Runpod lists 19 GPU models across 19 configurations, starting at $0.250 per GPU-hour for the RTX A4000. It is the cheapest dedicated provider we track for 5 of its 19 GPU-and-pricing-model combinations: RTX A5000 (on-demand), RTX 3090 (on-demand), A40 (on-demand), L40 (on-demand), MI350X (on-demand).
| GPU | VRAM | Pricing | Runpod $/GPU-hr | Best dedicated | Difference | Cheapest at | |
|---|---|---|---|---|---|---|---|
| RTX A4000 | 16 GB | on-demand | $0.250 | $0.150 | +67% | Hyperstack | rent |
| RTX A5000 | 24 GB | on-demand | $0.270 | $0.270 | cheapest | — | rent |
| RTX 3090 | 24 GB | on-demand | $0.500 | $0.500 | cheapest | — | rent |
| A40 | 48 GB | on-demand | $0.590 | $0.590 | cheapest | — | rent |
| L4 | 24 GB | on-demand | $0.590 | $0.425 | +39% | Seeweb | rent |
| RTX A6000 | 48 GB | on-demand | $0.590 | $0.500 | +18% | Hyperstack | rent |
| L40 | 48 GB | on-demand | $0.820 | $0.820 | cheapest | — | rent |
| RTX 4090 | 24 GB | on-demand | $0.890 | $0.580 | +53% | Spheron | rent |
| RTX 6000 Ada | 48 GB | on-demand | $0.990 | $0.750 | +32% | Prime Intellect | rent |
| L40S | 48 GB | on-demand | $1.09 | $0.550 | +98% | Novita | rent |
| RTX 5090 | 32 GB | on-demand | $1.19 | $0.520 | +129% | GPU.ai | rent |
| A100 PCIe | 80 GB | on-demand | $1.79 | $1.20 | +49% | Prime Intellect | rent |
| A100 SXM | 80 GB | on-demand | $1.79 | $1.07 | +67% | GPU.ai | rent |
| RTX PRO 6000 | 96 GB | on-demand | $2.49 | $1.40 | +78% | Seeweb | rent |
| H200 | 141 GB | on-demand | $3.79 | $2.91 | +30% | Seeweb | rent |
| H100 SXM | 80 GB | on-demand | $3.99 | $1.79 | +123% | Cudo Compute | rent |
| MI350X | 288 GB | on-demand | $5.49 | $5.49 | cheapest | — | rent |
| B200 | 192 GB | on-demand | $7.99 | $4.09 | +95% | Together AI | rent |
| B300 | 288 GB | on-demand | $8.99 | $4.99 | +80% | Together AI | rent |
How much does a GPU cost on Runpod?
Runpod starts at $0.250 per GPU-hour for the RTX A4000. It lists 19 GPU models in total: A100 PCIe, A100 SXM, A40, B200, B300, H100 SXM, H200, L4, L40, L40S.
Is Runpod cheaper than other GPU clouds?
For 5 of the 19 GPU and pricing-model combinations it offers, Runpod is the cheapest dedicated provider on this table — including RTX A5000, RTX 3090, A40, L40. For the rest, the table above names the provider that beats it and by how much. Comparisons are like-for-like on GPU, pricing model and capacity tier.
Which GPUs does Runpod offer?
19 models: A100 PCIe, A100 SXM, A40, B200, B300, H100 SXM, H200, L4, L40, L40S, MI350X, RTX 3090, RTX 4090, RTX 5090, RTX 6000 Ada, RTX A4000, RTX A5000, RTX A6000, RTX PRO 6000. Availability changes; the "in stock" flags on each GPU page reflect the last scrape.