API Overview

AINode exposes an OpenAI-compatible API on port 8000 and a management API on port 3000.

Base URLs

Purpose	URL
Inference (OpenAI-compatible)	http://localhost:8000/v1
Management API	http://localhost:3000/api
Prometheus metrics	http://localhost:8000/metrics

Authentication

Disabled by default. Enable for internet-exposed instances:

ainode auth enable    # generates an API key
ainode auth new-key   # rotate

Pass the key as Authorization: Bearer <key> on all /v1/* requests.

OpenAI-compatible endpoints

Endpoint	Method	Description
/v1/chat/completions	POST	Chat completions (streaming supported)
/v1/completions	POST	Text completions
/v1/embeddings	POST	Embeddings
/v1/models	GET	List loaded models

Management endpoints

Endpoint	Description
GET /api/status	Node status, GPU info, engine state
GET /api/nodes	All discovered cluster nodes
GET /api/cluster/resources	Aggregated VRAM across cluster
GET /api/metrics	JSON metrics snapshot
GET /metrics	Prometheus text exposition
POST /api/engine/set-model	Switch active model
POST /api/engine/update	Trigger docker pull + restart
GET /api/version/check	Check for newer version on GHCR