RunPod operates a dual-tier marketplace: community GPUs at ultra-low spot prices and a SOC 2-compliant Secure Cloud for production inference. Per-second billing, instant provisioning, and a broad catalog spanning H100, A100, RTX, and even MI300X accelerators make it flexible for projects of any scale.
NVIDIA RTX A6000 cloud pricing
- Vendor
- NVIDIA
- VRAM
- 48 GB
- Architecture
- Ampere
- FP16
- 155 TFLOPS
- Launched
- 2020
Lowest
$0.319
Median
$0.490
Highest
$0.760
9 results
| Provider | Plan | Price | Regions | Visit | ||||
|---|---|---|---|---|---|---|---|---|
|
|
RTX A6000 (Secure Cloud) On-demand | 1 | 48 GB | 9 | 50 GB |
$0.490
/GPU-hr
Verified
|
3 countries | Visit → |
|
|
RTX A6000 (Secure Cloud) Reserved | 1 | 48 GB | 9 | 50 GB |
$0.319
/GPU-hr
Verified
|
3 countries | Visit → |
|
|
RTX A6000 (per GPU) On-demand | 1 | 48 GB | 12 | 58 GB |
$0.500
/GPU-hr
Verified
|
1 country | Visit → |
|
|
RTX A6000 (per GPU) Reserved | 1 | 48 GB | 12 | 58 GB |
$0.325
/GPU-hr
Verified
|
1 country | Visit → |
|
|
RTX A6000 (marketplace) On-demand | 1 | 48 GB | 8 | 64 GB |
$0.550
/GPU-hr
Verified
|
3 countries | Visit → |
|
|
RTX A6000 (marketplace) Spot | 1 | 48 GB | 8 | 64 GB |
$0.330
/GPU-hr
Verified
|
3 countries | Visit → |
|
|
RTX A6000 (marketplace) Reserved | 1 | 48 GB | 8 | 64 GB |
$0.357
/GPU-hr
Verified
|
3 countries | Visit → |
|
|
RTX A6000 machine On-demand | 1 | 48 GB | 8 | 45 GB |
$0.760
/GPU-hr
Verified
|
2 countries | Visit → |
|
|
RTX A6000 machine Reserved | 1 | 48 GB | 8 | 45 GB |
$0.494
/GPU-hr
Verified
|
2 countries | Visit → |
Providers offering this GPU
Hyperstack is a next-generation GPU cloud platform offering H100, A100, B200, L40S, and RTX-class accelerators at aggressive on-demand and reserved rates. With data centers in London and Oslo, Terraform support, and fast API-driven provisioning, it targets teams that want hyperscaler-grade GPU availability without the lock-in.
Paperspace, now part of DigitalOcean, offers GPU cloud compute with a developer-friendly notebook environment and a genuine free GPU tier for experimentation. With predictable on-demand pricing across H100, A100, and A6000 instances, it bridges the gap between zero-setup Jupyter notebooks and production-grade GPU infrastructure.
Vast.ai is a decentralized GPU marketplace where host operators list idle accelerators at market-driven prices - often the lowest spot rates anywhere. The trade-off is variable reliability, no compliance certs, and community-grade support; ideal for cost-sensitive experimentation, fine-tuning, and batch inference where occasional interruption is acceptable.
Frequently asked questions
How much does an NVIDIA RTX A6000 cost per hour in the cloud?
The lowest on-demand NVIDIA RTX A6000 price we track is $0.319 per GPU-hour. Spot and reserved rates are usually lower; sort the table above by price to see the current rate from every provider.
What is the cheapest NVIDIA RTX A6000 cloud provider?
Sort the table by price (low to high) to see the cheapest NVIDIA RTX A6000 provider right now. Marketplace and spot providers often undercut hyperscalers by a wide margin for the same NVIDIA RTX A6000.
Which cloud providers offer NVIDIA RTX A6000 GPUs?
Every provider with published NVIDIA RTX A6000 availability is listed above, with per-hour pricing, the number of GPUs per instance, region coverage, and on-demand, spot, and reserved rates.
Is spot NVIDIA RTX A6000 cheaper than on-demand?
Yes. Spot (preemptible) capacity is typically 40-70% cheaper than on-demand but can be reclaimed at short notice. Use the pricing-mode filter to compare on-demand, spot, and reserved rows side by side.
How much VRAM does the NVIDIA RTX A6000 have?
The NVIDIA RTX A6000 ships with 48 GB of VRAM. Larger VRAM lets you fit bigger models and batch sizes without sharding.
Is the NVIDIA RTX A6000 good for AI training and inference?
The NVIDIA RTX A6000 is used for both LLM training and inference. Match its VRAM and throughput (shown above) to your model size, and use spot capacity for fault-tolerant training to cut costs.