GPU Rental Prices
SearchCtrl K

RTX A6000 rental price: from $0.35/hr today

The cheapest on-demand RTX A6000 today is $0.35 an hour at Thunder Compute, checked 22 October 2026; the typical provider charges $0.57.

Cheapest on-demand · 48 GB · today$0.35/GPU-hourThunder Compute
  • Community $0.33 RunPod, interruptible
  • Reserved $0.35 Hyperstack, term not published
  • Serverless $0.75 Koyeb, per second
  • In stock $0.59 RunPod, stock reported
  • Provider median $0.57
  • Highest on-demand $1.09
  • 10 offers
  • 8 providers
  • Cheapest the same as 90 days ago
  • Same offers, 90 days: +7.3%
  • Source thundercompute.com

RTX A6000 offers: 10 configurations from 8 providers

More filters: provider, memory, node size, stock, place, sort, price unit

“Machines in” filters the 1 of 10 offers whose provider says where the machine is; the others are under “Place not stated”.

10 offers; rates are per GPU and the node total is for the smallest listed node.

7 providers with on-demand offers, cheapest first. Tap a provider for its configurations.

GPU / providerBilling$/GPU-hourNode · total per hourRent
RTX A6000 · Thunder Compute48 GBon-demand$0.351× $0.35Rent →
checked 22 OctDetails
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · TensorDock48 GBon-demand$0.45–Rent →
checked 22 OctDetails
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · Hyperstack48 GBon-demand$0.50–Rent →
checked 22 OctDetails
RAM
Up to 58 GB RAM; configuration-dependent
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · Massed Compute48 GBon-demand$0.571× $0.57Rent →
checked 22 OctDetails
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · RunPod48 GBsecure cloud$0.59+11.3% in 30 days–In stock: lowRent →
checked 22 OctDetails
CPU
9 vCPU
RAM
50 GB RAM
Region
Europe
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · Verda (DataCrunch)48 GBon-demand$0.78+27.9% in 30 days1× $0.78Rent →
checked 22 OctDetails
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · Lambda48 GB · ×3 listingson-demand$1.091× $1.09Rent →
checked 22 OctDetails
CPU
14 vCPU
RAM
100 GiB
Disk
512 GiB SSD
Configurations
4x NVIDIA A6000; 2x NVIDIA A6000; 1x NVIDIA A6000
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · RunPod48 GBcommunity cloud$0.33–Rent →
checked 22 OctDetails
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · Hyperstack48 GBreserved / committedTerm and minimum volume not published in this table; confirm reservation quoteStarting rate$0.35–Rent →
checked 22 OctDetails
Checked
22 October 2026

Source price ↗ · Report this price

RTX A6000 · Koyeb48 GBserverless$0.75$0.000208/sec–Rent →
checked 22 OctDetails
Checked
22 October 2026

Source price ↗ · Report this price

Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.

Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.

Cite this data

GPU Rental Prices, "RTX A6000 rental price: from $0.35/GPU-hour", prices checked 22 October 2026, https://gpurentalprices.com/rtx-a6000

Quote it with a link to this page. Downloads of the whole dataset are on Data & API.

On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.

RTX A6000 price history and range

Date range for the RTX A6000 chart
  • Cheapest on-demand$0.35(the same as 90 days ago)
  • Provider median$0.57
  • Cheapest spot$0.33
Daily, 2026-07-05 to 2026-10-22, from our own price checks. The provider median counts each provider's cheapest on-demand rate once and is drawn only on days with three or more providers. Missing days stay gaps.

RTX A6000 price range by billing type

Per GPU-hour, today's offers. Axis $0 to $2.00.

On-demand7 offers · 7 providersfrom $0.35median $0.57to $1.09
Spot & community1 offer · 1 providerfrom $0.33to $0.33
Reserved1 offer · 1 providerfrom $0.35to $0.35
Serverless1 offer · 1 providerfrom $0.75to $0.75

CheapestProvider median (each provider's cheapest rate counted once; shown with three or more providers)

Price changes

  • 30 days: +7.3% across 5 matching on-demand configurations since 22 September 2026.
  • 90 days: +7.3% across 5 matching on-demand configurations since 24 July 2026.

Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region (RunPod's place is where that day's stock sat, so it is not matched). New listings are not counted as price changes. Full ledger on the history hub.

RTX A6000 daily figures (110 days)
DateCheapest on-demandProvider medianCheapest spot
2026-10-22$0.35$0.57$0.33
2026-10-21$0.35$0.57$0.33
2026-10-20$0.35$0.57$0.33
2026-10-19$0.35$0.57$0.33
2026-10-18$0.35$0.57$0.33
2026-10-17$0.35$0.57$0.33
2026-10-16$0.35$0.57$0.33
2026-10-15$0.35$0.57$0.33
2026-10-14$0.35$0.57$0.33
2026-10-13$0.35$0.57$0.33
2026-10-12$0.35$0.57$0.33
2026-10-11$0.35$0.57$0.33
2026-10-10$0.35$0.57$0.33
2026-10-09$0.35$0.57$0.33
2026-10-08$0.35$0.53$0.33
2026-10-07$0.35$0.53$0.33
2026-10-06$0.35$0.53$0.33
2026-10-05$0.35$0.53$0.33
2026-10-04$0.35$0.53$0.33
2026-10-03$0.35$0.53$0.33
2026-10-02$0.35$0.53$0.33
2026-10-01$0.35$0.53$0.33
2026-09-30$0.45$0.53$0.33
2026-09-29$0.35$0.53$0.33
2026-09-28$0.35$0.53$0.33
2026-09-27$0.35$0.53$0.33
2026-09-26$0.35$0.53$0.33
2026-09-25$0.35$0.53$0.33
2026-09-24$0.35$0.53$0.33
2026-09-23$0.35$0.53$0.33
2026-09-22$0.35$0.53$0.33
2026-09-21$0.35$0.53$0.33
2026-09-20$0.35$0.53$0.33
2026-09-19$0.35$0.53$0.33
2026-09-18$0.35$0.53$0.33
2026-09-17$0.35$0.53$0.33
2026-09-16$0.35$0.53$0.33
2026-09-15$0.35$0.53$0.33
2026-09-14$0.35$0.53$0.33
2026-09-13$0.35$0.53$0.33
2026-09-12$0.35$0.53$0.33
2026-09-11$0.35$0.53$0.33
2026-09-10$0.35$0.53$0.33
2026-09-09$0.35$0.53$0.33
2026-09-08$0.35$0.53$0.33
2026-09-07$0.35$0.53$0.33
2026-09-06$0.35$0.53$0.33
2026-09-05$0.35$0.53$0.33
2026-09-04$0.35$0.53$0.33
2026-09-03$0.35$0.53$0.33
2026-09-02$0.35$0.53$0.33
2026-09-01$0.35$0.53$0.33
2026-08-31$0.35$0.53$0.33
2026-08-30$0.35$0.53$0.33
2026-08-29$0.35$0.53$0.33
2026-08-28$0.35$0.53$0.33
2026-08-27$0.35$0.53$0.33
2026-08-26$0.35$0.53$0.33
2026-08-25$0.35$0.53$0.33
2026-08-24$0.35$0.53$0.33
2026-08-23$0.35$0.53$0.33
2026-08-22$0.35$0.53$0.33
2026-08-21$0.35$0.53$0.33
2026-08-20$0.35$0.53$0.33
2026-08-19$0.35$0.53$0.33
2026-08-18$0.35$0.53$0.33
2026-08-17$0.35$0.53$0.33
2026-08-16$0.35$0.53$0.33
2026-08-15$0.35$0.53$0.33
2026-08-14$0.35$0.53$0.33
2026-08-13$0.35$0.53$0.33
2026-08-12$0.35$0.53$0.33
2026-08-11$0.35$0.53$0.33
2026-08-10$0.35$0.53$0.33
2026-08-09$0.35$0.53$0.33
2026-08-08$0.35$0.53$0.33
2026-08-07$0.35$0.53$0.33
2026-08-06$0.35$0.53$0.33
2026-08-05$0.35$0.53$0.33
2026-08-04$0.35$0.53$0.33
2026-08-03$0.35$0.53$0.33
2026-08-02$0.35$0.53$0.33
2026-08-01$0.35$0.53$0.33
2026-07-31$0.35$0.53$0.33
2026-07-30$0.35$0.53$0.33
2026-07-29$0.35$0.53$0.33
2026-07-28$0.35$0.53$0.33
2026-07-27$0.35$0.53$0.33
2026-07-26$0.35$0.53$0.33
2026-07-25$0.35$0.53$0.33
2026-07-24$0.35$0.53$0.33
2026-07-23$0.35$0.53$0.33
2026-07-22$0.35$0.53$0.33
2026-07-21$0.35$0.50$0.33
2026-07-20$0.35$0.50$0.33
2026-07-19$0.45$0.53$0.33
2026-07-18$0.45$0.53$0.33
2026-07-17$0.49$0.57$0.33
2026-07-16$0.49$0.57$0.33
2026-07-15$0.49$0.57$0.33
2026-07-14$0.49$0.57$0.33
2026-07-13$0.49$0.57$0.33
2026-07-12$0.49$0.57$0.33
2026-07-11$0.49$0.57$0.33
2026-07-10$0.49$0.57$0.33
2026-07-09$0.49$0.57$0.33
2026-07-08$0.49$0.57$0.33
2026-07-07$0.49$0.57$0.33
2026-07-06$0.49$0.55$0.33
2026-07-05$0.49–$0.33

