Nvidia RTX PRO 6000

Nvidia RTX PRO 6000

Blackwell server GPU for AI inference and visualization.

Compare vs other GPUs →
Aggregating historical prices...

Weekly median price per GPU per hour. Nvidia RTX PRO 6000 price history (JSON).

At a glance

Hardware

Architecture
Blackwell
Memory per GPU
96 GB GDDR7
Memory bandwidth
1,597 GB/s
Release date
Q1 2025

Market Updated 15 minutes ago

Cheapest in stock
$0.66 / GPU / hr
on-demand · 1x · Packet·ai
Median price
$2.19 / GPU / hr
on-demand
90-day trend
+5%
median on-demand
Coverage
44 providers
127 of 334 configs in stock

RTX PRO 6000 Pricing and Availability

44 providers

How this list works

The two views

By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.

Order

What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.

Within a group, five factors set the order:

  1. Location: datacenter proximity, blended with provider HQ.
  2. Price: hourly price, per GPU and in total.
  3. Billing type: reserved ahead of spot, spot ahead of quote-only.
  4. Specs: more VRAM, vCPUs and RAM.
  5. Provider diversity: a provider's repeat rows rank slightly lower, so one company can't take all the top spots.

Search

We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.

Transparency and funding

  • Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
  • Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
  • Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.
Packet·ai logo

Packet·ai

Our sponsor

United States of America flag USA 2 configs 1x

On-Demand from $0.66 Custom on request
From $0.66 / GPU / hr On-Demand Visit website
Lium logo

Lium

In stock

United States of America flag USA 6 configs 1x-8x

On-Demand from $1.19
From $1.19 / GPU / hr On-Demand Visit website
Vast.ai logo

Vast.ai

In stock

United States of America flag USA 61 configs 1x-8x

On-Demand from $1.18 Reserved from $1.06 Spot from $0.40
From $1.18 / GPU / hr On-Demand Visit website
EcoHash logo

EcoHash

In stock

United States of America flag USA 4 configs 1x-8x

On-Demand from $1.89
From $1.89 / GPU / hr On-Demand PCIe Visit website
Runpod logo

Runpod

In stock

United States of America flag USA 6 configs 1x-8x

On-Demand from $2.09 Reserved on request
From $2.09 / GPU / hr On-Demand Visit website
Geodd logo

Geodd

In stock

United States of America flag USA 4 configs 1x-8x

On-Demand from $2.14
From $2.14 / GPU / hr On-Demand PCIe Visit website
Massed Compute logo

Massed Compute

In stock

United States of America flag USA 8 configs 1x-8x

On-Demand from $2.19
From $2.19 / GPU / hr On-Demand Visit website
Runcrate logo

Runcrate

In stock

United States of America flag USA 1 config 1x

On-Demand from $2.41
From $2.41 / GPU / hr On-Demand PCIe Visit website
Koyeb logo

Koyeb

In stock

France flag France 1 config 1x

On-Demand from $2.20
From $2.20 / GPU / hr On-Demand Visit website
Sesterce logo

Sesterce

In stock

France flag France 18 configs 1x-8x

On-Demand from $2.41
From $2.41 / GPU / hr On-Demand Visit website
Verda logo

Verda

In stock

Finland flag Finland 35 configs 1x-8x

On-Demand from $1.89 Reserved from $1.42 Spot from $0.94
From $1.89 / GPU / hr On-Demand Visit website
GPU.ai logo

GPU.ai

In stock

United Arab Emirates flag UAE 2 configs 1x-2x

On-Demand from $1.99
From $1.99 / GPU / hr On-Demand Visit website
Cloudzy logo

Cloudzy

In stock

United Arab Emirates flag UAE 2 configs 1x

On-Demand from $1.93 Reserved from $1.81
From $1.93 / GPU / hr On-Demand PCIe Visit website
HyperAI logo

HyperAI

In stock

Hong Kong flag Hong Kong 8 configs 1x-8x

On-Demand from $0.80 Reserved from $0.48
From $0.80 / GPU / hr On-Demand Visit website
GPUhub logo

GPUhub

In stock

Singapore flag Singapore 4 configs 1x-8x

On-Demand from $0.91
From $0.91 / GPU / hr On-Demand Visit website
Latitude.sh logo

Latitude.sh

In stock

Brazil flag Brazil 3 configs 8x

On-Demand from $6.00 Reserved from $2.10
From $6.00 / GPU / hr On-Demand Visit website
Spheron logo

Spheron

In stock

Singapore flag Singapore 1 config 1x

Spot from $1.32
From $1.32 / GPU / hr Spot PCIe Visit website
GPUaaS logo

GPUaaS

In stock

United States of America flag USA 1 config 8x

Custom on request
Pricing On request Custom Visit website
Beam logo

United States of America flag USA 1 config 1x

On-Demand from $1.09
From $1.09 / GPU / hr On-Demand PCIe Visit website
Enverge logo

