Loading prices…
RTX 4000 SFF Ada rental prices
NVIDIA · Ada Lovelace · 20 GB GDDR6 · PCIe · 2023
2 providers · 2 configurations · prices as of Nov 9, 2026, 21:02 UTC
Other versions:20GB
Lowest on-demand
$0.18per GPU·h · ≈ $131/month
at RunPodMedian on-demand
$0.34/GPU·h
across 2 providers
Lowest spot
—
interruptible
FP16/BF16 cost
$2.35/PFLOP·h
#23 of 69 GPUs for value
Providers
2
2 configurations
Price history
Daily RTX 4000 SFF 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-demand
Price by provider
Cheapest On-demand RTX 4000 SFF Ada offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Thin vertical line = median across providers ($0.18).
Every provider we track
Pricing
Size
Host
Provider HQ
2 providers · 2 configurations
Sort
RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demandCheapest$0.18/GPU·hCheapest- 1× GPU—$0.18 /GPU·h$0.18 /hOn-demandCommunity CloudRent ↗
KoyebOn-demand🇫🇷 HQ in Francevia Koyeb pricing pagefrom · On-demand2.8×$0.50/GPU·h2.8×- 1× GPU6 vCPU · 44 GB RAM · 240 GB disk$0.50 /GPU·h$0.50 /hOn-demandRent ↗
What can the RTX 4000 SFF 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 | 2 | $0.36 at RunPod | $263 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 2 | $0.36 at RunPod | $263 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 4 | $0.72 at RunPod | $526 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 8 | $1.44 at RunPod | $1,051 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 8 | $1.44 at RunPod | $1,051 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 16 | $2.88 at RunPod | $2,102 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 64 | $11.52 at RunPod | $8,410 |
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 4000 SFF Ada
GPUs with similar compute and memory, and their lowest on-demand price right now.
- RTX 4000 Ada20 GB · 0.0818 PF FP16$0.20/h$2.44/PFLOP·h
- RTX A400016 GB · 0.0767 PF FP16$0.10/h$1.24/PFLOP·h
- RTX A450020 GB · 0.0946 PF FP16$0.19/h$2.01/PFLOP·h
- RTX A500024 GB · 0.111 PF FP16$0.16/h$1.44/PFLOP·h
- RTX 3090 Ti24 GB · 0.08 PF FP16$0.27/h$3.38/PFLOP·h
- RTX 309024 GB · 0.071 PF FP16$0.09/h$1.27/PFLOP·h
RTX 4000 SFF Ada pricing questions
How much does it cost to rent an RTX 4000 SFF Ada?
On-demand RTX 4000 SFF Ada prices start at $0.18 per GPU-hour (RunPod). The median across 2 providers is $0.34, and the most expensive is $0.50. Running one GPU around the clock costs about $131 per month at the lowest price.
How much compute do you get per dollar with the RTX 4000 SFF Ada?
At $0.18 per hour and 0.0767 PF of dense FP16/BF16, the RTX 4000 SFF Ada costs $2.35 per PFLOP-hour. That ranks 23 of 69 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the RTX 4000 SFF Ada's key specs?
20 GB GDDR6 with 280 GB/s of memory bandwidth, Ada Lovelace architecture (2023), PCIe form factor, 70 W. Dense peak: 0.0767 PF FP16 / BF16, 0.153 PF FP8, 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 9, 2026, 21:02 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.