Google Gemini (AI Studio)

Through Gemini's OpenAI-compatible endpoint (generativelanguage.googleapis.com/v1beta/openai). Tool calling and streaming work; logprobs are not offered, so Verdict's LLM link answers without a distribution (rules and a decision model first).

LLM_CHAIN=gemini,anthropic   # failover to a second endpoint is one more name
LLM_GEMINI_API_KEY=AIza…
LLM_GEMINI_MODEL=gemini-2.5-pro

Every endpoint takes the same knobs: LLM_<NAME>_TEMPERATURE (none omits it), LLM_<NAME>_BODY (JSON merged into every request), LLM_<NAME>_PRICE (input,cached,output per million, for the cost ledger), LLM_<NAME>_NOTES (a per-model notes file). Two models of one provider: LLM_FAST_PRESET=gemini under another name. Environment has the full list.

Check it: npm run gateway, then curl localhost:8787/api/health — the llm.chain entry shows the endpoint, whether its key is set, and its state.

Provider docs: https://ai.google.dev/gemini-api/docs/openai

---

Source: docs/providers/gemini.md — edit it there; the site mirrors the repository.