The cheapest RTX A6000 on the table right now is $0.160 per GPU-hour at Vast.ai (spot), out of 28 offers from 11 providers. The RTX A6000 carries 48 GB of VRAM on NVIDIA's Ampere generation. That is peer/marketplace capacity — rented from other users' machines, and not directly comparable to a dedicated instance.
On-demand pricing for the same card spans $0.200 to $1.09 per GPU-hour — a 5.5× spread between the cheapest and the most expensive provider for identical silicon. That gap is the entire reason this table exists.
Cheapest by pricing model: on-demand $0.200 at Octa · spot $0.160 at Vast.ai.
| Provider | Tier | $/GPU-hr | Pricing | Node | Commit | In stock | |
|---|---|---|---|---|---|---|---|
| Vast.ai | marketplace | $0.160 | spot | 1, 2× GPU | — | yes | rent |
| Octa | marketplace | $0.200 | on-demand | 1× GPU | — | yes | rent |
| Vast.ai | marketplace | $0.281 | on-demand | 1× GPU | — | yes | rent |
| Thunder Compute * | dedicated | $0.350 | on-demand | 1× GPU | — | yes | rent |
| Verda | dedicated | $0.358 | spot | 1–8× GPU | — | — | rent |
| Vast.ai | marketplace | $0.361 | on-demand | 2× GPU | — | yes | rent |
| Vast.ai | marketplace | $0.391 | spot | 4× GPU | — | yes | rent |
| Vast.ai | marketplace | $0.401 | on-demand | 4× GPU | — | yes | rent |
| Hyperstack | dedicated | $0.500 | on-demand | 1× GPU | — | — | rent |
| Massed Compute | dedicated | $0.550 | on-demand | 1–8× GPU | — | — | rent |
| Runpod | dedicated | $0.590 | on-demand | 1× GPU | — | yes | rent |
| Prime Intellect | dedicated | $0.607 | on-demand | 1× GPU | — | yes | rent |
| Verda | dedicated | $0.717 | on-demand | 1–8× GPU | — | — | rent |
| Koyeb | dedicated | $0.750 | on-demand | 1× GPU | — | — | rent |
| Seeweb | dedicated | $0.828 | on-demand | 1× GPU | — | — | rent |
| Lambda Labs | dedicated | $1.09 | on-demand | 1–4× GPU | — | — | rent |
How much does an RTX A6000 cost per hour?
As of the latest scrape, $0.160 per GPU-hour at Vast.ai is the cheapest RTX A6000 offer across 11 tracked cloud providers. The cheapest on-demand rate is $0.200 per GPU-hour at Octa, and the most expensive on-demand rate is $1.09 at Lambda Labs.
Which cloud is cheapest for the RTX A6000?
Vast.ai at $0.160 per GPU-hour on spot capacity. Prices move constantly, so this page is regenerated from the live scrape every 15 minutes. Note that marketplace tiers are peer hardware and are not directly comparable to dedicated capacity.
Is spot RTX A6000 capacity cheaper?
Yes — the cheapest spot RTX A6000 is $0.160 per GPU-hour at Vast.ai, -20% versus the cheapest on-demand rate of $0.200. Spot instances can be reclaimed by the provider at any time, so they suit checkpointed training and batch inference rather than long-lived services.
How many GB of VRAM does the RTX A6000 have?
48 GB, on the Ampere architecture. Multi-GPU instances multiply that: an 8× RTX A6000 node exposes 384 GB of GPU memory in total.