Skip to content
Orbin TechNimbo
PortuguêsSign inRequest access
Orbin TechNimbo
Request access
Menu
PortuguêsSign in
GPU compute and inference API

Superintelligence, within reach of those who build.

Frontier models through one API. GPU compute over SSH. Choose the resources for what you want to build.
Request an invitationExplore GPUsAn account provides portal access. Service availability is shown separately. View account access
GPU capacity and inference, with one BRL ledger

Choose how you build.

Choose the model for the task.

Explore models through a common API, with capabilities and prices in the catalogue.

Take control of your compute.

Access your compute environment over SSH or integrate models through the API.

Understand the cost.

Review the price before launching a GPU and follow your usage in your account.

Start with an invitation.

Request an invitation, then choose a service and manage it in the portal.
GPU

Dedicated compute. Control for builders.

Your environment, with SSH access and connectivity included. Choose the GPU for what you want to build.
Explore GPUs
Models

Frontier models for your next product.

Choose a model for your application and connect through the Nimbo API, compatible with the OpenAI SDKs.
Explore models
Next up

DGX Spark

A dedicated environment for your models. Billed in Brazilian reais.

Decision models

Intelligence that decides, not just answers.

Build what comes next.

Request an invitation and tell the team what you want to build.
Request an invitation