Google Gemini LLM
GoogleLLM plugs Google Gemini chat models into Patter’s pipeline mode via the Generative Language API. Streams normalise to Patter’s unified {type: "text" | "tool_call" | "done"} chunk protocol, and Gemini function_call parts map directly onto Patter tools.
This page covers Google Gemini in chat-completions mode for the pipeline (STT → LLM → TTS). For Gemini’s bidirectional speech-to-speech engine, see the separate
gemini-live adapter under Engines.Install
Usage
The namespaced import (
import * as google from "getpatter/llm/google" / from getpatter.llm import google) auto-resolves the API key from GEMINI_API_KEY first, then GOOGLE_API_KEY for parity with other SDKs, and exposes a uniform LLM class.Supported models
Pricing in USD per 1M tokens.| Model | Input | Output | Notes |
|---|---|---|---|
gemini-2.5-flash (default) | $0.30 | $2.50 | Best price/perf for voice. |
gemini-2.5-pro | $1.25 | $10.00 | Highest quality. |
gemini-2.0-flash | n/a | n/a | Older fast model. |
gemini-2.0-flash-lite | n/a | n/a | Lightweight 2.0. |
gemini-1.5-flash | n/a | n/a | Legacy fast model. |
gemini-1.5-pro | n/a | n/a | Legacy pro model. |
gemini-live-2.5-flash-native-audio (input 2.50), see the Engines page — it is a separate Realtime adapter, not a chat-completions model.
Environment variables
| Variable | Required | Notes |
|---|---|---|
GEMINI_API_KEY | one of these | Preferred — Google’s CLI tooling uses this name. |
GOOGLE_API_KEY | one of these | Legacy/alt name accepted for parity. |
Options
| Option | Default | Notes |
|---|---|---|
apiKey / api_key | undefined | Reads GEMINI_API_KEY, then GOOGLE_API_KEY. |
model | "gemini-2.5-flash" | Any Gemini chat model id. |
baseUrl / base_url | unset | Override the Generative Language API endpoint (rarely needed). |
temperature | unset | Optional sampling temperature. |
maxOutputTokens / max_output_tokens | unset | Output token cap. |
Vertex AI is currently only exposed in the Python SDK (
vertexai=True, project=..., location=...). The TypeScript adapter targets the Developer API; Vertex AI parity is on the roadmap.Function calling
Gemini’sfunction_call parts map directly onto Patter tools — define a tool once and it works on every LLM provider. Patter assigns a monotonically increasing index per function_call part since Gemini does not provide a stable per-call index across stream chunks. Token usage is collected from usage_metadata (cumulative on each chunk; only the last value is yielded as a usage event to avoid double-counting).
