RTX 5090 Cloud Rental Pricing

Consumer Blackwell GPU with 32GB GDDR7, faster and roomier than the 4090 for local-scale models.

4 offers from 4 providers · updated November 16, 2026

Lowest on-demand
$0.37/hr
Median
$0.60/hr
Lowest spot
$0.25/hr
8x GPUs, 1 month
from $2,161
Provider Variant VRAM On-demand /hr Spot /hr Per month Billing
Vast.ai RTX 5090 32GB $0.37 — $270 per second
Salad RTX 5090 32GB $0.60 $0.25 $438 per second
Prime Intellect RTX 5090 32GB $1.22 — $891 per minute
RunPod credits RTX 5090 32GB $1.39 — $1,015 per ms

Per GPU-hour, on-demand unless noted. Monthly = 730 hours. Check each provider for region availability and multi-GPU node minimums.

Or run models at home

If you rent a RTX 5090 mainly for inference, a mini PC with lots of unified memory can hold the same open models on your desk. It's slower per token than a RTX 5090, but there's no hourly bill.Compare mini PCs for local LLMs.

GMKtecfrom $2,199.99

GMKtec EVO-X2

Chip
AMD Ryzen AI Max+ 395
Memory
64GB or 128GB unified (up to 96GB as VRAM)
Bandwidth
256 GB/s
Runs
128GB: gpt-oss-120b, Qwen3.5 122B-A10B, GLM-4.5 Air. 64GB: 30B-class models

128GB / 1TB is $3,499.99. The cheapest 128GB Ryzen AI Max box we found.

Minisforumfrom $3,959

Minisforum MS-S1 Max

Chip
AMD Ryzen AI Max+ 395
Memory
128GB unified (up to 96GB as VRAM)
Bandwidth
256 GB/s
Runs
gpt-oss-120b, Qwen3.5 122B-A10B, Llama 4 Scout, Mistral Small 4

Sale price (list $4,949) for 128GB / 2TB. Built as a small workstation, with more ports than most.

NVIDIAfrom $6,950

NVIDIA DGX Spark

Chip
NVIDIA GB10 Grace Blackwell
Memory
128GB unified
Bandwidth
273 GB/s
Runs
gpt-oss-120b, Qwen3.5 122B-A10B, Llama 4 Scout; CUDA, so most training tools work

128GB / 4TB Founders Edition. Partner GB10 boxes from ASUS, MSI and Dell cost $5,599 to $8,500.

Applefrom $3,099

Mac Studio (M5 Max)

Chip
Apple M5 Max
Memory
48GB or 128GB unified
Bandwidth
614 GB/s (40-core GPU)
Runs
128GB: gpt-oss-120b, Qwen3.5 122B-A10B, at more than twice the bandwidth of the AMD boxes

128GB is $5,099. The M5 Ultra (96GB to 512GB, 1.2 TB/s) starts at $5,499.

Starting prices from each maker's own store on November 22, 2026; they change often, so check the store. "Runs" is a rough guide for 4-bit quantized models.

RTX 5090 guides

RTX 5090 rental FAQ

How much does it cost to rent an RTX 5090?

On-demand RTX 5090 rental ranges from $0.37 to $1.39 per GPU-hour across 4 providers (median $0.60), as of November 16, 2026. Spot/interruptible capacity starts at $0.25/hr.

What is the cheapest RTX 5090 cloud provider?

Vast.ai has the lowest on-demand RTX 5090 price we track at $0.37 per GPU-hour (RTX 5090).

How much does an 8x RTX 5090 server cost per month?

At the cheapest on-demand rate ($0.37/GPU-hour), 8x RTX 5090 running 24/7 costs about $2,161 per month (730 hours). At the median rate it is about $3,504.

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.