RTX A6000 prices by provider and billing type

Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its RTX A6000 page with node sizes, fees and its own history.

ProviderOn-demandSpot & communityReservedServerless
Thunder Compute$0.35–––
TensorDock$0.45–––
Hyperstack$0.50–$0.35–
Massed Compute$0.57–––
RunPod$0.59$0.33––
Verda (DataCrunch)$0.78–––
Lambda$1.09–––
Koyeb–––$0.75

RTX A6000 hardware specs

RTX A6000 hardware specifications
ArchitectureAmpere
VRAM48 GB
FP16 TFLOPS (dense)155
Memory bandwidth768 GB/s
TDP300 W
InterconnectNVLink 112.5GB/s
Launched2020

Manufacturer datasheet figures for the RTX A6000. Source: www.nvidia.com.

LLM memory estimates for this GPU

Qwen2.5 14B at 16-bit weights
36.4GB
Weights 29.5 GB · cache 0.8 GB · headroom 6.1 GB. Capacity line: 48 GB.

These models have an estimated inference footprint within 48 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.

Model16-bit GB8-bit GB4-bit GB
Qwen2.5 72B176.1 88.9 45.2 ✓
DeepSeek R1 Distill Llama 70B170.9 86.3 43.9 ✓
Mixtral 8x7B v0.1112.7 56.7 28.7 ✓
Qwen2.5 32B79.9 40.6 ✓20.9 ✓
Qwen2.5 Coder 32B79.9 40.6 ✓20.9 ✓
DeepSeek R1 Distill Qwen 32B79.9 40.6 ✓20.9 ✓
QwQ 32B79.9 40.6 ✓20.9 ✓
Qwen3 32B79.9 40.6 ✓20.9 ✓
Qwen3 30B A3B73.8 37.1 ✓18.8 ✓
Qwen3 30B A3B 250773.8 37.1 ✓18.8 ✓
Qwen3 Coder 30B A3B73.8 37.1 ✓18.8 ✓
Mistral Small 3.2 24B 250658.4 29.6 ✓15.2 ✓
Mistral Small 24B 250157.4 29.1 ✓14.9 ✓
Devstral Small 250757.4 29.1 ✓14.9 ✓
Qwen2.5 14B36.4 ✓18.7 ✓9.8 ✓
Qwen2.5 Coder 14B36.4 ✓18.7 ✓9.8 ✓
DeepSeek R1 Distill Qwen 14B36.4 ✓18.7 ✓9.8 ✓
Qwen3 14B36.2 ✓18.5 ✓9.7 ✓
phi 436.2 ✓18.6 ✓9.8 ✓
Phi 4 reasoning36.2 ✓18.6 ✓9.8 ✓
Phi 4 reasoning plus36.2 ✓18.6 ✓9.8 ✓
Mistral Nemo 240730.2 ✓15.5 ✓8.2 ✓
Qwen3 8B20.4 ✓10.6 ✓5.6 ✓
DeepSeek R1 Distill Llama 8B19.9 ✓10.3 ✓5.5 ✓
Qwen2.5 7B18.6 ✓9.4 ✓4.9 ✓
Qwen2.5 Coder 7B18.6 ✓9.4 ✓4.9 ✓
DeepSeek R1 Distill Qwen 7B18.6 ✓9.4 ✓4.9 ✓
Mistral 7B v0.318.0 ✓9.3 ✓5.0 ✓
Qwen3 4B10.4 ✓5.6 ✓3.1 ✓
Qwen3 4B 250710.4 ✓5.6 ✓3.1 ✓
Qwen2.5 3B7.6 ✓3.9 ✓2.0 ✓
Qwen2.5 Coder 3B7.6 ✓3.9 ✓2.0 ✓
Qwen3 1.7B5.4 ✓3.0 ✓1.8 ✓
DeepSeek R1 Distill Qwen 1.5B4.4 ✓2.3 ✓1.2 ✓
