analyze_image
Analyze images using AI vision models to extract information from screenshots, photos, diagrams, and web content. Supports base64, file paths, and URL inputs with customizable prompts and output formats.
Instructions
Analyze images using OpenRouter's vision models. Supports various input formats including base64, file paths, and URLs.
Input Schema
Name | Required | Description | Default |
---|---|---|---|
data | Yes | The image data (base64 string, file path, or URL) | |
format | No | Output format (default: text) | |
maxTokens | No | Maximum tokens in response (default: 4000) | |
mimeType | No | MIME type of the image (required for base64 input) | |
prompt | No | Custom prompt for image analysis (optional) | |
temperature | No | Sampling temperature (default: 0.1) | |
type | Yes | The type of image input |
Input Schema (JSON Schema)
{
"properties": {
"data": {
"description": "The image data (base64 string, file path, or URL)",
"type": "string"
},
"format": {
"description": "Output format (default: text)",
"enum": [
"text",
"json"
],
"type": "string"
},
"maxTokens": {
"description": "Maximum tokens in response (default: 4000)",
"type": "number"
},
"mimeType": {
"description": "MIME type of the image (required for base64 input)",
"type": "string"
},
"prompt": {
"description": "Custom prompt for image analysis (optional)",
"type": "string"
},
"temperature": {
"description": "Sampling temperature (default: 0.1)",
"maximum": 2,
"minimum": 0,
"type": "number"
},
"type": {
"description": "The type of image input",
"enum": [
"base64",
"file",
"url"
],
"type": "string"
}
},
"required": [
"type",
"data"
],
"type": "object"
}