Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openclaw.kr/llms.txt

Use this file to discover all available pages before exploring further.

​
Google (Gemini)

The Google plugin provides access to Gemini models through Google AI Studio, plus image generation, media understanding (image/audio/video), and web search via Gemini Grounding.
  • Provider: google
  • Auth: GEMINI_API_KEY or GOOGLE_API_KEY
  • API: Google Gemini API
  • Alternative provider: google-gemini-cli (OAuth)

​
Quick start

  1. Set the API key:
openclaw onboard --auth-choice google-api-key
  1. Set a default model:
{
  agents: {
    defaults: {
      model: { primary: "google/gemini-3.1-pro-preview" },
    },
  },
}

​
Non-interactive example

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice google-api-key \
  --gemini-api-key "$GEMINI_API_KEY"

​
OAuth (Gemini CLI)

An alternative provider google-gemini-cli uses PKCE OAuth instead of an API key. This is an unofficial integration; some users report account restrictions. Use at your own risk. Environment variables:
  • OPENCLAW_GEMINI_OAUTH_CLIENT_ID
  • OPENCLAW_GEMINI_OAUTH_CLIENT_SECRET
(Or the GEMINI_CLI_* variants.)

​
Capabilities

CapabilitySupported
Chat completionsYes
Image generationYes
Image understandingYes
Audio transcriptionYes
Video understandingYes
Web search (Grounding)Yes
Thinking/reasoningYes (Gemini 3.1+)

​
Environment note

If the Gateway runs as a daemon (launchd/systemd), make sure GEMINI_API_KEY is available to that process (for example, in ~/.openclaw/.env or via env.shellEnv).