RTX PRO 5000 Blackwell from $0.15 per GPU-hour
RTX PRO 5000 Blackwell is a professional workstation card with ECC memory with 48 GB of GDDR7, built on the Blackwell architecture in 2025. It holds models in the 20–30B range at FP16, or much larger ones once quantised. Memory bandwidth is 1,344 GB/s, which is what sets token throughput for inference.
Billed per started minute. 192 GB of GPU memory on a 4× node. Persistent storage $0.08 per GB-month. No egress fees.
- GPU memory
- 48GBGDDR7
- Bandwidth
- 1,344GB/sSets token throughput on inference
- Node sizes
- 1× · 2× · 4×Same price per GPU at every size
- Reclaim rate
- 5–10%Spot instances reclaimed over 30 days
What you get with each RTX PRO 5000 node.
| Node | GPU memory | vCPU | RAM | Local NVMe | Spot | On-demand | Action |
|---|---|---|---|---|---|---|---|
| 1× RTX PRO 5000 | 48 GB | 12 | 96 GB | 1 TB | $0.15/h | $0.29/h | Configure |
| 2× RTX PRO 5000 | 96 GB | 24 | 192 GB | 2 TB | $0.30/h | $0.58/h | Configure |
| 4× RTX PRO 5000 | 192 GB | 48 | 384 GB | 4 TB | $0.60/h | $1.16/h | Configure |
GPU-to-GPU link: PCIe 5.0 x16. Local NVMe is scratch space wiped when the instance ends; keep anything you need on a persistent disk.
32 RTX PRO 5000 GPUs free right now.
Straight from the capacity pool the console books against. Prices are identical in every region — pick the one closest to your data.
A region with zero free GPUs still accepts reserved capacity requests — we hold hardware for a term rather than sell what is already taken.
What fits in 48 GB — and what it costs per hour.
Weights need about 2 GB per billion parameters at FP16 / BF16, 1 GB per billion parameters at FP8, 0.5 GB per billion parameters at INT4. We keep 20% of the memory free for activations, the KV cache and the CUDA context, then take the smallest node that still fits.
| Open model | Parameters | FP16 / BF16node · spot price | FP8node · spot price | INT4node · spot price |
|---|---|---|---|---|
| Mistral 7BAssistants, RAG, classification | 7.2B | 1× $0.15/h | 1× $0.15/h | 1× $0.15/h |
| Llama 3.1 8BAssistants, agents, fine-tuning | 8B | 1× $0.15/h | 1× $0.15/h | 1× $0.15/h |
| Gemma 2 27BHigher-quality assistants | 27B | 2× $0.30/h | 1× $0.15/h | 1× $0.15/h |
| Qwen2.5 32BCode and reasoning | 32B | 2× $0.30/h | 1× $0.15/h | 1× $0.15/h |
| Mixtral 8x7BMixture of experts, high throughput | 46.7B | 4× $0.60/h | 2× $0.30/h | 1× $0.15/h |
| Llama 3.3 70BThe common production baseline | 70B | 4× $0.60/h | 2× $0.30/h | 1× $0.15/h |
| Qwen2.5 72BMultilingual, long context | 72B | 4× $0.60/h | 2× $0.30/h | 1× $0.15/h |
| Mixtral 8x22BMixture of experts, large capacity | 141B | over 4× | 4× $0.60/h | 2× $0.30/h |
| Llama 3.1 405BLargest widely used open model | 405B | over 4× | over 4× | over 4× |
Real usage depends on context length, batch size and the serving engine: a long context can add tens of gigabytes of KV cache. Treat the table as the floor, not the ceiling — and if a job is close to the limit, take the next node size or quantise one step further.
What a dollar buys on an RTX PRO 5000.
Ranked 10 of 12 workstation models in this catalogue on cost per gigabyte of GPU memory.
GPU memory you get for $1.00 of spot time, per hour.
Bandwidth decides token throughput far more often than raw FLOPS.
Spot price divided by published FP32 throughput.
One GPU on spot, billed per minute, storage excluded.
