Loading prices…
RTX A4000 rental prices
NVIDIA · Ampere · 16 GB GDDR6 · PCIe · 2021
6 providers · 16 configurations · prices as of Nov 11, 2026, 01:04 UTC
Lowest on-demand
$0.10per GPU·h · ≈ $73/month
at GPU.aiMedian on-demand
$0.17/GPU·h
across 6 providers
Lowest spot
—
Reserved from $0.11
FP16/BF16 cost
$1.30/PFLOP·h
#4 of 73 GPUs for value
Providers
6
16 configurations
Price history
Daily RTX A4000 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 A4000 offer at each provider, per GPU-hour. Shorter and greener is cheaper.
GPU.ai🇺🇸$0.10best
Hyperstack🇬🇧$0.15+50%
Sesterce🇫🇷$0.17+65%
RunPod🇺🇸$0.17+70%
EmpirioLabs AI🇺🇸$0.252.5×
Paperspace🇺🇸$0.808.0×
Thin vertical line = median across providers ($0.17).
Every provider we track
Pricing
Size
Host
Provider HQ
6 providers · 16 configurations
Sort
- GPU.aicommunityOn-demand🇺🇸 HQ in United Statesvia GPU.aifrom · On-demandCheapest$0.10/GPU·hCheapest
- HyperstackOn-demandReserved🇬🇧 HQ in United Kingdomvia Hyperstack pricing pagefrom · On-demand+50%$0.15/GPU·h+50%
- SesterceOn-demand🇫🇷 HQ in Francevia Sestercefrom · On-demand+65%$0.17/GPU·h+65%
- 2× GPU · PCIe8 vCPU · 43 GB RAM · 200 GB disk$0.17 /GPU·h$0.33 /hOn-demandNOR-Oslo-1● availableRent ↗
- 1× GPU · PCIe4 vCPU · 21 GB RAM · 100 GB disk$0.17 /GPU·h$0.17 /hOn-demandNOR-Oslo-1● availableRent ↗
- 4× GPU · PCIe32 vCPU · 180 GB RAM · 1,000 GB disk$0.88 /GPU·h$3.52 /hOn-demandUSA-NewYork-1● availableRent ↗
- RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demand+70%$0.17/GPU·h+70%
- EmpirioLabs AIOn-demand🇺🇸 HQ in United Statesvia EmpirioLabs APIfrom · On-demand2.5×$0.25/GPU·h2.5×
- PaperspaceOn-demand🇺🇸 HQ in United Statesvia Shadeformfrom · On-demand8.0×$0.80/GPU·h8.0×
- 2× GPU · PCIe16 vCPU · 90 GB RAM · 500 GB disk$0.80 /GPU·h$1.60 /hOn-demand🇺🇸 US, New York, NY● availableRent ↗
- 4× GPU · PCIe32 vCPU · 180 GB RAM · 1,000 GB disk$0.80 /GPU·h$3.20 /hOn-demand🇺🇸 US, New York, NY● availableRent ↗
- 1× GPU · PCIe8 vCPU · 45 GB RAM · 250 GB disk$0.80 /GPU·h$0.80 /hOn-demand🇺🇸 US, New York, NY● availableRent ↗
What can the RTX A4000 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 | 2 | $0.20 at GPU.ai | $146 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 2 | $0.20 at GPU.ai | $146 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 4 | $0.40 at GPU.ai | $292 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 8 | $0.80 at GPU.ai | $584 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 8 | $0.80 at GPU.ai | $584 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 16 | $1.60 at GPU.ai | $1,168 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 64 | $6.40 at GPU.ai | $4,672 |
Kimi K3 Moonshot AI · 2.78T | 2.78T · 104B active | 2.53 TiB | 64+ | — | — |
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 A4000
GPUs with similar compute and memory, and their lowest on-demand price right now.
- RTX 4000 SFF Ada20 GB · 0.0767 PF FP16$0.50/h$6.52/PFLOP·h
- RTX 4000 Ada20 GB · 0.0818 PF FP16$0.20/h$2.44/PFLOP·h
- RTX A450020 GB · 0.0946 PF FP16$0.18/h$1.90/PFLOP·h
- RTX 2000 Ada16 GB · 0.048 PF FP16$0.24/h$5.00/PFLOP·h
- RTX 5070 Ti16 GB · 0.0879 PF FP16$0.16/h$1.83/PFLOP·h
- T416 GB · 0.065 PF FP16$0.11/h$1.69/PFLOP·h
RTX A4000 pricing questions
How much does it cost to rent an RTX A4000?
On-demand RTX A4000 prices start at $0.10 per GPU-hour (GPU.ai). The median across 6 providers is $0.17, and the most expensive is $0.80. Running one GPU around the clock costs about $73 per month at the lowest price.
How much compute do you get per dollar with the RTX A4000?
At $0.10 per hour and 0.0767 PF of dense FP16/BF16, the RTX A4000 costs $1.30 per PFLOP-hour. That ranks 4 of 73 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the RTX A4000's key specs?
16 GB GDDR6 with 448 GB/s of memory bandwidth, Ampere architecture (2021), PCIe form factor, 140 W. Dense peak: 0.0767 PF FP16 / BF16, 0.153 PF INT8, 0.0384 PF TF32, 0.0192 PF FP32, 0.0003 PF FP64.
How current are these prices?
Prices were collected on Nov 11, 2026, 01:04 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.