Documentation

OpenAI-compatible LLM inference, routed across a fleet of community and self-hosted GPU nodes. Point any OpenAI SDK at one base URL, pick a model, and requests route to a node that can serve it — loading the model on demand if needed. EU-sovereign by design.

Every page here is also available as raw Markdown (append .md to any URL) and indexed for machines in llms.txt · llms-full.txt.

Get started

Using the API

Run a node