Skip to main content

​
Brightnode console

The web interface for managing inference, compute, storage, API keys, usage, billing, and team resources.

​
Router

Brightnode’s hosted inference entrypoint. Router gives you one OpenAI-compatible base URL for the models Brightnode makes available through the shared catalog.

​
Model

A model is an inference target you can call through Router or deploy through Beams. Model IDs are passed directly in your API request, and may include slashes such as meta-llama/Llama-3.3-70B-Instruct.

​
API key

A Brightnode API key is a scoped credential for programmatic access. Current key scopes are centered on Inference and Deployments.

​
Bnode

A dedicated GPU or CPU instance for containerized AI/ML workloads, such as training models, running inference, or other compute-intensive tasks.

​
Network volume

Persistent storage that exists independently of your other compute resources. Network volumes are designed for durable datasets, checkpoints, and shared assets across Brightnode workflows.

​
Beams

The preview deployment workflow for managed inference models. Beams is intended for cases where you need deployment-level control instead of the shared hosted inference router.

​
Usage analytics

The console views for request count, token usage, latency, and cost across your inference traffic.

​
Container

A Docker-based environment that packages your code, dependencies, and runtime into a portable unit that runs consistently across machines.

​
Data center

Physical facilities where Brightnode’s GPU and CPU hardware is located. Your choice of data center can affect latency, available GPU types, and pricing.

​
Machine

The physical server hardware within a data center that hosts your workloads. Each machine contains CPUs, GPUs, memory, and storage.