MERLIN
AI Inference Engine
Merlin routes AI requests to Vultr Serverless Inference and local Ollama models. Use the API endpoints below to interact with AI models.
API Endpoints
POST /v1/merlin/chat — Chat completion
POST /v1/merlin/generate — Text generation
GET /v1/merlin/models — List available models
GET /v1/merlin/health — Health check
Return to Portal
✔ Merlin Proxy Active — Vultr AI + Ollama Connected