GPU model
NVIDIA RTX PRO 6000 Blackwell: specs, VRAM and rental prices
NVIDIA’s NVIDIA RTX PRO 6000 Blackwell: 96 GB of GPU memory (GDDR7 with ECC), rented from $1.80 per GPU-hour on demand (Nebius). Specs from NVIDIA, prices as of Oct 25, 2026.
The RTX PRO 6000 Blackwell is a Blackwell-generation GPU with 96 GB of GDDR7 memory that NVIDIA announced in 2025. NVIDIA names a Server Edition for data center servers and a Workstation Edition for desktop workstations, with different memory bandwidth, and rental listings usually refer to the server card.
Prices were last checked Oct 25, 2026. A listing not re-checked for 7 days is greyed and left out of every lowest-price figure; after 14 days it is removed from the page.
NVIDIA RTX PRO 6000 Blackwell specifications
| Specification | Server Edition | Workstation Edition | Source |
|---|---|---|---|
| Architecture | Blackwell | Blackwell | nvidia.com |
| GPU memory | 96 GB | 96 GB | nvidia.com |
| Memory type | GDDR7 with ECC | GDDR7 with ECC | nvidia.com |
| Memory interface | 512-bit | Not published | nvidia.com |
| Memory bandwidth | 1,597 GB/s | 1,792 GB/s | nvidia.com |
| CUDA cores | 24,064 | Not published | nvidia.com |
| RT cores | 188 (fourth generation) | Fourth generation | nvidia.com |
| Tensor cores | Fifth generation | Fifth generation | nvidia.com |
| FP4 tensor | 4 PFLOPS | Not published | nvidia.com |
| FP8 tensor | 2 PFLOPS | Not published | nvidia.com |
| FP16 / BF16 tensor | 1 PFLOPS | Not published | nvidia.com |
| TF32 tensor | 234 TFLOPS | Not published | nvidia.com |
| FP32 | 120 TFLOPS | Not published | nvidia.com |
| AI TOPS | Not published | 4,000 | nvidia.com |
| FP64 | Not published | Not published | nvidia.com |
| Max power consumption | Up to 600 W (configurable) | 600 W | nvidia.com |
| Form factor | Air: dual-slot, FHFL; liquid: single-slot, FHXL | Not published | nvidia.com |
| Multi-Instance GPU | Up to 4 instances | Not published | nvidia.com |
NVIDIA’s Server Edition page prints the tensor throughput without saying whether it is dense or with sparsity, so the comparison pages do not compare it with figures that state a basis. NVIDIA lists no FP64 figure on these pages. Not published on the pages cited here: FP64 throughput; Whether the Server Edition tensor figures are dense or sparse.
Sources: NVIDIA RTX PRO 6000 Blackwell Server Edition page · NVIDIA RTX PRO 6000 Blackwell Workstation Edition page · RTX PRO Blackwell announcement (2025). Every figure above is copied from these NVIDIA pages; nothing is estimated.
RTX PRO 6000 rental prices by provider
Lowest listed price by pricing type
| Pricing | $ per GPU-hour | Provider | Checked |
|---|---|---|---|
| On-demand | $1.80 | Nebius | Oct 25, 2026 |
| Spot | $0.79 | Nebius | Oct 25, 2026 |
On-demand price by provider
Each provider’s lowest fresh on-demand listing, $ per GPU-hour.