United States of America flag USA 1 config 1x

On-Demand from $1.95
From $1.95 / GPU / hr On-Demand Visit website
Cerebrium logo

United States of America flag USA 4 configs 1x-8x

On-Demand from $2.50
From $2.50 / GPU / hr On-Demand Visit website
Fal.ai logo

United States of America flag USA 2 configs 1x

On-Demand from $2.99 Custom from $1.10
From $2.99 / GPU / hr On-Demand Visit website
Hugging Face logo

United States of America flag USA 4 configs 1x-8x

On-Demand from $2.75
From $2.75 / GPU / hr On-Demand Visit website
Akamai Cloud logo

United States of America flag USA 4 configs 1x-8x

On-Demand from $3.00
From $3.00 / GPU / hr On-Demand Visit website
Amazon Web Services logo

AWS

United States of America flag USA 6 configs 1x-8x

On-Demand from $3.36
From $3.36 / GPU / hr On-Demand Visit website
Google Cloud logo

United States of America flag USA 16 configs 1x-8x

On-Demand from $4.50 Reserved from $1.98 Spot from $1.69
From $4.50 / GPU / hr On-Demand Visit website
Microsoft Azure logo

United States of America flag USA 40 configs 1x-2x

On-Demand from $5.50 Reserved from $2.42 Spot from $1.02
From $5.50 / GPU / hr On-Demand Visit website
Nebius logo

Netherlands flag Netherlands 2 configs 1x

On-Demand from $1.80 Spot from $0.95
From $1.80 / GPU / hr On-Demand PCIe Visit website
Hyperstack logo

United Kingdom flag UK 3 configs 1x

On-Demand from $1.85 Reserved from $1.30 Spot from $1.48
From $1.85 / GPU / hr On-Demand Visit website
CoreWeave logo

United States of America flag USA 3 configs 8x

On-Demand from $2.50 Spot from $1.20
From $2.50 / GPU / hr On-Demand Visit website
SwissGPU logo

Switzerland flag Switzerland 1 config 1x

On-Demand from $1.85
From $1.85 / GPU / hr On-Demand Visit website
Exoscale logo

Switzerland flag Switzerland 4 configs 1x-8x

On-Demand from $2.00
From $2.00 / GPU / hr On-Demand Visit website
Hetzner logo

Germany flag Germany 1 config 1x

On-Demand from $2.23
From $2.23 / GPU / hr On-Demand Visit website
Elastx logo

Sweden flag Sweden 1 config 1x

On-Demand from $2.94
From $2.94 / GPU / hr On-Demand Visit website
Leafcloud logo

Netherlands flag Netherlands 3 configs 1x-4x

On-Demand from $3.21
From $3.21 / GPU / hr On-Demand PCIe Visit website
Oracle Cloud logo

United States of America flag USA 1 config 8x

On-Demand from $4.50
From $4.50 / GPU / hr On-Demand Visit website
AceCloud logo

India flag India 28 configs 1x-4x

On-Demand from $2.74 Reserved from $2.00
From $2.74 / GPU / hr On-Demand Visit website
Database Mart logo

United States of America flag USA 3 configs 1x

Reserved from $0.90
From $0.90 / GPU / hr Reserved (24mo) Visit website
Oblivus logo

United States of America flag USA 8 configs 1x-8x

On-Demand from $2.60 (sold out) Reserved from $2.00
From $2.00 / GPU / hr Reserved (6mo) PCIe Visit website
Cirrascale logo

United States of America flag USA 4 configs 8x

Reserved from $1.39
From $1.39 / GPU / hr Reserved (12mo) Visit website
Contabo logo

Germany flag Germany 2 configs 1x

Reserved from $2.26
From $2.26 / GPU / hr Reserved (1mo) Visit website
Leaseweb logo

Netherlands flag Netherlands 4 configs 1x-2x

Reserved from $0.91
From $0.91 / GPU / hr Reserved (1mo) Visit website
Utho logo

India flag India 1 config 1x

Reserved from $1.71
From $1.71 / GPU / hr Reserved (36mo) Visit website
Nova Cloud logo

Nova Cloud

Out of stock

Canada flag Canada 20 configs 1x-8x

On-Demand from $1.26 Reserved from $1.01 Spot from $0.30
From $1.26 / GPU / hr On-Demand PCIe Visit website

Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.

What size AI models can the RTX PRO 6000 run?

One RTX PRO 6000 has 96 GB of VRAM. In practice, that's enough memory for roughly 146B parameters at 4-bit or 38B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.

