What can you do with it?

Use Gemini for tasks involving text, images, audio, and video. Perfect for complex reasoning, multimodal analysis, content generation, and real-time interactions. The command provides access to Google’s advanced AI models with support for multiple file types and formats.

How to use it?

Basic Command Structure

/gemini [prompt] [optional-parameters]

Parameters

Required:
  • prompt - Your instructions or questions for Gemini
Optional:
  • model - Specific Gemini model to use (defaults to gemini-2.0-flash)
  • system prompt - Override the default system prompt
  • files - File URLs to include (supports audio, images, videos, and text)

Response Format

The command returns:
{
  "response": "Gemini's generated response",
  "format": "response format (JSON/plaintext/markdown/HTML)",
  "metadata": {
    "model": "model used",
    "processing_time": "time taken"
  }
}

Examples

Basic Usage

/gemini
prompt: Explain the concept of machine learning
Gets a simple response from Gemini explaining machine learning concepts.

Advanced Usage

/gemini
prompt: Describe what's happening in this video and transcribe any dialogue
files: video_file.mp4
model: gemini-2.5-pro
Analyzes multimedia content using an advanced model for video understanding and transcription.

Specific Use Case

/gemini
prompt: Convert this text to natural speech: "Welcome to our presentation"
model: gemini-2.5-pro-tts
Generates text-to-speech audio using the specialized TTS model.

Notes

See LLM File Type Support for detailed information about file formats supported by Gemini and other models.

Supported Models

Choose the appropriate Gemini model based on your specific needs:
  • gemini-2.5-flash - Cost-efficient model for fast, general tasks (supports audio, images, videos, text → text)
  • gemini-2.5-pro - Enhanced thinking and reasoning, multimodal understanding, advanced coding (supports audio, images, videos, text → text)
  • gemini-2.0-flash (default) - Next generation features with speed, thinking, and realtime streaming for high-volume general tasks (supports audio, images, videos, text → text)
  • gemini-2.0-flash-exp - Cost-efficient experimental model for fast, general tasks (supports audio, images, videos, text → text)
  • gemini-2.0-flash-lite - Cost efficiency and low latency for cost-sensitive, basic tasks (supports audio, images, videos, text → text)
  • gemini-1.5-pro - Complex reasoning with long context for complex document analysis (supports audio, images, videos, text → text)
  • gemini-1.5-flash - Volume-optimized for lower-cost, high-frequency tasks (supports audio, images, videos, text → text)