Against the rest of the market
3 providers · September 2026- Median on-demand elsewhere
- $0.67Our on-demand is 57% below it
- Cheapest on-demand seen
- $0.66Our on-demand $0.29 is 56% below it
- 24 hours on one GPU
- $3.60 on spot$6.96 on-demand · $15.84 at the cheapest rate found elsewhere
Index built from published prices for the same GPU across 137 providers (public price index (getdeploying.com)), September 2026. How the guarantee is enforced.
What people run on an RTX PRO 5000 Blackwell.
Fine-tuning with LoRA and QLoRA
Comfortable for parameter-efficient training on 13B–34B models without sharding.
Inference servers
Holds 30B-class models quantised, or several smaller models side by side.
Anything that can checkpoint
On the spot tier this model is 48% below its own on-demand price, with a 2-minute notice before a reclaim.
NVIDIA RTX PRO 5000 Blackwell, as published by NVIDIA.
Taken from the vendor datasheet. Where a figure is not published, the row is absent rather than estimated.
- Vendor
- NVIDIA
- Architecture
- Blackwell (2025)
- Segment
- Workstation
- Memory
- 48 GB GDDR7
- Memory bandwidth
- 1,344 GB/s
- FP32
- 65 TFLOPS
- CUDA cores
- 14,080
- Board power
- 300 W
- Form factor
- PCIe dual-slot
- Interconnect
- PCIe 5.0 x16
- Multi-instance (MIG)
- Not available
- 8-bit float (FP8)
- Supported by the architecture
Source: www.nvidia.com · not confirmed on a vendor document
Software that runs on it
8 templatesPre-built environments, pulled on the node before you land on it. Or bring any OCI image from a public or private registry.
On the spot tier
5–10% reclaimed · 30 d- 2 minutes of notice on the metadata endpoint, a webhook and the console
- The instance is stopped, not deleted — disk and IP stay attached
- Auto-relaunch on the next free RTX PRO 5000, or switch the same disk to on-demand
- You save $3.36 a day per GPU against on-demand
If the RTX PRO 5000 is not the right fit.
Same memory or more, 40% cheaper on spot
A100 PCIe 80GB 80 GB HBM2e · Ampere $0.09/h spotNext step up in memory: 80 GB instead of 48 GB
RTX PRO 6000 Blackwell 96 GB GDDR7 · Blackwell $0.19/h spotSame Blackwell generation
RTX PRO 4500 Blackwell 32 GB GDDR7 · Blackwell $0.09/h spotSame Blackwell generation
Or put two of them side by side: RTX PRO 5000 vs RTX A6000 · RTX PRO 5000 vs A100 PCIe · RTX PRO 5000 vs RTX PRO 6000
RTX PRO 5000 Blackwell — the questions that come up
How much does an RTX PRO 5000 Blackwell cost per hour?
Spot is $0.15 per GPU-hour and on-demand is $0.29, both billed per minute — every started minute costs the hourly price divided by 60, so $0.0025 on spot. Reserved capacity is $0.19 per GPU-hour on a monthly commitment. Storage and egress are not included in that rate: persistent disks are $0.08 per GB-month and there are no egress fees.
How many GPUs can I put in one instance?
Node sizes are 1×, 2×, 4× — up to 4 RTX PRO 5000 Blackwell GPUs in a single virtual machine, with CPU, RAM and local NVMe scaled with the GPU count. The price per GPU is identical at every node size.
Can it run a 70B model?
Yes. At FP8, a 70B model needs about 70 GB for the weights, so it fits on 2× RTX PRO 5000 Blackwell ($0.30 per hour on spot) with roughly 20% of the memory left for activations and the KV cache.
Which regions have it?
Available now in US West (Oregon), EU Central (Frankfurt). Prices are identical in every region; pick the one closest to your data.
How often is a spot RTX PRO 5000 reclaimed?
Over the trailing 30 days, 5–10% of spot instances on this model were reclaimed. You get a 2-minute notice on the metadata endpoint, through a webhook and in the console; the instance is then stopped, never deleted, and the persistent disk stays attached.
Anything else about this model? Ask an engineer — the same people run the nodes.
An RTX PRO 5000 Blackwell for $0.15 an hour, running in under 60 seconds.
Pay as you go — no contracts, no minimum commitment. Add credit, launch, stop whenever you want.
Billed per minute from the moment the instance is reachable. Minimum credit $40, no subscription. 32 RTX PRO 5000 GPUs available right now.