Model Parameters 4-bitINT4 / FP4 8-bitFP8 / INT8 16-bitFP16 / BF16
Alibaba Cloud logo Qwen3.8-27B
27B
1 GPU 18 GB VRAM · $1,577/mo
1 GPU 30 GB VRAM · $1,577/mo
1 GPU 58 GB VRAM · $1,577/mo
Google Cloud logo Gemma 4 31B
30.7B
1 GPU 22 GB VRAM · $1,577/mo
1 GPU 35 GB VRAM · $1,577/mo
1 GPU 69 GB VRAM · $1,577/mo
OpenAI logo GPT-OSS-120B
117B 5.1B active
1 GPU 67 GB VRAM · $1,577/mo
2 GPUs 120 GB VRAM · $3,154/mo
4 GPUs 237 GB VRAM · $6,307/mo
DeepSeek logo DeepSeek V4 Flash
284B 13B active
2 GPUs 160 GB VRAM · $3,154/mo
4 GPUs 287 GB VRAM · $6,307/mo
8 GPUs 573 GB VRAM · $12,614/mo
Z.AI logo GLM-5.3-Flash
320B 18B active
4 GPUs 178 GB VRAM · $6,307/mo
4 GPUs 322 GB VRAM · $6,307/mo
8 GPUs 642 GB VRAM · $12,614/mo
MiniMax logo MiniMax-M3
428B 23B active
4 GPUs 239 GB VRAM · $6,307/mo
8 GPUs 432 GB VRAM · $12,614/mo
10 GPUs 862 GB VRAM
Moonshot AI logo Kimi K3
2.8T 104B active
18 GPUs 1,544 GB VRAM
33 GPUs 2,804 GB VRAM
65 GPUs 5,605 GB VRAM

Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Technical Specifications

Nvidia RTX PRO 6000 · Per GPU · PCIe

Compute · dense
FP4 2,000 TFLOPS 4,000 with sparsity
FP8 1,000 TFLOPS 2,000 with sparsity
FP16 / BF16 500 TFLOPS 1,000 with sparsity
INT8 1,000 TOPS 2,000 with sparsity
FP32 120 TFLOPS
Precision support FP4FP8FP16BF16TF32FP32INT8
Memory
Capacity 96 GB GDDR7
Bandwidth 1,597 GB/s
Bus width 512-bit
ECC Yes
Silicon
Architecture Blackwell
Process TSMC 4N
Transistors 92.2 billion
Shader cores 24,064 CUDA cores
Matrix cores 752 Tensor cores
Compute units 188 SMs
Fabric and host
Host interface PCIe 5.0 x16
Power
Board power 600 W
Cooling Passive

Source: official Nvidia RTX PRO 6000 datasheet.

Frequently Asked Questions

How much does the RTX PRO 6000 cost per hour?

As of September 8, 2026, the median on-demand price is $2.19 per GPU per hour across 35 providers with a priced on-demand config.

Billing type Configs Median / GPU / hr Cheapest
On-demand 155 $2.19 $0.66 (in stock, Packet·ai)
Reserved 130 $1.81 $0.48 (1 mo, in stock, HyperAI)
Spot 46 $1.19 $0.40 (in stock, Vast.ai)
Custom contract 3 $1.10

No median for custom-contract: we only show this when at least 3 providers list the GPU on that billing type. Custom-contract pricing is negotiated per deal and usually not published.

Who has the cheapest RTX PRO 6000?

As of September 8, 2026, the cheapest verified in-stock on-demand RTX PRO 6000 tracked by GetDeploying is $0.66 per GPU per hour from Packet·ai. Cheapest verified in stock on other billing types: reserved $0.48 (1 mo) from HyperAI and spot $0.40 from Vast.ai.

How much does the RTX PRO 6000 cost per month?

As of September 8, 2026, at 720 hours per month, one RTX PRO 6000 costs an estimated $1,577 at the median on-demand price. Cheapest verified in stock: $475 per month on-demand, $346 reserved (1 mo), $288 spot.

Where can I rent an RTX PRO 6000?

GetDeploying currently tracks RTX PRO 6000 configs from 44 providers. The cheapest verified in-stock on-demand configs come from Packet·ai, HyperAI, GPUhub and Vast.ai. See the full price comparison above for every provider and config.

Are RTX PRO 6000 prices going up or down?

As of September 8, 2026, the median on-demand price has risen about 5% over the past 90 days to $2.19 per GPU per hour, and about 22% over the past 12 months.

How many RTX PRO 6000 GPUs do I need?

One RTX PRO 6000 runs models up to roughly 146B parameters at 4-bit quantization or 38B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.

Why choose the RTX PRO 6000?

96GB GDDR7 with Blackwell FP4 Tensor Cores. Fits very large models and datasets on a single GPU.

When is the RTX PRO 6000 not a good fit?

No NVLink, and GDDR7 at 1,597 GB/s is about half the memory bandwidth of an HBM part like the H100, so multi-GPU training runs over PCIe and memory-bound inference runs slower per card. For large distributed training, the B200 or H200 is the better fit.

Alternatives to Nvidia RTX PRO 6000

Last updated