analyze_image
Analyze images using Gemini AI vision models to answer questions, identify content, or extract information from images provided via URL or base64 data.
Instructions
Analyze images using Gemini vision capabilities
Input Schema
Name | Required | Description | Default |
---|---|---|---|
imageBase64 | No | Base64-encoded image data (alternative to URL) | |
imageUrl | No | URL of the image to analyze | |
model | No | Vision-capable Gemini model | gemini-2.5-flash |
prompt | Yes | Question or instruction about the image |
Input Schema (JSON Schema)
{
"properties": {
"imageBase64": {
"description": "Base64-encoded image data (alternative to URL)",
"type": "string"
},
"imageUrl": {
"description": "URL of the image to analyze",
"type": "string"
},
"model": {
"default": "gemini-2.5-flash",
"description": "Vision-capable Gemini model",
"enum": [
"gemini-2.5-pro",
"gemini-2.5-flash",
"gemini-2.0-flash"
],
"type": "string"
},
"prompt": {
"description": "Question or instruction about the image",
"type": "string"
}
},
"required": [
"prompt"
],
"type": "object"
}