Gemini

Google Gemini via its OpenAI-compatible endpoint, selected with LLM_PROVIDER=gemini, used to extract facts from conversations.

Enable it

LLM_PROVIDER=gemini
OPENAI_API_KEY=<gemini-api-key>
OPENAI_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai
OPENAI_LLM_MODEL=gemini-2.0-flash

Configuration

Variable	Default	Description
LLM_PROVIDER	openai	Set to gemini.
OPENAI_API_KEY	(none)	Google API key, sent as a bearer token.
OPENAI_BASE_URL	https://api.openai.com/v1	Point at Gemini's OpenAI endpoint: https://generativelanguage.googleapis.com/v1beta/openai.
OPENAI_LLM_MODEL	gpt-4.1-nano	A Gemini model, e.g. gemini-2.0-flash.

Notes

• OpenAI-compatible: the provider reuses the OpenAI request handling and only differs by base URL, key, and model.
• The provider also reads a key directly from GEMINI_API_KEY, then GOOGLE_API_KEY, when no key is supplied.
• You must override OPENAI_BASE_URL to Gemini's endpoint; its default points at OpenAI.