Brightnode gives you dedicated compute, hosted inference, and shared storage for AI workloads. Use Bnodes when you want full control over the machine, and use the hosted inference stack when you want a single OpenAI-compatible endpoint for model access.Documentation Index
Fetch the complete documentation index at: https://docs.brightnode.cloud/llms.txt
Use this file to discover all available pages before exploring further.
Get started
If you’re new to Brightnode, start here for the core product concepts and account setup flow.Quickstart
Create an account, deploy your first Bnode, and connect to it.
Product overview
Compare Router, Models, Beams, Bnodes, and storage.
Concepts
Learn the key platform terms used throughout the docs and console.
API keys
Create scoped API keys for inference and deployment workflows.
Inference
Brightnode’s hosted inference experience is built around a shared router, a model catalog, scoped API keys, and usage analytics.Router
Use one OpenAI-compatible endpoint across the Brightnode model catalog.
Models
Browse available model IDs, metadata, pricing, and quickstarts.
Usage
Track requests, tokens, latency, and cost in the console.
Beams preview
Learn how preview model deployments fit into the inference stack.
Compute and storage
Use Bnodes when you need full environment control, persistent sessions, and custom containers. Use network volumes when you want portable storage that survives machine lifecycles.Bnodes
Launch dedicated GPU or CPU machines for training, experimentation, and long-running services.
Network volumes
Keep data persistent across Bnodes and shared workflows.
S3-compatible API
Upload and manage network volume data without starting a machine.
Utility services
Use built-in tools such as JupyterLab, VS Code Server, and vLLM.
Support
Contact
Submit a support request using our contact page.
Email help@brightnode.cloud for direct support.
Status page
Check the status of Brightnode services and infrastructure.
Discord
Join the Brightnode community on Discord.