Every listed RTX PRO 6000 price
| Provider | Configuration | Pricing | $ per GPU-hour | Region | Checked | Source |
|---|---|---|---|---|---|---|
| Nebius | Configuration not stated RTX PRO 6000 |
Spot | $0.79 Listed from $0.79 (preemptible) |
— | nebius.com | |
| Lium Sponsor | Server Edition · 96 GB each RTX PRO 6000 Blackwell Server Edition |
Marketplace | $1.19 Listed $1.19 – $1.99 (RTX PRO 6000 Blackwell Server Edition) |
— | lium.io | |
| CoreWeave | Server Edition · 8 GPUs per instance · 96 GB each RTX PRO 6000 Blackwell Server Edition (Standard Memory) |
Spot | $1.20 Listed $9.56/hr per 8-GPU instance (spot) |
North America | coreweave.com | |
| CoreWeave | Server Edition · 8 GPUs per instance · 96 GB each RTX PRO 6000 Blackwell Server Edition (High Memory) |
Spot | $1.39 Listed $11.09/hr per 8-GPU instance (spot) |
North America | coreweave.com | |
| Hyperstack | SE · 96 GB each RTX Pro 6000 SE |
Spot | $1.48 | — | hyperstack.cloud | |
| Lium Sponsor | Workstation Edition · 96 GB each RTX PRO 6000 Blackwell Workstation Edition |
Marketplace | $1.60 Listed $1.60 (RTX PRO 6000 Blackwell Workstation Edition) |
— | lium.io | |
| RunPod Community Cloud | 96 GB each RTX Pro 6000 |
Marketplace | $1.69 Listed $1.69/hr (RTX Pro 6000, Community Cloud) |
— | runpod.io | |
| Nebius | Configuration not stated RTX PRO 6000 |
On-demand | $1.80 | — | nebius.com | |
| Hyperstack | SE · 96 GB each RTX Pro 6000 SE |
On-demand | $1.85 | — | hyperstack.cloud | |
| CoreWeave | Server Edition · 8 GPUs per instance · 96 GB each RTX PRO 6000 Blackwell Server Edition (High Memory) |
On-demand | $2.50 Listed $20.00/hr per 8-GPU instance |
North America and Europe | coreweave.com | |
| AWS | Server Edition · 1 GPU per instance · 96 GB each g7e.2xlarge |
On-demand | $3.36 Listed $3.36/hr per 1-GPU instance |
us-east-1 | aws.amazon.com | |
| AWS | Server Edition · 2 GPUs per instance · 96 GB each g7e.12xlarge |
On-demand | $4.14 Listed $8.29/hr per 2-GPU instance |
us-east-1 | aws.amazon.com | |
| AWS | Server Edition · 8 GPUs per instance · 96 GB each g7e.48xlarge |
On-demand | $4.14 Listed $33.14/hr per 8-GPU instance |
us-east-1 | aws.amazon.com | |
| Oracle Cloud | 8 GPUs per instance · 96 GB each · 8x400 Gb/s RDMA BM.GPU.RTXPro.8 |
On-demand | $4.50 Listed $4.5 per GPU per hour (OCI - Compute - GPU - RTX PRO 6000) |
— | apexapps.oracle.com | |
| Microsoft Azure | Server Edition · 1 GPU per instance · 96 GB each Standard_NC144lds_xl_RTXPRO6000BSE_v6 |
On-demand | $5.50 Listed $5.50/hr per 1-GPU instance |
eastus | prices.azure.com | |
| Microsoft Azure | Server Edition · 2 GPUs per instance · 96 GB each Standard_NC288ds_xl_RTXPRO6000BSE_v6 |
On-demand | $5.50 Listed $11.00/hr per 2-GPU instance |
eastus | prices.azure.com | |
| Microsoft Azure | Server Edition · 2 GPUs per instance · 96 GB each Standard_NC288lds_xl_RTXPRO6000BSE_v6 |
On-demand | $5.50 Listed $11.00/hr per 2-GPU instance |
eastus | prices.azure.com | |
| Microsoft Azure | Server Edition · 1 GPU per instance · 96 GB each Standard_NC144ds_xl_RTXPRO6000BSE_v6 |
On-demand | $6.38 Listed $6.38/hr per 1-GPU instance |
eastus | prices.azure.com |
Download: current prices (CSV) · current prices (JSON) · daily history (CSV) · price-change feed (RSS). Free to reuse with attribution under CC BY 4.0.
Compare the RTX PRO 6000 with other GPUs
- RTX PRO 6000 vs L40S: specs side by side with the lowest listed rental price for each.
- RTX PRO 6000 vs H100: specs side by side with the lowest listed rental price for each.
Price history
The history chart appears once there are two daily snapshots of an on-demand price. Tracking began Oct 15, 2026; the first snapshot has the lowest listed on-demand price at $1.80 per GPU-hour.
Embed this chart
<iframe src="https://datacentercensus.com/embed/gpu-prices/rtx-pro-6000" title="NVIDIA RTX PRO 6000 Blackwell rental prices" width="100%" height="500" style="border:0;max-width:640px" loading="lazy"></iframe>
<p style="font:13px/1.4 system-ui,sans-serif;margin:6px 0 0">Source: <a href="https://datacentercensus.com/gpu-prices/rtx-pro-6000">Data Center Census</a></p>
<script>addEventListener("message",function(e){if(e.origin==="https://datacentercensus.com"&&e.data&&e.data.dcc){document.querySelectorAll('iframe[src^="https://datacentercensus.com/embed/"]').forEach(function(f){if(f.contentWindow===e.source)f.style.height=e.data.h+"px"})}})</script>Free with the credit line. Preview the embed.
