RRunyard Index
Runyard / GPU Index / NVIDIA RTX A6000
NVIDIA
Rental price index

NVIDIA RTX A6000

Ampere workstation card, 48 GB, a value favourite.

Prices collected 2026-10-11 · 16 providers, 38 configurations

Jump to:At a glancePricingChangesAI modelsBuy vs rentSpecsFAQAlternatives
On-demandOn-demand (archive, Lambda only)ReservedSpot
$0.00$0.25$0.50$0.75$1.00Oct 5Oct 7Oct 9Oct 11

Index median price per GPU per hour, by billing type. Nothing is interpolated.

At a glance

Median on-demand
$0.58/GPU/hr
Cheapest on-demand
$0.33RunPod Community Cloud
Floor, any billing
$0.33incl. spot
Per month at 720h
$418

NVIDIA RTX A6000 pricing by provider

One card per provider, cheapest first. A configuration is one priced unit — an instance type, a SKU, a marketplace offer — and the per-GPU price is that unit's price divided by its GPU count. Open a card to see every configuration with its vCPU, RAM and region where the provider publishes them.

16 providers · 36 configurations
Vast.aiIn stock
USA12 configs1x–4xcollected 2026-10-11
On-Demand from $0.39
From
$0.39 / GPU / hr
On-Demand · Arizona, USVisit website →
GPU.aiIn stock
UAE1 config1xcollected 2026-10-11
On-Demand from $0.40
From
$0.40 / GPU / hr
On-DemandVisit website →
io.netIn stock
USA4 configs1x–8xcollected 2026-10-11
On-Demand from $0.49
From
$0.49 / GPU / hr
On-DemandVisit website →
HyperstackIn stock
UK1 config1xcollected 2026-10-11
On-Demand from $0.50Spot from $0.40Reserved from $0.35
From
$0.50 / GPU / hr
On-DemandVisit website →
BeamIn stock
USA1 config1xcollected 2026-10-11
On-Demand from $0.54
From
$0.54 / GPU / hr
On-DemandVisit website →
OblivusIn stock
UK3 configs1xcollected 2026-10-11
On-Demand from $0.55
From
$0.55 / GPU / hr
On-DemandVisit website →
RuncrateIn stock
1 config1xcollected 2026-10-11
On-Demand from $0.65
From
$0.65 / GPU / hr
On-DemandVisit website →
KoyebIn stock
France1 config1xcollected 2026-10-11
On-Demand from $0.75
From
$0.75 / GPU / hr
On-DemandVisit website →
SeewebIn stock
Italy1 config1xcollected 2026-10-11
On-Demand from $0.83
From
$0.83 / GPU / hr
On-DemandVisit website →
LambdaIn stock
USA3 configs1x–4xcollected 2026-10-11
On-Demand from $1.09
From
$1.09 / GPU / hr
On-DemandVisit website →

Recent price changes

Every time a provider's median for the NVIDIA RTX A6000 moved between two consecutive snapshots. A listing appearing or vanishing is not a price change and is not shown.

WhenProviderFromToChange
2026-10-11 09:14DataCrunch (Verda)$0.69$0.71+2%
2026-10-10 08:53GPU.ai$0.41$0.40-1.2%
2026-10-09 09:31RunPod Secure Cloud$0.53$0.59+11.3%
2026-10-09 09:31DataCrunch (Verda)$0.68$0.69+1.5%
2026-10-08 09:24io.net$0.64$0.49-22.9%
2026-10-08 09:24GPU.ai$0.40$0.41+1.3%
2026-10-07 09:10io.net$0.49$0.64+29.8%
2026-10-05 09:33DataCrunch (Verda)$0.67$0.67+1.1%
2026-10-03 08:31DataCrunch (Verda)$0.66$0.67+1.1%
2026-10-02 08:54Runcrate$0.74$0.65-12.2%

Spot, reserved and where it is cheapest

Spot median
$0.4031% off · 1 providers
Reserved median
$0.3540% off · 1 providers
UAE providers
$0.40median of 1
USA providers
$0.54median of 9

By provider country: UAE $0.40 (1) · USA $0.54 (9) · UK $0.65 (2) · Finland $0.71 (1) · France $0.75 (1) · Italy $0.83 (1). Full breakdown →

What fits on a NVIDIA RTX A6000

Weights + KV cache at 8K context + runtime overhead, against 43 GB usable of the 48 GB on the card. Capacity follows total parameters, even for mixture-of-experts models — any expert may be needed next. Where one card is not enough, the table says how many are, and prices the set at today's median.

