Pick the right LLM provider

OpenMind talks to four LLM providers via a thin adapter layer. Pick one in Settings → LLM provider (saved in your browser, not per project); switch any time without losing the existing graph (the data shape is provider-agnostic). Ollama and LM Studio need a self-hosted instance.

• Cloud · default

  Anthropic Claude Sonnet 5

  The default. Picked for extraction quality on conversational German + English. Fastest path to a working extraction loop; no setup, just an API key.

• Cloud · alternative

  OpenAI GPT-4o mini

  Solid alternative when you already have OpenAI credit or your team is standardised on the OpenAI API. Slightly different extraction style — switch and compare on one project to see which fits your domain.

• Local · privacy-first

  Ollama

  On your own machine, without a cloud model. Smaller models (Llama 3.2, Phi-4-mini, Qwen 2.5) trade extraction quality for zero data leaving the box. Best for sensitive projects and self-host operators.

• Local · power-user

  LM Studio

  If you prefer LM Studio's GUI for managing local models and quantisations. Same endpoint shape as Ollama; the adapter just calls the OpenAI-compatible server LM Studio exposes on :1234.