Loading prices…
RTX 3090 Ti rental prices
NVIDIA · Ampere · 24 GB GDDR6X · PCIe · 2022
2 providers · 4 configurations · prices as of Nov 10, 2026, 07:01 UTC
Other versions:24GB
Lowest on-demand
$0.27per GPU·h · ≈ $197/month
at RunPodMedian on-demand
$0.27/GPU·h
across 1 providers
Lowest spot
$0.12/GPU·h
interruptible
FP16/BF16 cost
$3.38/PFLOP·h
#48 of 73 GPUs for value
Providers
2
4 configurations
Price history
Daily RTX 3090 Ti 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 3090 Ti offer at each provider, per GPU-hour. Shorter and greener is cheaper.
RunPod🇺🇸$0.27best
Thin vertical line = median across providers ($0.27).
Every provider we track
Pricing
Size
Host
Provider HQ
2 providers · 4 configurations
Sort
- RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demandCheapest$0.27/GPU·hCheapest
- 1× GPU—$0.27 /GPU·h$0.27 /hOn-demandCommunity CloudRent ↗
Vast.aicommunitySpot🇺🇸 HQ in United Statesvia Vast.aifrom · SpotCheapest$0.12/GPU·hCheapest · Spot
What can the RTX 3090 Ti 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 | $0.27 at RunPod | $197 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 2 | $0.54 at RunPod | $394 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 2 | $0.54 at RunPod | $394 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 4 | $1.08 at RunPod | $788 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 8 | $2.16 at RunPod | $1,577 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 16 | $4.32 at RunPod | $3,154 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 32 | $8.64 at RunPod | $6,307 |
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 3090 Ti
GPUs with similar compute and memory, and their lowest on-demand price right now.
- RTX 309024 GB · 0.071 PF FP16$0.09/h$1.27/PFLOP·h
- RTX 5070 Ti16 GB · 0.0879 PF FP16$0.16/h$1.83/PFLOP·h
- RTX 4070 Ti12 GB · 0.0802 PF FP16$0.13/h$1.66/PFLOP·h
- RTX 408016 GB · 0.0975 PF FP16$0.18/h$1.85/PFLOP·h
- RTX 4070 SUPER12 GB · 0.071 PF FP16$0.09/h$1.34/PFLOP·h
- RTX 4080 SUPER16 GB · 0.104 PF FP16$0.20/h$1.94/PFLOP·h
RTX 3090 Ti pricing questions
How much does it cost to rent an RTX 3090 Ti?
On-demand RTX 3090 Ti prices start at $0.27 per GPU-hour (RunPod). The median across 1 providers is $0.27, and the most expensive is $0.27. Running one GPU around the clock costs about $197 per month at the lowest price.
Is there cheaper spot or interruptible RTX 3090 Ti capacity?
Yes. Spot (interruptible) RTX 3090 Ti capacity starts at $0.12 per GPU-hour, 54% 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 3090 Ti?
At $0.27 per hour and 0.08 PF of dense FP16/BF16, the RTX 3090 Ti costs $3.38 per PFLOP-hour. That ranks 48 of 73 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the RTX 3090 Ti's key specs?
24 GB GDDR6X with 1,008 GB/s of memory bandwidth, Ampere architecture (2022), PCIe form factor, 450 W. Dense peak: 0.08 PF FP16 / BF16, 0.32 PF INT8, 0.04 PF TF32, 0.04 PF FP32, 0.0006 PF FP64.
How current are these prices?
Prices were collected on Nov 10, 2026, 07:01 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.