ModelParams4-bit8-bit16-bit
Kimi K32.8T104B active37× GPU$21.46/hr70× GPU$40.60/hr130× GPU$75.40/hr
DeepSeek V4.1-Flash552B16B active8× GPU$4.64/hr14× GPU$8.12/hr26× GPU$15.08/hr
Llama 4 Maverick400B17B active6× GPU$3.48/hr10× GPU$5.80/hr19× GPU$11.02/hr
gpt-oss-120b117B5.1B active2× GPU$1.16/hr3× GPU$1.74/hr6× GPU$3.48/hr
Llama 3.1 70B70B2× GPU$1.16/hr2× GPU$1.16/hr4× GPU$2.32/hr
Gemma 4 31B31B✓ 21.2 GB~35 tok/s · $4.6/M tok✓ 36.7 GB~19 tok/s · $8.48/M tok2× GPU$1.16/hr
Qwen3 Coder 30B-A3B30.5B3.3B active✓ 19 GB~331 tok/s · $0.49/M tok✓ 34.3 GB~175 tok/s · $0.92/M tok2× GPU$1.16/hr
Qwen3.8 27B27B✓ 18.7 GB~40 tok/s · $4.03/M tok✓ 32.2 GB~21 tok/s · $7.67/M tok2× GPU$1.16/hr
gpt-oss-20b21B3.6B active✓ 13.7 GB~303 tok/s · $0.53/M tok✓ 24.2 GB~161 tok/s · $1/M tok2× GPU$1.16/hr
Llama 3.1 8B8B✓ 6.9 GB~137 tok/s · $1.18/M tok✓ 10.9 GB~72 tok/s · $2.24/M tok✓ 18.4 GB~38 tok/s · $4.24/M tok

tok/s is decode throughput from memory bandwidth, derated 20%, single stream — an estimate, not a benchmark. $/M tok is the hourly median divided by that rate: the one-user floor for a million generated tokens. Set cost uses today's median × GPUs required.

Buy or rent a RTX A6000?

Approx. list price
$4,500not tracked
Rent, per month
$418at median, 720 h
Break-even
7,759 h≈ 10.8 months

Rent for fewer than about 10.8 months of continuous use and renting wins on the card alone; past that, owning does — before the server, power, cooling and the person who keeps it running, which for a datacenter card are not small. The list price is a typical quoted figure and is not tracked by the index.

Specifications

Memory48 GB GDDR6
Memory bandwidth768 GB/s
ArchitectureAmpere
VendorNVIDIA
ClassWorkstation
Released2020-10

Bandwidth is listed because it governs generation speed: each token streams the active weights once, so tokens per second is bandwidth divided by bytes read. TFLOPs decide prompt processing and training, not how fast text appears.

Alternatives and comparisons

RTX A6000 vs RTX 6000 AdaPrice, memory, what fits, cost per tokenRTX A6000 vs RTX A5000Price, memory, what fits, cost per tokenRTX A6000 vs RTX 4090Price, memory, what fits, cost per tokenRTX A6000 vs A40Price, memory, what fits, cost per token
NVIDIA RTX 6000 Ada48 GB · $0.89/hr median · 10 providersNVIDIA RTX A500024 GB · $0.26/hr median · 8 providersNVIDIA RTX A400016 GB · $0.16/hr median · 8 providers

Questions

How much does it cost to rent a NVIDIA RTX A6000?

As of 2026-10-11, the median on-demand price across 16 providers is $0.58 per GPU-hour, about $418 a month at 720 hours. The cheapest we saw was $0.33 at RunPod Community Cloud.

Why do prices for the same GPU vary so much?

Hyperscalers bundle CPU, RAM and network into an instance price and charge for the ecosystem around it. Neoclouds sell the GPU more directly. Marketplaces are independent hosts competing on price, with the trade-offs of shared, third-party hardware. The per-GPU figure is the instance price divided by GPU count, which is the only way to compare an 8-GPU node with a single-card listing.

Is the median the price I will pay?

No — it is the middle of the market. Each provider's own median is taken first so a provider with many instance sizes counts once, then the median across providers. Spot and reserved rates are excluded from it; they set the floor shown separately. Use it to judge whether a quote is high or low, then verify with the provider.

Which models can a NVIDIA RTX A6000 run?

With 48 GB per GPU, the table above shows which reference models fit on one card at 4, 8 and 16-bit, using the same memory arithmetic as the rest of Runyard: weights plus KV cache plus runtime overhead, with capacity following total parameters even for mixture-of-experts models. Where a model needs more than one GPU it says how many and what that set costs at today's median.

Own the hardware instead? Work out what your card holds with the same arithmetic.
Check what fits →