---
title: "Dedicated Compute: reserved NVIDIA B300 capacity"
canonical: https://telnyx.com/products/dedicated-compute
---
# Dedicated Compute: reserved NVIDIA B300 capacity

[View as page](https://telnyx.com/products/dedicated-compute)

**Inference**

# Dedicated Compute

Reserved NVIDIA B300 nodes for inference, on GPUs we own.

[Talk to sales](https://telnyx.com/contact-us)

THE HARDWARE

## B300 nodes on bare metal, reserved for you

Each node is an 8U system built for large-scale inference serving.

* GPU  
8 x NVIDIA B300 on the NVIDIA HGX platform. 288 GB each, 2.3 TB per node.
* GPU interconnect  
NVIDIA NVLink with NVSwitch.
* CPU and memory  
2 x AMD EPYC 9575F, 128 cores per node, with 3 TB of DDR5-6400.
* Local storage  
8 x 7.6 TB E1.S NVMe SSD, plus 2 x 1.9 TB M.2 NVMe.
* Network  
8 x 800GbE (XDR800) and 2 x dual-port 200GbE (NDR200).
* Tenancy and security  
Single-tenant bare metal. Encryption in transit and at rest. SOC 2 Type II.

WHAT IS INCLUDED

## What a Dedicated Compute agreement includes

The capacity, the environment around it and the people who run it.

* Full-node reservation  
Your nodes are yours all day, every day, for the term. There is no daily window and no preemption.
* Single-tenant bare metal  
No other customer's workload runs on your assigned nodes.
* Cluster networking  
Eight 800 Gb/s ports on every node, one for each GPU, with RDMA across the cluster.
* A persistent environment  
Storage volumes, images and network configuration stay in place across the term.
* Hot-spare node pool  
Spare nodes on hand, with a 4-hour replacement target.
* A named team  
A named technical account manager, a shared Slack channel and 24/7 engineering support.

**PRICING**

## A public rate, fixed for the term

$8.50 per GPU-hour on NVIDIA B300, on a 12-month minimum agreement. Capacity is reserved for you and billed monthly. Larger commitments and longer terms are quoted by our team.

$8.50

per GPU-hour, 12-month minimum

[Talk to sales](https://telnyx.com/contact-us)

PRODUCTS

## Not ready for a term?

The same GPUs sit behind per-token inference. Start there and move to dedicated nodes when the workload calls for it.

[See all products](https://telnyx.com/products)

* ### Inference  
By the token. Open-weight models behind an OpenAI-compatible API, with no commitment.  
[Learn more](https://telnyx.com/products/inference)
* ### GPU Sandbox  
By the hour. A whole GPU node, self-serve, with no term.  
[Learn more](https://telnyx.com/products/gpu-sandbox)
* ### Cloud Storage  
Keep datasets, checkpoints and results next to your compute.  
[Learn more](https://telnyx.com/products/cloud-storage)
* ### Model Library  
The open-weight models available on Telnyx.  
[Learn more](https://telnyx.com/llm-library)

## Talk to us about capacity.

Tell us the workload, the GPU count and where it needs to sit. We will come back with a written rate.

[TALK TO SALES](https://telnyx.com/contact-us)[TEST THE PLATFORM](https://telnyx.com/sign-up)

## Talk to us about capacity.

Tell us the workload, the GPU count and where it needs to sit. We will come back with a written rate.

[TALK TO SALES](https://telnyx.com/contact-us)[TEST THE PLATFORM](https://telnyx.com/sign-up)

## FAQ

### What is Dedicated Compute?

Dedicated Compute is reserved, single-tenant NVIDIA B300 capacity on hardware Telnyx owns and operates. You rent the nodes for a term and they are yours around the clock.

### How much does Dedicated Compute cost?

$8.50 per GPU-hour on a 12-month minimum agreement. The rate is fixed for the full term.

### What is the minimum commitment?

12 months. Capacity is sold in whole nodes of 8 GPUs. \[SMALLEST DEAL SIZE FROM DEAL DESK\]

### What hardware do I get?

Bare-metal nodes with 8 NVIDIA B300 GPUs at 288 GB each, two AMD EPYC 9575F processors, 3 TB of system memory, 8 x 7.6 TB of local NVMe and eight 800GbE ports.

### Is the hardware shared with other customers?

No. Assigned nodes are single-tenant, with no oversubscription and no preemption.

### Where is the capacity located?

On Telnyx sites across the Americas, Europe, APAC and MENA. Placement is agreed with you, based on where your data and users are.

### What happens if a node fails?

We hold a hot-spare node pool and replace a failed node from it, with a 4-hour replacement target.

### How do I access the nodes?

\[ANSWER FROM PRODUCT: bare metal access, Kubernetes or Slurm\]

[Start building](https://telnyx.com/sign-up)
