Skip to content
InfratoApp
GPU prices / RTX-PRO-6000-96GB

NVIDIA RTX PRO 6000 96 GB

RTX-PRO-6000-96GB costs $0.80 to $4.00 per GPU-hour on demand across 19 cloud providers, cheapest at HyperAI. Prices were read from each provider's own pricing page, most recently on 2026-10-27.
Cheapest read 26 Oct · spread 5.0× · a missing provider is never an estimate
CHEAPEST $0.80/hrMEDIAN $1.95/hrSPREAD 5.0×PROVIDERS 19

Price by provider — cheapest first

Provider$/GPU·hr ↓Δ 7dTermsRead
HyperAI$0.80— 0.0%not stated26 Oct ↗
Shadeform$0.99— 0.0%not stated26 Oct ↗
Beam$1.09— 0.0%not stated27 Oct ↗
GPUhub$1.10— 0.0%not stated26 Oct ↗
Vast.ai$1.40— 0.0%on demand27 Oct ↗
Nova Cloud$1.56— 0.0%not stated26 Oct ↗
Lium$1.75▼ −12.1%not stated27 Oct ↗JSON
Hyperstack$1.85— 0.0%not stated26 Oct ↗
EcoHash$1.89— 0.0%not stated26 Oct ↗
Enverge$1.95— 0.0%not stated26 Oct ↗
Massed Compute$2.19— 0.0%not stated26 Oct ↗
Spheron$2.35— 0.0%not stated26 Oct ↗
RunPod$2.49— 0.0%on demand27 Oct ↗
Cerebrium$2.50— 0.0%not stated27 Oct ↗
3NV$2.50FIRST READINGnot stated27 Oct ↗
Verda (DataCrunch)$2.57▲ +4.1%on demand27 Oct ↗
Runcrate$2.59▼ −10.6%not stated26 Oct ↗
Modal$3.03— 0.0%not stated26 Oct ↗
Fal.ai$4.00FIRST READINGnot stated22 Oct ↗
Why a provider might be missing: its price is behind a quote form, older than 21 days, or flagged for review. A missing row is never an estimate.

Price history — cheapest daily reading

⚑ 7 of 12 weeks measuredWEEKLY LOW SHOWN
2026-08-05A FLAT MARK IS A WEEK WE DID NOT READ2026-10-21

Cost calculator

GPUs1×
Hours / month730 h
730 = 24/7 · on-demand rates only
HyperAI$584 /mo
Shadeform$723 /mo
Beam$796 /mo
GPUhub$803 /mo
Vast.ai$1,022 /mo
Nova Cloud$1,139 /mo
Lium$1,278 /mo
Hyperstack$1,351 /mo
EcoHash$1,380 /mo
Enverge$1,424 /mo
Massed Compute$1,599 /mo
Spheron$1,716 /mo
RunPod$1,818 /mo
Cerebrium$1,825 /mo
3NV$1,825 /mo
Verda (DataCrunch)$1,874 /mo
Runcrate$1,891 /mo
Modal$2,212 /mo
Fal.ai$2,920 /mo

Spec sheet

VRAM96 GB
Bandwidth1.79 TB/ssource
FP16○
FP8○
TDP600 Wsource
NVLinkPCIe 5 (no NVLink)source
ArchitectureBlackwell
Released2025source
6 of 8 figures held

Good for

Workstation inference/fine-tune up to ~70B with large VRAM & FP4 without HBM cost
reasoned from the specification, not measured · source

Benchmarks

llama3.1-8b Offline
60,680 Tokens/s
v6.0 · 10 accelerators · HPE
submission ↗
llama3.1-8b Server
59,633 Tokens/s
v6.0 · 10 accelerators · HPE
submission ↗
llama3.1-8b Interactive
53,055 Tokens/s
v6.0 · 10 accelerators · HPE
submission ↗
mixtral-8x7b Offline
41,242 Tokens/s
v6.0 · 10 accelerators · HPE
submission ↗
mixtral-8x7b Server
39,234 Tokens/s
v6.0 · 10 accelerators · HPE
submission ↗
llama2-70b-99 Offline
36,711 Tokens/s
v6.0 · 10 accelerators · HPE
submission ↗

LLMs that fit this GPU’s VRAM

FP16
~38B params
FP8
~76B params
FP4/INT4
~153B params
Qwen 72B @FP8; Llama 3.1 70B @FP8; 32B @FP16
ceilings at each precision, reasoned from VRAM · not a benchmark

Frequently asked

How much does an RTX-PRO-6000-96GB cost per hour right now?
$0.80 an hour at HyperAI, the cheapest of 19 sellers we read. The dearest posts $4.00 at Fal.ai. Every rate links to the page it was read from, with the date it was read.
Why do RTX-PRO-6000-96GB prices vary 5.0× between providers?
Because a GPU-hour is not one product. $0.80 at HyperAI and $4.00 at Fal.ai buy different things: interconnect, host CPU and RAM, storage, egress, support, and whether the capacity is dedicated or shared. We publish the posted rate for each and the page it came from, and do not blend them into one number.
What is the cheapest way to rent an RTX-PRO-6000-96GB long-term?
We hold no committed or reserved rate for this card — every figure here is an on-demand posted rate. Committed pricing is usually quoted rather than published, so the honest answer is that we cannot tell you, rather than a guess at a discount.
How fresh are these prices?
These rates were read between 2026-10-22 and 2026-10-27. Nothing older than 21 days is shown: a reading that goes stale is hidden rather than displayed with an old date, because a wrong price is worse than a missing one. Each row links to the page its figure came from, so any of them can be checked against the seller.
Which is cheaper for an RTX-PRO-6000-96GB — a region or a commitment?
Both move the number and they move it independently. Where a provider prices the same card in several regions we show the cheapest they charge anywhere and name the region, because a rate you can only get in Estonia is still a rate you can get. A committed term is a different contract rather than a discount on this one, so committed rates are kept out of the headline and shown separately.
Can a provider pay to be listed first for the RTX-PRO-6000-96GB?
No. The table has one stated sort at a time and nothing in it can be bought — a sponsor cannot enter it, reorder a row or change a rate. How the site is paid for, and the line each source of money does not cross, is set out under money and independence at /our-data#sec5.
Vs its class
Live cheapest rates
GPUCheapest $/hrVRAMFP8 TFLOPS
RTX-3090-24GB$0.09○○
RTX-A4000-16GB$0.10○○
RTX-4090-24GB$0.1624 GB○
RTX-5090-32GB$0.25○○
RTX-A4500-20GB$0.25○○
RTX-A5000-24GB$0.27○○

Cite this page

infratoapp, “RTX-PRO-6000-96GB cloud pricing”, read 26 October 2026. $0.80 per GPU-hour at HyperAI. https://www.infratoapp.com/gpu/RTX-PRO-6000-96GB
Reading date travels inside the citation. How we read this data →