How these prices are collected
- What counts
- Only prices a provider publishes on a public pricing page or in its public price list, opened by the Census on the day shown. A marketplace is listed under the same rule as every other provider: it must publish per-GPU-hour prices publicly, with no login, and its rows are shown with the type Marketplace. Quotes and “contact sales” rows are not listed, and neither are purchase prices.
- $ per GPU-hour
- The listed price per GPU-hour. Where a provider lists a price per instance, the Census divides it by the GPUs in that instance and shows the original figure under it. Nothing else is converted or estimated.
- Pricing types
- On-demand, spot (including tiers a provider calls preemptible or low-priority), reserved with the term the provider states, and marketplace. Reserved rows without a stated term are not listed. A marketplace row is the lowest per-GPU-hour price its public page shows for that GPU, which comes from third-party hosts and changes often. Marketplace rows are a separate type: they appear in the table, filters, downloads and feeds, but never in the “lowest on-demand” or “lowest spot” figures.
- Variants
- SXM, PCIe, NVL and similar versions are kept separate when the provider names them. A provider that does not name the variant is shown without one.
- Freshness
- Every listing carries the date it was last confirmed, and the daily run re-opens each one. If a listing goes 7 days without a re-check it stays on the page greyed, labelled with the date it was last confirmed, and drops out of the “lowest” figures and the calculator’s default results. At 14 days without a re-check it is taken off the site; the daily history still holds it.
- History
- Each daily run saves a snapshot, so the model pages can chart the lowest listed on-demand price over time and the change log can show what moved. History began Oct 15, 2026.
- Differences between providers
- Listed prices are not like for like: regions, minimum instance sizes, networking, storage, commitments and availability differ and are not priced here. Check the provider before relying on a figure.
Providers checked but not listed
- Google Cloud: The compute pricing pages (cloud.google.com/compute/gpus-pricing and vm-instance-pricing) showed no GPU prices when opened.
- Vast.ai: Its pricing page loads live "from" prices from a public JSON file whose terms allow display and citation with attribution but require a data license for bulk collection, redistribution or use in any index, benchmark or derivative product. The Census republishes prices as open data, so it does not list Vast.ai without that license.
- Voltage Park: Its pricing pages say "Contact for pricing" for every GPU; one homepage line says "Starting at $1.99/hr" without a GPU model or unit.
RTX PRO 6000: common questions
How much VRAM does the RTX PRO 6000 have?
NVIDIA lists 96 GB of GPU memory for the NVIDIA RTX PRO 6000 Blackwell, which is GDDR7 with ECC, with memory bandwidth of 1,597 GB/s (Server Edition), 1,792 GB/s (Workstation Edition). The specification table on this page shows each figure with the page it came from.
How much power does the RTX PRO 6000 use?
NVIDIA lists the NVIDIA RTX PRO 6000 Blackwell at Up to 600 W (configurable) (Server Edition), 600 W (Workstation Edition).
How much does it cost to rent a RTX PRO 6000 per hour?
The lowest listed on-demand price among listings checked in the last 7 days is $1.80 per GPU-hour at Nebius, checked Oct 25, 2026. 18 fresh listings from 8 providers are shown in the table above, including spot, reserved and marketplace prices.
Which providers list RTX PRO 6000 prices?
Nebius, Lium, CoreWeave, Hyperstack, RunPod Community Cloud, AWS, Oracle Cloud, Microsoft Azure.
Which architecture is the RTX PRO 6000 built on, and when was it announced?
The NVIDIA RTX PRO 6000 Blackwell uses the Blackwell architecture and was announced or launched in 2025, according to the NVIDIA page cited in the specifications.
Related: All GPU prices · GPU comparisons · Rental cost calculator · H100 · H200 · B200 · B300 · GB200 NVL72 · GB300 NVL72 · A100 · L40S · L4 · T4 · MI300X · MI325X · MI355X
Cite this page
Last updated Oct 25, 2026. Figures may change as records are updated — include the date you retrieved them.
| APA | Data Center Census. (2026). NVIDIA RTX PRO 6000 Blackwell specs and rental prices. Retrieved from https://datacentercensus.com/gpu-prices/rtx-pro-6000 |
|---|---|
| MLA | “NVIDIA RTX PRO 6000 Blackwell specs and rental prices.” Data Center Census, Oct 25, 2026, https://datacentercensus.com/gpu-prices/rtx-pro-6000. |
| Link | https://datacentercensus.com/gpu-prices/rtx-pro-6000 |
Republishing a figure or table? Attribute it to Data Center Census with a link to this page. The underlying data is downloadable as JSON and CSV; the press kit has standing figures and contact details.