Nvidia RTX 5090 cloud rental prices
5 providers list the Nvidia RTX 5090, 4 have it in stock. Prices run from $0.28 to $0.70 per GPU hour — the same card, 2.5x apart.
Prices and stock checked 2 hours ago
What it costs you to run
Estimated at the cheapest listed rate of $0.28/GPU/hr (Vast.ai), per GPU, before storage, egress or commitment discounts.
Renting at the median instead of the floor costs you an extra $268 a month per GPU. That is 57% of the bill, for identical silicon.
Every provider renting the Nvidia RTX 5090
Ordered strictly by entry price per GPU hour. Rows above the median are marked. Stock is what the provider reported at our last check, not a guarantee.
| Provider | Country | Configs | Scale | From | Spot | Reserved | Stock | Grab |
|---|---|---|---|---|---|---|---|---|
| Vast.ai | United States of America | 1 | 1x-1x | $0.28 | — | — | In stock | GrabVast.ai — opens the provider's site |
| Excess Supply | — | 5 | 1x-8x | $0.65 | — | — | In stock | GrabExcess Supply — opens the provider's site |
| Lium | — | 1 | 1x-1x | $0.65 | — | — | In stock | GrabLium — opens the provider's site |
| Runpod | United States of America | 2 | 1x-1x | $0.69 | $0.69 | — | In stock | GrabRunpod — opens the provider's site |
| Phyntec | — | 1 | 8x-8x | $0.70 | — | — | Out of stock | GrabPhyntec — opens the provider's site |
Live inventory signal
The Lium marketplace publishes GPU counts, which almost nobody else does. It holds 246 Nvidia RTX 5090 GPUs at $0.65/GPU/hr, with 63% already rented. There is slack at that price today.
All 10 configurations
| Configuration | Provider | Region | VRAM | vCPU | RAM | Billing | Per GPU/hr | Total/hr | Stock |
|---|---|---|---|---|---|---|---|---|---|
| 1x RTX 5090 | Vast.ai | TH | 32 GB | 16 | 125 GB | On-Demand | $0.28 | $0.28 | In stock |
| 1x RTX5090 | Excess Supply | oslo-norway-3 | 32 GB | 12 | 120 GB | On-Demand | $0.65 | $0.65 | In stock |
| 2x RTX5090 | Excess Supply | oslo-norway-3 | 64 GB | 24 | 240 GB | On-Demand | $0.65 | $1.30 | In stock |
| 8x RTX5090 | Excess Supply | oslo-norway-3 | 256 GB | 120 | 960 GB | On-Demand | $0.65 | $5.20 | Out of stock |
| 4x RTX5090 | Excess Supply | oslo-norway-3 | 128 GB | 60 | 480 GB | On-Demand | $0.65 | $2.60 | In stock |
| 1x NVIDIA GeForce RTX 5090 | Lium | — | — | — | — | On-Demand | $0.65 | $0.65 | In stock |
| 1x RTX 5090 | Runpod | — | 32 GB | — | — | On-Demand | $0.69 | $0.69 | In stock |
| 1x RTX 5090 | Runpod | — | 32 GB | — | — | Spot | $0.69 | $0.69 | In stock |
| 8x RTX5090 | Excess Supply | casper-usa-2 | 256 GB | 120 | 228 GB | On-Demand | $0.70 | $5.60 | In stock |
| 8x RTX5090 | Phyntec | casper-usa-1 | 256 GB | 64 | 256 GB | On-Demand | $0.70 | $5.60 | Out of stock |
What fits in 32 GB
The question behind most rentals: will the model load. Sized against one Nvidia RTX 5090.
