AI Model Configuration

Configure Moltbot with Google Gemini

Use Google's Gemini models with Moltbot (formerly Clawdbot). Gemini offers excellent multimodal capabilities and competitive pricing.

✨ Why Choose Gemini?

✓Multimodal native — Excellent at understanding images, audio, and video
✓2M token context — Process extremely long documents and conversations
✓Competitive pricing — Often cheaper than other frontier models
✓Google integration — Native access to Search, Maps, and other Google services
✓Free tier available — Limited free usage for testing

Available Gemini Models

Gemini 2.0 Flash

Recommended

Latest model with multimodal capabilities. Fast and cost-effective.

gemini-2.0-flash

Input: $0.075/MTok

Output: $0.30/MTok

Gemini 1.5 Pro

Best for complex reasoning. 2M token context window.

gemini-1.5-pro

Input: $1.25/MTok

Output: $5.00/MTok

Gemini 1.5 Flash

Balanced speed and capability. Good for most tasks.

gemini-1.5-flash

Input: $0.075/MTok

Output: $0.30/MTok

* Prices per million tokens as of January 2026. Check Google AI's pricing page for current rates.

Setup Instructions

Get Your API Key

Get a free API key from Google AI Studio:

• Go to aistudio.google.com/apikey
• Sign in with your Google account
• Click "Create API Key"
• Copy the generated key

Configure Moltbot

Add Gemini configuration to your config file:

{
  "agent": {
    "provider": "google",
    "model": "gemini-2.0-flash",
    "apiKey": "AIzaSy..."
  }
}

Restart Moltbot

Apply the configuration:

moltbot restart

🆓 Free Tier Available

Google offers a generous free tier for Gemini API:

• 15 requests per minute for Gemini Flash
• 2 requests per minute for Gemini Pro
• No credit card required to start

Great for testing or light personal use!

Advanced Configuration

{
  "agent": {
    "provider": "google",
    "model": "gemini-2.0-flash",
    "apiKey": "AIzaSy...",
    "maxTokens": 8192,
    "temperature": 0.7,
    "safetySettings": {
      "harassment": "BLOCK_ONLY_HIGH",
      "hateSpeech": "BLOCK_ONLY_HIGH"
    }
  }
}

maxTokens — Maximum response length (up to 8192)
temperature — Creativity level 0-2 (default: 0.7)
safetySettings — Configure content filtering levels

Gemini vs Claude: Quick Comparison

Aspect	Gemini	Claude
Best for	Multimodal, images, long context	Instructions, coding, analysis
Context	2M tokens	200K tokens
Price	Lower	Higher
Free tier	Yes	No

Gemini Configured!

Now connect your messaging channels and start chatting.

Connect Telegram Try Claude Instead