NVIDIA GB300 NVL72
Rent 72 Blackwell Ultra GPUs and 36 Grace CPUs in one NVLink domain, built for AI reasoning and trillion-parameter inference.
NVIDIA GB300 NVL72 Pricing & Specs
Together provisions, tunes, and operates the liquid-cooled system with high-performance storage, monitoring, and direct support from the research team. Your data and model weights stay yours, backed by SOC 2 Type II controls.
10x
vs Hopper GPUs
5x
vs Hopper GPUs
1.5x
vs GB200 NVL72
Pricing
Rent GB300 NVL72 on demand, or reserve dedicated capacity at a lower rate. All prices are per GPU per hour.
Plan | Price |
|---|---|
On-demand (pay as you go) | — |
Reserved 7-30 days | Contact us |
Reserved 31-90 days | |
Reserved 91-180 days | |
Reserved 181+ days |
Prices as of July 2026.
See pricing for every GPU on the GPU cluster pricing page.
Technical specification
- Configuration 36 Grace CPU: 72 Blackwell Ultra GPUs
- FP4 Tensor Core 1,400 PFLOPS (with sparsity) | 1,100 PFLOPS (dense)
- FP8/FP6 Tensor Core 720 PFLOPS
- INT8 Tensor Core 23 PFLOPS
- FP16/BF16 Tensor Core 360 PFLOPS
- TF32 Tensor Core 180 PFLOPS
- FP32 6 PFLOPS
- FP64 / FP64 Tensor Core 100 TFLOPS
- GPU Memory | Bandwidth Up to 21 TB | Up to 576 TB/s
- NVLink Bandwidth 130 TB/s
- CPU Core Count 2,592 Arm® Neoverse V2 cores
- CPU Memory | Bandwidth Up to 18 TB SOCAMM with LPDDR5X | Up to 14.3 TB/s
Why Rent NVIDIA GB300 NVL72 on Together
The world’s most powerful AI infrastructure. Delivered faster. Tuned smarter.
A single 72-GPU NVLink domain for reasoning at scale
GB300 unifies 72 Blackwell Ultra GPUs and 36 Grace CPUs in one platform, optimized for test-time scaling inference.
Purpose-built for AI reasoning throughput
Compared to Hopper, GB300 delivers 10x higher TPS per user and 5x higher TPS per megawatt, combining to 50x higher AI-factory output.
Massive on-rack memory for frontier contexts
Run long-context LLMs and agentic workloads with up to 21 TB of aggregate GPU HBM (up to 576 TB/s bandwidth) and up to 40 TB fast memory.
Run by the same people pushing the Blackwell stack forward
Work with engineers who co-develop Blackwell optimizations; our team continually tunes workloads and publishes cutting-edge training breakthroughs.
What our customers are saying
"Delivering competitive pricing, strong reliability and a properly set up cluster is the bulk of the value differentiation for most AI clouds. The only differentiated value we have seen outside this set is from a Neocloud called Together AI, where the inventor of FlashAttention, Tri Dao, works. We don't believe the value created by Together can be replicated elsewhere."
"Together GPU Clusters provided a combination of amazing training performance, expert support, and the ability to scale to meet our rapid growth to help us serve our growing community of AI creators."
Demi Guo
CEO, Pika
“Together AI provides the performance and reliability we need for real-time, high-quality image and video generation at scale. We value that Together AI is much more than an infrastructure provider — they're a true innovation partner, enabling us to push creative boundaries without compromise.”
Victor Perez
Co-Founder, Krea
Rent NVIDIA GB300 NVL72 GPUs on Together GPU Clusters
Scale from one node to a full rack
Rent GB300 NVL72 sized to your run, from a single node to a full 72-GPU rack or multiple racks, all in one NVLink domain.
Fully managed, your data stays yours
Together provisions, tunes, and operates the liquid-cooled system with high-performance storage, monitoring, and direct support from the research team. Your data and model weights stay yours, backed by SOC 2 Type II controls.
Ready to put GB300 NVL72 to work?
See GPU cluster pricing for full details.
Infrastructure you can trust at scale.
Production-grade security.
We take security and compliance seriously, with strict data privacy controls to keep your information protected. Your data and models remain fully under your ownership, safeguarded by robust security measures.
preferred partner
SOC 2 Type II
ISO 27001:2022
Regions and availability zones
Choose from global regions to meet data residency and compliance requirements—HIPAA for healthcare, GDPR for Europe, or banking regulations.
USA2GW+ in the portfolio with 600MW of near-term capacity in US.
Europe150 MW+ available in Europe: UK, Spain, France, Portugal, and Iceland also.
Asia & Middle EastOptions available based on the scale of the projects in Asia and the Middle East.
FAQ
What is the NVIDIA GB300 NVL72?
The GB300 NVL72 is the Blackwell Ultra system, connecting 72 Blackwell Ultra GPUs and 36 Grace CPUs into one liquid-cooled NVLink domain, with 288GB of HBM3e per GPU and around 1.1 exaFLOPS of FP4 compute, built for AI reasoning and trillion-parameter inference.
How much does it cost to rent a GB300 NVL72?
GB300 NVL72 is offered to rent as reserved capacity, priced per GPU or per rack by quantity, term, and region. Contact sales for a current quote.
Can I rent GB300 GPUs by the hour?
GB300 NVL72 is available to rent as reserved capacity rather than by the hour. You can rent any count, from a single node up to a full rack or multiple racks. Contact sales to get started.
How much memory does the GB300 have?
Each Blackwell Ultra GPU has 288GB of HBM3e. A full NVL72 rack holds up to 21TB of HBM3e, and up to 40TB of fast memory including the Grace CPUs.
What is the GB300 memory bandwidth?
Each Blackwell Ultra GPU provides 8TB/s of memory bandwidth, with 130TB/s of NVLink bandwidth across the rack.
What is the power consumption of the GB300 NVL72?
The GB300 NVL72 is a 100% liquid-cooled system drawing roughly 120kW per rack, handled by Together's data center infrastructure.
Is the GB300 NVL72 available on demand or only reserved?
It is offered to rent as reserved capacity. Contact sales to check availability.
Which regions are GB300 NVL72 clusters available in?
Across the US, Europe, and select Asia and Middle East regions, supporting data-residency and compliance needs.
How is the GB300 different from the GB200?
The GB300 uses Blackwell Ultra GPUs with 288GB of HBM3e (versus 186GB on the GB200) and adds roughly 1.5x the FP4 compute, with a focus on AI reasoning and test-time scaling inference.
How many GPUs are in a GB300 NVL72?
A full NVL72 rack contains 72 Blackwell Ultra GPUs and 36 Grace CPUs.
Browse other NVIDIA GPUs
Self-serve GPUs with transparent billing.