RTX A6000 pricing on Vast.ai
Every Vast.ai RTX A6000 offering we track, normalized to a per-GPU hourly rate and ranked against 25 providers with current RTX A6000 pricing.
The cheapest RTX A6000 we currently track is $0.330/hr on Runpod.
Vast.ai RTX A6000 rates
Hourly prices per GPU. Multi-GPU rows show the per-GPU rate, not the instance total.
| Price / GPU-hr | Type | GPUs |
|---|---|---|
| $0.391 | On-demand | 1 |
| $0.402 | On-demand | 2 |
RTX A6000 specifications
- VRAM
- 48GB
- Architecture
- Ampere
- CUDA Cores
- 10,752
- Tensor Cores
- 336
- Memory Bandwidth
- 768 GB/s
- TDP
- 300W
RTX A6000 on other providers
- Runpod$0.330/hr
- Hyperstack$0.350/hr
- Thunder Compute$0.350/hr
- Verda$0.394/hr
- gpu.ai$0.400/hr
- Lium.io$0.420/hr
- QuantaCloud$0.480/hr
- IO.NET$0.493/hr
- Massed Compute$0.500/hr
- Shadeform$0.500/hr
- Omega Gradient$0.530/hr
- Aquanode$0.550/hr
- Hexgrid Cloud$0.550/hr
- Oblivus$0.550/hr
- Sesterce$0.550/hr
- Runcrate$0.570/hr
- Fluence Cloud$0.590/hr
- 1Legion$0.660/hr
- Koyeb$0.750/hr
- Seeweb$0.828/hr
- VoltageGPU$0.840/hr
- AceCloud$0.927/hr
- Paperspace$0.945/hr
- Lambda Labs$1.09/hr
About Vast.ai
Vast.ai is a GPU marketplace with live, supply-and-demand pricing across community hosts and Secure Cloud datacenter partners. Instances are provisioned through the console, CLI, Python SDK, or REST API and billed per second.
Frequently Asked Questions
How much does the RTX A6000 cost on Vast.ai?
Vast.ai lists the RTX A6000 from $0.391 per GPU-hour across 2 tracked configurations. Prices are collected daily — see the table above for the current rates.
Is Vast.ai the cheapest place to rent the RTX A6000?
Vast.ai ranks #4 of 25 providers we track with current RTX A6000 pricing. The cheapest right now is Runpod. Price is only one factor — region availability, network, and storage costs differ between providers.
Which RTX A6000 configurations does Vast.ai offer?
We currently track 2 RTX A6000 offerings from Vast.ai, covering the GPU counts, pricing types, and regions listed in the table above. Every price is normalized to a per-GPU hourly rate so it can be compared across providers.