Gemini 2.0 Flash Lite

Gemini | 2.0 | Flash Lite

Use Google's Gemini 2.0 Flash Lite for multimodal analysis. Process text prompts with optional image inputs for vision-language tasks.

Quick Start

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gemini-2-0-flash-lite",
    "version": "0.0.1",
    "input": {
      "prompt": "Describe what you see in this image in detail",
      "image_urls": ["https://example.com/photo.jpg"]
    }
  }'

Parameters

Output

• Type: text

Examples

Image Description

{
  "model": "gemini-2-0-flash-lite",
  "version": "0.0.1",
  "input": {
    "prompt": "What objects are in this image and what is happening?",
    "image_urls": ["https://example.com/scene.jpg"]
  }
}

Text-Only Query

{
  "model": "gemini-2-0-flash-lite",
  "version": "0.0.1",
  "input": {
    "prompt": "Write a short creative story about a robot learning to paint"
  }
}

Multi-Image Comparison

{
  "model": "gemini-2-0-flash-lite",
  "version": "0.0.1",
  "input": {
    "prompt": "Compare these two images and describe the differences",
    "image_urls": ["https://example.com/image-a.jpg", "https://example.com/image-b.jpg"]
  }
}

Related Models

• Video Analyzer - Analyze video content
• Imagen 4 Preview - Generate images from text

Documentation

• EachLabs API Docs