Available models
/v1/modelsDiscover models served at the direct inference endpoint.
Private infrastructure · Public API endpoint
BookFreq serves an authenticated, OpenAI-compatible API backed by vLLM on Kubernetes. The inference, networking, and infrastructure are built and operated in my homelab — not rented from an AI API provider.
The API
The direct inference endpoint uses HTTP Basic authentication. These standard API routes support model discovery, chat completions, and text completions; documentation and service health are available separately.
/v1/modelsDiscover models served at the direct inference endpoint.
/v1/chat/completionsSend messages using the familiar OpenAI chat schema.
/v1/completionsGenerate text through the completions API.
Behind the endpoint
I built it to learn AI infrastructure by actually operating it: a seven-node K3s cluster, two GPU inference tiers, retrieval-augmented generation, GitOps, observability, and a daily human-reviewed vulnerability workflow. The project page has the architecture, design choices, and recorded demonstrations.