Early access

Rent GPUs by the day.

Whole machines we build and host in Oregon, never a slice of one. Tell us what you need and we match one.

Pick a node.

Node	GPU memory	Memory bandwidth	Between GPUs	Form factor
NVIDIA H200 NVL	141 GB HBM3e per GPU	4.8 TB/s per GPU	NVLink	4U rack
NVIDIA RTX PRO 6000 Server Edition	96 GB GDDR7 per GPU	1.6 TB/s per GPU	PCIe	4U rack
NVIDIA RTX 5090	32 GB GDDR7 per GPU	1.8 TB/s per GPU	PCIe	Workstation tower

Market rate: The median hourly price for this GPU across public listings on other marketplaces, polled live. It is context, not a B3IQ price.

Own one: NVIDIA H200 NVL · Own one: NVIDIA RTX PRO 6000 Server Edition · Own one: NVIDIA RTX 5090

The facility

48 hour burn-in
~90% carbon-free grid
N+1 redundant power
24/7 monitoring and on-call

Tour the facility · Security and compliance

Size a cluster.

Ask for up to 104 GPUs, in whole nodes of 8. Networking between nodes is arranged on request.

Call models on your own machines.

Use an OpenAI-compatible API for models your machines serve. Your gateway key routes only to your account’s machines, with no per-request B3IQ charge.

OpenAI-compatible

Use the supported chat, streaming, and model-list methods with your gateway key.

We don’t train on your prompts.

On the hosted API path, B3IQ doesn’t sell or store prompt and output content.

How we handle prompts

What do you need?

1. You ask: A GPU, a count, dates, and what it’s for.
2. We match a machine: Our team finds a node that fits.
3. You confirm: Nothing starts until you do.

Availability, exact configuration, dates and price are confirmed with our team before anything starts.

A request starts with a short call. Your choices come with it. Book a call · Browse machines

Don’t know the size yet?

Tell the team what you’re running. They’ll help you size it. Book a call