Loading prices…
RTX 6000 Ada rental prices
NVIDIA · Ada Lovelace · 48 GB GDDR6 · PCIe · 2022
9 providers · 25 configurations · prices as of Nov 11, 2026, 05:01 UTC
Lowest on-demand
$0.63per GPU·h · ≈ $460/month
at Vast.aiMedian on-demand
$0.91/GPU·h
across 9 providers
Lowest spot
$0.77/GPU·h
interruptible
FP16/BF16 cost
$1.73/PFLOP·h
#12 of 72 GPUs for value
Providers
9
25 configurations
Price history
Daily RTX 6000 Ada 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 6000 Ada offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Vast.ai🇺🇸$0.63best
GPU.ai🇺🇸$0.72+13%
RunPod🇺🇸$0.74+17%
Massed Compute🇺🇸$0.79+25%
Lium$0.91+44%
Sesterce🇫🇷$1.07+69%
EmpirioLabs AI🇺🇸$1.502.4×
Verda (DataCrunch)🇫🇮$1.542.4×
DigitalOcean🇺🇸$1.572.5×
Thin vertical line = median across providers ($0.91).
Every provider we track
Pricing
Size
Host
Provider HQ
9 providers · 25 configurations
Sort
- Vast.aicommunityOn-demand🇺🇸 HQ in United Statesvia Vast.aifrom · On-demandCheapest$0.63/GPU·hCheapest
- 2× GPU · PCIe43 vCPU · 168 GB RAM · 1,468 GB disk$0.63 /GPU·h$1.26 /hOn-demand🇪🇪 Estonia, EE● availableRent ↗
- GPU.aiOn-demand🇺🇸 HQ in United Statesvia GPU.aifrom · On-demand+13%$0.72/GPU·h+13%
- RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demand+17%$0.74/GPU·h+17%
- Massed ComputeOn-demand🇺🇸 HQ in United Statesvia Massed Compute pricing pagefrom · On-demand+25%$0.79/GPU·h+25%
- LiumcommunityOn-demandSpotHQ unknownvia Liumfrom · On-demand+44%$0.91/GPU·h+44%
- 1× GPU11 vCPU · 71 GB RAM · 343 GB disk$0.91 /GPU·h$0.91 /hOn-demand🇺🇸 Des Moines, US● availableRent ↗
- 2× GPU25 vCPU · 142 GB RAM · 688 GB disk$0.91 /GPU·h$1.82 /hOn-demand🇺🇸 Las Vegas, US● availableRent ↗
- 1× GPU31 vCPU · 126 GB RAM · 1,500 GB disk$1.00 /GPU·h$1.00 /hOn-demand🇧🇬 Plovdiv, BG● availableRent ↗
- SesterceOn-demand🇫🇷 HQ in Francevia Sestercefrom · On-demand+69%$1.07/GPU·h+69%
- 1× GPU · PCIe12 vCPU · 80 GB RAM · 350 GB disk$1.07 /GPU·h$1.07 /hOn-demandUSA-Kansascity-1● availableRent ↗
- EmpirioLabs AIOn-demand🇺🇸 HQ in United Statesvia EmpirioLabs APIfrom · On-demand2.4×$1.50/GPU·h2.4×
- Verda (DataCrunch)On-demandSpot🇫🇮 HQ in Finlandvia Verdafrom · On-demand2.4×$1.54/GPU·h2.4×
What can the RTX 6000 Ada 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 | $0.63 at Vast.ai | $460 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 1 | $0.63 at Vast.ai | $460 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 1 | $0.63 at Vast.ai | $460 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 2 | $1.26 at Vast.ai | $920 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 4 | $2.52 at Vast.ai | $1,841 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 8 | $5.04 at Vast.ai | $3,682 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 16 | $10.09 at Vast.ai | $7,363 |
Kimi K3 Moonshot AI · 2.78T | 2.78T · 104B active | 2.53 TiB | 64 | $40.35 at Vast.ai | $29,452 |
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 6000 Ada
GPUs with similar compute and memory, and their lowest on-demand price right now.
- RTX PRO 5000 Blackwell48 GB · 0.268 PF FP16$0.80/h$2.99/PFLOP·h
- L40S48 GB · 0.362 PF FP16$0.38/h$1.05/PFLOP·h
- RTX PRO 6000 Blackwell Max-Q96 GB · 0.439 PF FP16$1.64/h$3.74/PFLOP·h
- RTX 5000 Ada32 GB · 0.261 PF FP16$0.49/h$1.88/PFLOP·h
- A100 SXM 40GB40 GB · 0.312 PF FP16$0.91/h$2.92/PFLOP·h
- A100 PCIe 40GB40 GB · 0.312 PF FP16$1.09/h$3.49/PFLOP·h
RTX 6000 Ada pricing questions
How much does it cost to rent an RTX 6000 Ada?
On-demand RTX 6000 Ada prices start at $0.63 per GPU-hour (Vast.ai). The median across 9 providers is $0.91, and the most expensive is $1.57. Running one GPU around the clock costs about $460 per month at the lowest price.
Is there cheaper spot or interruptible RTX 6000 Ada capacity?
Yes. Spot (interruptible) RTX 6000 Ada capacity starts at $0.77 per GPU-hour, -22% 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 6000 Ada?
At $0.63 per hour and 0.364 PF of dense FP16/BF16, the RTX 6000 Ada costs $1.73 per PFLOP-hour. That ranks 12 of 72 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the RTX 6000 Ada's key specs?
48 GB GDDR6 with 960 GB/s of memory bandwidth, Ada Lovelace architecture (2022), PCIe form factor, 300 W. Dense peak: 0.364 PF FP16 / BF16, 0.729 PF FP8, 0.729 PF INT8, 0.182 PF TF32, 0.0911 PF FP32, 0.0014 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.