $15 | $45 |
| Qwen3.8 27B | NVIDIA RTX A4000 · 16 GBVast.ai | IQ4_XS16 GB | $0.06 | $15 | $45 |
| Qwen3.6 27B | NVIDIA RTX A4000 · 16 GBVast.ai | IQ4_XS16 GB | $0.06 | $15 | $45 |
| Qwen3.5 27B | NVIDIA RTX A4000 · 16 GBVast.ai | IQ4_XS16 GB | $0.06 | $15 | $45 |
| Gemma 4 26B-A4B (MoE) | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q2_K11 GB | $0.03 | $8 | $25 |
| Mistral Small 24B | NVIDIA RTX A4000 · 16 GBVast.ai | Q4_016 GB | $0.06 | $15 | $45 |
| gpt-oss 20B (MoE) | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | IQ4_XS12 GB | $0.03 | $8 | $25 |
| DeepSeek R1 Distill 14B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q4_012 GB | $0.03 | $8 | $25 |
| Qwen3 14B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q4_K_M12 GB | $0.03 | $8 | $25 |
| Phi-4 14B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q4_012 GB | $0.03 | $8 | $25 |
| Gemma 3 12B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q6_K11 GB | $0.03 | $8 | $25 |
| Gemma 4 12B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q6_K10 GB | $0.03 | $8 | $25 |
| Qwen3.5 9B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q8_011 GB | $0.03 | $8 | $25 |
| Qwen3 8B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q8_011 GB | $0.03 | $8 | $25 |
| Gemma 4 E4B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q8_09 GB | $0.03 | $8 | $25 |
| Qwen2.5 7B Instruct | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q8_09 GB | $0.03 | $8 | $25 |
| Mistral 7B Instruct v0.3 | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | Q8_010 GB | $0.03 | $8 | $25 |
| Gemma 4 E2B | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | F1610 GB | $0.03 | $8 | $25 |
| Llama 3.2 3B Instruct | NVIDIA GeForce RTX 3060 12GB · 12 GBVast.ai | F169 GB | $0.03 | $8 | $25 |
Monthly figures are the live $/hr × 240h (8h/day) or × 720h (24/7). Whether renting beats buying depends on your own usage — the rent-vs-buy break-even walks through it honestly.
Get a note when H100 or 5090 rentals drop
Prices have fallen 60–75% from their 2024 peak and still move week to week. We watch them hourly; you get the drops that matter, not the noise.
The Aliteq brief
The tech worth knowing — hardware, AI, gaming, deals. No spam, unsubscribe anytime.
Referral linkThe cheapest spot marketplace
A marketplace of independent hosts — usually the lowest $/hr anywhere, with reliability that varies by host. Best for interruptible work.
Referral linkManaged pods + serverless
Predictable on-demand pods, one-click templates and per-second serverless — the easiest way to go from zero to a running GPU.
How to read this page
How often are these cloud GPU prices updated?
Hourly. Our worker pulls live offers from each provider's API and stores the minimum, 25th-percentile and median $/hr per GPU. The capture time is shown on the page — never quote a price without its timestamp.
Which cloud GPU providers are tracked?
2 today: Vast.ai (a spot marketplace of independent hosts — cheapest, variable reliability) and Runpod (managed on-demand pods and spot). We add providers only where a live, legally usable price API exists; we don't scrape.
What's the difference between spot and on-demand GPU pricing?
Spot (interruptible) capacity is cheaper but can be reclaimed by the provider mid-job — fine for inference and checkpointed training. On-demand is reserved while you run it and costs more. The table shows both where a provider offers them.
How is 'cheapest GPU that runs a model' calculated?
From each model's own config (layers, hidden size, heads) we compute the VRAM it needs at each quantisation at 16k context (bits-per-weight constants validated to a 0.7% median error), then pick the cheapest live-priced GPU it fits on. It is an estimate of fit and cost, not a benchmark.
Disclosure:provider links may be referral links — if you sign up through one we may earn a commission at no cost to you. That never changes the ranking: every price on this page is the live figure from the provider's API, cheapest first. Sponsored placements are labelled. Provider names and logos are their owners' trademarks, used to identify the services compared; no partnership or endorsement is implied. Prices are pulled hourly; VRAM fit is an estimate from each model's config, not a benchmark.