Loading prices…
RTX 3080 rental prices
NVIDIA · Ampere · 10 GB GDDR6X · PCIe · 2020
2 providers · 3 configurations · prices as of Nov 11, 2026, 03:01 UTC
Other versions:Ti 12GB
Lowest on-demand
$0.12per GPU·h · ≈ $88/month
at GPU.aiMedian on-demand
$0.15/GPU·h
across 2 providers
Lowest spot
—
interruptible
FP16/BF16 cost
$2.02/PFLOP·h
#24 of 74 GPUs for value
Providers
2
3 configurations
Price history
Daily RTX 3080 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 3080 offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Thin vertical line = median across providers ($0.12).
Every provider we track
Pricing
Size
Host
Provider HQ
2 providers · 3 configurations
Sort
GPU.aicommunityOn-demand🇺🇸 HQ in United Statesvia GPU.aifrom · On-demandCheapest$0.12/GPU·hCheapest
RunPodcommunityOn-demand🇺🇸 HQ in United Statesvia RunPodfrom · On-demand+42%$0.17/GPU·h+42%- 1× GPU—$0.17 /GPU·h$0.17 /hOn-demandCommunity CloudRent ↗
What can the RTX 3080 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 | 4 | $0.48 at GPU.ai | $350 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 4 | $0.48 at GPU.ai | $350 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 8 | $0.96 at GPU.ai | $701 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 16 | $1.92 at GPU.ai | $1,402 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 16 | $1.92 at GPU.ai | $1,402 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 32 | $3.84 at GPU.ai | $2,803 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 64+ | — | — |
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 3080
GPUs with similar compute and memory, and their lowest on-demand price right now.
- RTX 3080 Ti12 GB · 0.0682 PF FP16$0.18/h$2.64/PFLOP·h
- RTX 407012 GB · 0.0583 PF FP16$0.10/h$1.64/PFLOP·h
- RTX 4070 SUPER12 GB · 0.071 PF FP16$0.09/h$1.33/PFLOP·h
- RTX 4070 Ti12 GB · 0.0802 PF FP16$0.13/h$1.65/PFLOP·h
- RTX 5060 Ti16 GB · 0.0474 PF FP16$0.10/h$2.20/PFLOP·h
- RTX 30708 GB · 0.0406 PF FP16$0.13/h$3.20/PFLOP·h
RTX 3080 pricing questions
How much does it cost to rent an RTX 3080?
On-demand RTX 3080 prices start at $0.12 per GPU-hour (GPU.ai). The median across 2 providers is $0.15, and the most expensive is $0.17. Running one GPU around the clock costs about $88 per month at the lowest price.
How much compute do you get per dollar with the RTX 3080?
At $0.12 per hour and 0.0595 PF of dense FP16/BF16, the RTX 3080 costs $2.02 per PFLOP-hour. That ranks 24 of 74 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the RTX 3080's key specs?
10 GB GDDR6X with 760 GB/s of memory bandwidth, Ampere architecture (2020), PCIe form factor, 320 W. Dense peak: 0.0595 PF FP16 / BF16, 0.238 PF INT8, 0.0298 PF TF32, 0.0298 PF FP32, 0.0005 PF FP64.
How current are these prices?
Prices were collected on Nov 11, 2026, 03:01 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.