Qwen2.5 1.5B3.8 ✓2.0 ✓1.1 ✓
Qwen2.5 Coder 1.5B3.8 ✓2.0 ✓1.1 ✓
Qwen3 0.6B2.4 ✓1.5 ✓1.0 ✓
Qwen2.5 0.5B1.2 ✓0.7 ✓0.4 ✓
Qwen2.5 Coder 0.5B1.2 ✓0.7 ✓0.4 ✓

Models that need more than one RTX A6000

Compare model memory requirements or change context and memory assumptions on a model's page.

When to choose the RTX A6000, and what to pick instead

Start from memory: your model, its context and your batch must fit in 48 GB (the model-fit table above estimates it). Then the RTX A6000 is the right card unless one of these fits your job better.

Our workload guides recommend the RTX A6000 for 3D rendering and CAD and remote workstations. Each compares it with the other cards that suit that job, at today's prices.

Rent or buy the RTX A6000

Confirmed RTX A6000 purchase listings start at $6,999 (RTX A6000 48GB, SabrePC, checked 22 October 2026, out of stock). That sum rents about 19,997 GPU-hours at today's cheapest on-demand rate of $0.35, about 9.6 years at 40 hours a week, before electricity, hosting and resale.

Compare RTX A6000 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.

RTX A6000 questions

How much does it cost to rent a RTX A6000?
The cheapest RTX A6000 rental we have is $0.35 per GPU-hour on Thunder Compute (on-demand), checked 22 October 2026. The median of each provider's cheapest on-demand rate is $0.57 across 7 providers.
How much VRAM does a RTX A6000 have?
48 GB.
Where is the RTX A6000 cheapest right now?
Thunder Compute has the cheapest checked on-demand rate today at $0.35 per GPU-hour; interruptible spot or community capacity starts at $0.33 (RunPod).

GPUs near the RTX A6000

Related

All 48 GB+ GPUs · GPUs under $1/hr · Price movers this week · Thunder Compute review · RTX A6000 vs L40S · RTX A6000 vs RTX 6000 Ada · RTX A4000 vs RTX A6000 · Best Cloud GPU to Rent for 3D Rendering · Cloud GPU for CAD and remote workstations

Compare your offers

Saved prices keep their original dates. Confirm the configuration, terms and availability at the source.

Select up to three offers to compare their rates and terms.

Type a GPU, a provider, a model or a question.