Available Models

Model Context Images Tools Price (1M tokens)
Gemini 2.0 Flash
Fast experimental model with multimodal capabilities
1000K ✓ ✓ $0.075 / $0.3
Gemini Pro 1.5
High-capability model for complex tasks
1000K ✓ ✓ $1.25 / $5

Authentication

API KEY

Google AI API key

Environment Variable: GOOGLE_API_KEY

Setup Steps:

  1. Go to ai.google.dev
  2. Create or select a project
  3. Enable the Gemini API
  4. Generate an API key
  5. Set GOOGLE_API_KEY environment variable

OAUTH

OAuth via Antigravity or Gemini CLI

Setup Steps:

  1. Install Gemini CLI plugin
  2. Run authentication flow
  3. Tokens managed automatically

Configuration Example

{
  "models": {
    "providers": {
      "google-gemini": {
        "apiKey": "${GOOGLE_API_KEY}",
        "baseUrl": "https://generativelanguage.googleapis.com"
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "google-gemini/gemini-2.0-flash-exp"
      }
    }
  }
}

Use Google Gemini with Messaging Channels

Connect Google Gemini to your favorite messaging platforms:

Frequently Asked Questions

How much does Google Gemini cost with OpenClaw?
Google Gemini pricing depends on your usage. Google Gemini charges based on tokens processed. OpenClaw itself is free and open source. You only pay for the AI provider API costs.
How do I authenticate Google Gemini with OpenClaw?
Google Gemini supports api_key, oauth. The most common method is using an API key which you can get from the Google Gemini console.
Which Google Gemini models work with OpenClaw?
OpenClaw supports all Google Gemini models including Gemini 2.0 Flash, Gemini Pro 1.5. You can configure your preferred model in openclaw.json or use model aliases for convenience.
Can I use Google Gemini as a fallback provider?
Yes, OpenClaw supports automatic failover. You can configure Google Gemini as a fallback in the model configuration. If your primary provider fails, OpenClaw will automatically switch to Google Gemini.