Google Gemma (open weights)

Gemma is a model, not an API: serve it with Ollama, vLLM or llama.cpp locally, or pick it on a hosted provider (Groq, Together, Fireworks). Everything below the model line is unchanged.

LLM_CHAIN=ollama,anthropic   # failover to a second endpoint is one more name
LLM_OLLAMA_MODEL=gemma3:12b
# or on Groq: LLM_GROQ_MODEL=gemma2-9b-it  LLM_GROQ_API_KEY=…

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=ollama 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/gemma

---

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