image_understanding
Analyze images using Grok AI vision capabilities to extract information, answer questions, and understand visual content based on text prompts.
Instructions
Analyze images using Grok AI vision capabilities (Note: Grok 3 may support image creation)
Input Schema
Name | Required | Description | Default |
---|---|---|---|
base64_image | No | Base64-encoded image data (without the data:image prefix) | |
image_url | No | URL of the image to analyze | |
model | No | Grok vision model to use (e.g., grok-2-vision-latest, potentially grok-3 variants) | grok-2-vision-latest |
prompt | Yes | Text prompt to accompany the image |
Input Schema (JSON Schema)
{
"properties": {
"base64_image": {
"description": "Base64-encoded image data (without the data:image prefix)",
"type": "string"
},
"image_url": {
"description": "URL of the image to analyze",
"type": "string"
},
"model": {
"default": "grok-2-vision-latest",
"description": "Grok vision model to use (e.g., grok-2-vision-latest, potentially grok-3 variants)",
"type": "string"
},
"prompt": {
"description": "Text prompt to accompany the image",
"type": "string"
}
},
"required": [
"prompt"
],
"type": "object"
}