Partner with Nawa Request compute

Inference compute

Reserved capacity, close to the user.

Interactive models carry a round-trip budget, and every network leg spends part of it. Nawa places reserved capacity near the user, on modular infrastructure it develops and operates.

Positioning

Serving a model is a placement problem.

An interactive session has a time budget set by the person or the machine at the other end. Transit between the user and the accelerator spends that budget before the model does any work.

Nawa builds small, repeatable deployments, which makes placement a site decision. A module can go in near demand or inside a named jurisdiction, and a reservation holds its capacity for one buyer.

Workloads

Who this serves.

  • Video generation

    Interactive video models hold a session open while frames are produced, and the viewer notices every stall. The workload wants sustained accelerator time with a short network leg to the screen.

  • Vision-language-action models

    A model that perceives a scene and acts on it sits inside a control loop, and the machine sets the loop budget. Capacity placed near the deployment keeps transit out of that budget.

  • Interactive agents

    Agent sessions chain many model calls, and a person waits at the end of each one. Dedicated capacity keeps a shared queue out of the loop.

Structure

How the offer is put together.

Structure is public. Hardware, price, region, and term are settled in the agreement.

The deployment model

Nawa-operated
Nawa develops the infrastructure and operates it. The site and hardware agreements behind a deployment sit with Nawa.
Close to power
Deployments go in where capacity already exists on the grid or behind the meter, which is what sets the cost base.
Close to the user
Site selection weighs the distance to demand alongside the distance to power, so interactive workloads keep a short network leg.
Sovereign where required
Where data residency or regulation constrains placement, the deployment sits inside a named jurisdiction. Nawa works in the United States and selected international markets, and deploys in-country.

What a reservation covers

Capacity
A stated block of accelerators, held for the buyer across the term.
Placement
The jurisdiction, and the site where the workload requires one.
Service boundary
A stated redundancy model and a bounded service obligation, written into the contract.
Counterparty
Nawa on the contract, holding the site and hardware agreements behind the deployment.

Next

Bring the workload.

Say what you need to serve and where the users sit. A residency constraint, if one applies, shapes the site list.

Discuss inference capacity