NEW · PROJECT 02 — BRISBANE WEST, QUEENSLAND
KenvoltCOMPUTE & INFERENCE

FOR CUSTOMERS

Inference capacity,
arranged directly.

Kenvolt is developing capacity for open-model inference at its nodes in Canada and Australia. Capacity is arranged through direct agreements with our team, sized to what each customer needs.

WHAT WE OFFER

Capacity, models
and location.

Three things, agreed together in one contract.

Dedicated inference capacity

Reserved capacity on a Kenvolt node, held for you under a capacity agreement.

Managed open-model inference

We run widely used open models on that capacity. Volume and term are agreed by contract.

In-country hosting

Nodes in Canada and Australia. Data is processed in the country it serves.

Who it suits.

Organisations with steady, predictable demand that want capacity agreed in advance.

  • AI application companies with steady inference volume.
  • Enterprises and public bodies that need in-country processing.
  • Model and platform providers that need regional capacity.
  • Cloud and compute providers that need additional capacity.

HOW AN ENGAGEMENT WORKS

From first call
to go-live.

Each step is agreed in writing before the next one starts.

  1. Conversation

    We learn what you run today and what you expect to need.

  2. Requirements

    Models, volume, latency and data residency.

  3. Capacity proposal

    Where, how much and on what timeline.

  4. Agreement

    A direct capacity agreement setting volume and term.

  5. Staged go-live

    Capacity comes online in stages, aligned to project milestones.

Honest
about timing.

Capacity becomes available in line with project milestones. Nothing is operating yet.

Early conversations shape what is built: the models, volumes and locations customers need inform how each node is configured.

Kenvolt does not run a self-serve online platform at this stage. All capacity is arranged directly with our team.

QUESTIONS

Common
questions.

If yours is not here, ask us directly.

Can I buy capacity online?

No. Capacity is arranged directly with our team under a capacity agreement.

Which models do you run?

Widely used open models, agreed with each customer as part of the capacity proposal.

When is capacity available?

In line with project milestones. Both projects are in development and nothing is operating yet.

Where is data processed?

In the country of the site serving you: Canada or Australia.

TALK TO US

Tell us what
you need to run.

Share your models, volume, latency and residency needs. We will tell you plainly what we can offer and when.

Discuss capacity