Skip to main content

Setup

  1. Get an API key from aistudio.google.com.
  2. Set the environment variable:
export GOOGLE_API_KEY="AI..."

Configuration

agents:
  root:
    model: google/gemini-2.5-flash

Available models

ModelBest for
gemini-3-proMost capable Gemini model
gemini-3-flashFast, efficient, good balance
gemini-2.5-flashFast inference, cost-effective
gemini-2.5-proStrong reasoning, large context

Thinking budget

Thinking budget configuration differs between Gemini 2.5 and Gemini 3 model families.
Gemini 2.5 uses token-based budgets (integers). Gemini 3 uses level-based budgets (strings). Use the correct format for your model version.
models:
  gemini-no-thinking:
    provider: google
    model: gemini-2.5-flash
    thinking_budget: 0     # disable thinking

  gemini-dynamic:
    provider: google
    model: gemini-2.5-flash
    thinking_budget: -1    # dynamic — model decides (default)

  gemini-fixed:
    provider: google
    model: gemini-2.5-flash
    thinking_budget: 8192  # fixed token budget

Build docs developers (and LLMs) love