| Model | 16-bit | 8-bit | 4-bit |
|---|---|---|---|
| DeepSeek-V3 DeepSeek · 671B params · 37B active | 1,610 GB 51× · 22 GB free | 805 GB 26× · 27 GB free | 403 GB 13× · 13 GB free |
| Llama 3.1 405B Meta · 405B params | 972 GB 31× · 20 GB free | 486 GB 16× · 26 GB free | 243 GB 8× · 13 GB free |
| Qwen3 235B-A22B Alibaba · 235B params · 22B active | 564 GB 18× · 12 GB free | 282 GB 9× · 6 GB free | 141 GB 5× · 19 GB free |
| Mixtral 8x22B Mistral · 141B params · 39B active | 338 GB 11× · 14 GB free | 169 GB 6× · 23 GB free | 85 GB 3× · 11 GB free |
| Mistral Large 2 Mistral · 123B params | 295 GB 10× · 25 GB free | 148 GB 5× · 12 GB free | 74 GB 3× · 22 GB free |
| gpt-oss-120b OpenAI · 117B params · 5.1B active | 281 GB 9× · 7 GB free | 140 GB 5× · 20 GB free | 70 GB 3× · 26 GB free |
| Qwen2.5 72B Alibaba · 72.7B params | 174 GB 6× · 18 GB free | 87 GB 3× · 9 GB free | 44 GB 2× · 20 GB free |
| Llama 3.3 70B Meta · 70.6B params | 169 GB 6× · 23 GB free | 85 GB 3× · 11 GB free | 42 GB 2× · 22 GB free |
| Qwen3 32B Alibaba · 32.8B params | 79 GB 3× · 17 GB free | 39 GB 2× · 25 GB free | 20 GB 1× · 12 GB free |
| Gemma 2 27B Google · 27.2B params | 65 GB 3× · 31 GB free | 33 GB 2× · 31 GB free | 16 GB 1× · 16 GB free |
| Mistral Small 3 Mistral · 24B params | 58 GB 2× · 6 GB free | 29 GB 1× · 3 GB free | 14 GB 1× · 18 GB free |
| Llama 3.1 8B Meta · 8B params | 19 GB 1× · 13 GB free | 10 GB 1× · 22 GB free | 5 GB 1× · 27 GB free |
Required memory is weights plus 20% for KV cache and runtime at short context; long contexts and large batches need more. Cells tinted green fit on a single Nvidia RTX 5090.
Nvidia RTX 5090 specifications
| Architecture | Blackwell |
|---|---|
| Memory per GPU | 32 GB GDDR7 |
| Memory bandwidth | 1,792 GB/s |
| Release date | Q1 2025 |
| FP4 compute rate | 1,676 TFLOPS (dense), 3,352 with sparsity |
| FP8 compute rate | 419 TFLOPS (dense), 838 with sparsity |
| FP16 / BF16 compute rate | 209.5 TFLOPS (dense), 419 with sparsity |
| INT8 compute rate | 838 TOPS (dense), 1,676 with sparsity |
| Process node | TSMC 4N |
| Board power | 575 W |
Frequently asked questions
How much does it cost to rent a Nvidia RTX 5090 per hour?
As of September 6, 2026 the Nvidia RTX 5090 rents from $0.28 per GPU per hour at Vast.ai. The median across 5 providers is $0.65 and the dearest listing asks $0.70.
Who is the cheapest Nvidia RTX 5090 provider right now?
Vast.ai at $0.28 per GPU per hour. That is 57% under the median of $0.65, so renting from a mid-priced provider costs you $0.37 an hour more for the same silicon.
What does a Nvidia RTX 5090 cost per month?
At the cheapest listed rate of $0.28 per GPU per hour, one Nvidia RTX 5090 running non-stop for a 730-hour month costs $206. At the median rate it costs $475.
Can I actually get a Nvidia RTX 5090 today?
Yes. 4 of 5 providers reported Nvidia RTX 5090 stock at the last check. The cheapest one with confirmed stock is Vast.ai at $0.28 per GPU per hour.
How much VRAM does the Nvidia RTX 5090 have?
32 GB GDDR7 per board. That holds a model of roughly 12 billion parameters at 16-bit, or about 25 billion at 8-bit, before context and activations.
What architecture is the Nvidia RTX 5090, and when did it launch?
Blackwell, released Q1 2025. 5 cloud providers publish a price for it.