Now offering crypto payments →

GPU Cloud Pricing · Ampere

RTX A6000 Cloud Pricing

The Ampere workstation flagship: 48 GB with ECC, widely stocked and consistently one of the cheapest 48 GB rentals available.

In stock — 44 GPUs available nowFrom $0.450/GPU/hr
Live pricing

RTX A6000 price per GPU-hour

GPU.ai rates are the live fleet floor — the cheapest provider with stock, passed through at cost. Competitor rates are public on-demand list prices.

Provider$ / GPU / hr
GPU.ai — Secure Cloud$0.450
GPU.ai — Community Cloud$0.450
CoreWeaveNot available
AWSNot available
AzureNot available

Need scale? Real 4× RTX A6000 nodes are in inventory from $0.450/GPU/hr.

Available regions: Europe East · Europe West · US Central · US East

How these prices are computed

GPU.ai prices are read live from our aggregated fleet of 12+ GPU clouds and normalized to a per-GPU hourly rate (a node's price is divided by its GPU count). We charge the provider's raw rate with zero markup and bill per second. Competitor figures are each provider's public on-demand list rate for the closest equivalent SKU — never spot, reserved, or committed-use discounts. Stock counts reflect launchable inventory, not theoretical capacity. Last updated 2026-08-17; this page refreshes hourly.

Specifications

NVIDIA RTX A6000 specs

ArchitectureAmpere
VRAM48 GB GDDR6
Memory bandwidth768 GB/s
FP16 tensor (dense)
CUDA cores10,752
Power (TDP)300 W
InterconnectPCIe 4.0
Released2020
What fits

What runs on 48 GB?

Minimum RTX A6000 count needed to hold popular open models in VRAM, at FP16 and 4-bit quantization.

ModelParamsFP164-bit
Llama 3.1 8B8B1× RTX A60001× RTX A6000
Mistral 7B7B1× RTX A60001× RTX A6000
Gemma 2 27B27B2× RTX A60001× RTX A6000
Qwen2.5 32B32B2× RTX A60001× RTX A6000
Llama 3.1 70B70B4× RTX A60001× RTX A6000
Qwen2.5 72B72B4× RTX A60002× RTX A6000
Mixtral 8x22B141B MoE8× RTX A60002× RTX A6000
Llama 3.1 405B405BDoesn't fit8× RTX A6000
FLUX.1 dev12B1× RTX A60001× RTX A6000
SDXL3.5B1× RTX A60001× RTX A6000
Whisper large-v31.5B1× RTX A60001× RTX A6000

Weights-only estimates with a 20% margin for KV cache and activations at moderate context. Long contexts, large batches, and training need substantially more memory.

FAQ

RTX A6000 rental questions

How much does it cost to rent an RTX A6000 in the cloud?

RTX A6000 cloud instances on GPU.ai currently start at $0.450 per GPU per hour, billed per second. That is the live floor price across every provider in our fleet — we route your launch to the cheapest provider with stock and add zero markup.

How much VRAM does the RTX A6000 have?

The NVIDIA RTX A6000 has 48 GB of GDDR6 memory with up to 768 GB/s of bandwidth. GPU.ai reports the minimum VRAM actually delivered across our fleet, so the figure you see at launch is the figure you get.

Can I rent a multi-GPU RTX A6000 node?

Yes — real 4× RTX A6000 nodes are launchable right now, from $0.450 per GPU per hour. We only advertise node sizes that exist in live inventory, not theoretical configurations.

How does GPU.ai's RTX A6000 pricing compare to AWS, Azure, and CoreWeave?

GPU.ai aggregates a dozen-plus GPU clouds and passes through each provider's raw price with no markup, so the same silicon is typically far cheaper than hyperscaler list rates. The comparison table on this page shows the current public on-demand list prices side by side.

How does billing work?

Billing is per second, starting when your instance is SSH-ready and stopping the moment you terminate. There are no minimum commitments, no reservation fees, and no egress surprises — you pay the listed hourly rate pro-rated to the second.