Loading prices…
RTX A6000 rental prices
NVIDIA · Ampere · 48 GB GDDR6 · PCIe · 2020
14 providers · 55 configurations · prices as of Nov 11, 2026, 05:01 UTC
Lowest on-demand
$0.33per GPU·h · ≈ $241/month
at RunPodMedian on-demand
$0.55/GPU·h
across 14 providers
Lowest spot
$0.40/GPU·h
Reserved from $0.35
FP16/BF16 cost
$2.13/PFLOP·h
#27 of 72 GPUs for value
Providers
14
55 configurations
Price history
Daily RTX A6000 prices per GPU-hour. The shaded period is reconstructed from public archives: the version history of SkyPilot's price catalogs, Internet Archive copies of providers' pricing pages and the open gpu-price-feed project (fewer providers than live data). After that, PetaPrice's own tracking.
Lowest on-demandMedian on-demandLowest spot
Price by provider
Cheapest On-demand RTX A6000 offer at each provider, per GPU-hour. Shorter and greener is cheaper.
RunPod🇺🇸$0.33best
Lium$0.40+21%
GPU.ai🇺🇸$0.44+33%
IMWT$0.49+48%
Hyperstack🇬🇧$0.50+52%
Massed Compute🇺🇸$0.55+67%
Oblivus🇬🇧$0.55+67%
Sesterce🇫🇷$0.55+67%
EmpirioLabs AI🇺🇸$0.702.1×
Koyeb🇫🇷$0.752.3×
Seeweb🇮🇹$0.832.5×
Verda (DataCrunch)🇫🇮$0.852.6×
Lambda🇺🇸$1.093.3×
Paperspace🇺🇸$1.935.8×
Thin vertical line = median across providers ($0.55).
Every provider we track
Pricing
Size
Host
Provider HQ
14 providers · 55 configurations
Sort
- RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demandCheapest$0.33/GPU·hCheapest
- LiumcommunityOn-demandHQ unknownvia Liumfrom · On-demand+21%$0.40/GPU·h+21%
- GPU.aicommunityOn-demand🇺🇸 HQ in United Statesvia GPU.aifrom · On-demand+33%$0.44/GPU·h+33%
- IMWTOn-demandHQ unknownvia Shadeformfrom · On-demand+48%$0.49/GPU·h+48%
- 8× GPU · PCIe62 vCPU · 384 GB RAM · 2,560 GB disk$0.49 /GPU·h$3.92 /hOn-demand🇺🇸 US, Des Moines, IA○ sold outRent ↗
- 1× GPU · PCIe6 vCPU · 48 GB RAM · 256 GB disk$0.49 /GPU·h$0.49 /hOn-demand🇺🇸 US, Kansas City, MO○ sold outRent ↗
- 2× GPU · PCIe14 vCPU · 96 GB RAM · 512 GB disk$0.49 /GPU·h$0.98 /hOn-demand🇺🇸 US, Des Moines, IA○ sold outRent ↗
- HyperstackOn-demandReservedSpot🇬🇧 HQ in United Kingdomvia Hyperstack pricing pagefrom · On-demand+52%$0.50/GPU·h+52%
- OblivusOn-demandReserved🇬🇧 HQ in United Kingdomvia Oblivus pricing pagefrom · On-demand+67%$0.55/GPU·h+67%
- Massed ComputeOn-demand🇺🇸 HQ in United Statesvia Massed Compute pricing pagefrom · On-demand+67%$0.55/GPU·h+67%
- SesterceOn-demand🇫🇷 HQ in Francevia Sestercefrom · On-demand+67%$0.55/GPU·h+67%
- 1× GPU · PCIe28 vCPU · 58 GB RAM · 100 GB disk$0.55 /GPU·h$0.55 /hOn-demandCAN-Montreal-2● availableRent ↗
- 4× GPU · PCIe30 vCPU · 192 GB RAM · 1,024 GB disk$0.63 /GPU·h$2.51 /hOn-demandUSA-Kansascity-1● availableRent ↗
- 2× GPU · PCIe14 vCPU · 96 GB RAM · 512 GB disk$0.63 /GPU·h$1.25 /hOn-demandUSA-Kansascity-1● availableRent ↗
What can the RTX A6000 run?
Memory for the weights plus one 32K-token sequence of context, how many GPUs hold it, and what that replica costs at the cheapest in-stock on-demand rate.
| Model | Params | Memory | GPUs | $/hr | $/mo |
|---|---|---|---|---|---|
gpt-oss-20b OpenAI · 20.9B | 20.9B · 3.6B active | 20 GiB | 1 | $0.33 at RunPod | $241 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 1 | $0.33 at RunPod | $241 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 1 | $0.33 at RunPod | $241 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 2 | $0.66 at RunPod | $482 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 4 | $1.32 at RunPod | $964 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 8 | $2.64 at RunPod | $1,927 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 16 | $5.28 at RunPod | $3,854 |
Kimi K3 Moonshot AI · 2.78T | 2.78T · 104B active | 2.53 TiB | 64 | $21.12 at RunPod | $15,418 |
Assumes 90% of each GPU's memory is usable and rounds up to 1, 2, 4, 8… GPUs for tensor parallelism (up to 64). $/hr is the GPU count times the cheapest in-stock on-demand rate per GPU; check that the provider rents instances that large. Serving many requests at once needs more memory for context.
Alternatives to the RTX A6000
GPUs with similar compute and memory, and their lowest on-demand price right now.
- RTX PRO 4000 Blackwell24 GB · 0.147 PF FP16$0.27/h$1.84/PFLOP·h
- A4048 GB · 0.15 PF FP16$0.59/h$3.94/PFLOP·h
- RTX PRO 4500 Blackwell32 GB · 0.211 PF FP16$0.72/h$3.41/PFLOP·h
- Quadro RTX 600024 GB · 0.131 PF FP16$0.33/h$2.49/PFLOP·h
- RTX PRO 5000 Blackwell48 GB · 0.268 PF FP16$0.80/h$2.99/PFLOP·h
- L4048 GB · 0.181 PF FP16$0.33/h$1.82/PFLOP·h
RTX A6000 pricing questions
How much does it cost to rent an RTX A6000?
On-demand RTX A6000 prices start at $0.33 per GPU-hour (RunPod). The median across 14 providers is $0.55, and the most expensive is $1.93. Running one GPU around the clock costs about $241 per month at the lowest price.
Is there cheaper spot or interruptible RTX A6000 capacity?
Yes. Spot (interruptible) RTX A6000 capacity starts at $0.40 per GPU-hour, -21% below the cheapest on-demand price. Spot instances can be preempted at any time, so use them for checkpointed training or batch jobs.
How much compute do you get per dollar with the RTX A6000?
At $0.33 per hour and 0.155 PF of dense FP16/BF16, the RTX A6000 costs $2.13 per PFLOP-hour. That ranks 27 of 72 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the RTX A6000's key specs?
48 GB GDDR6 with 768 GB/s of memory bandwidth, Ampere architecture (2020), PCIe form factor, 300 W. Dense peak: 0.155 PF FP16 / BF16, 0.31 PF INT8, 0.0774 PF TF32, 0.0387 PF FP32, 0.0006 PF FP64.
How current are these prices?
Prices were collected on Nov 11, 2026, 05:01 UTC from provider APIs and public catalogs and refresh about every 2 hours. They are indicative list prices; always confirm on the provider's website before booking.