prompt | string | Yes | - | Instructions for analyzing the images. This is a multi-line text area where you can: - Describe what to look for in the images - Ask specific questions about visual content - Request analysis of charts, graphs, or documents - Use line breaks to structure complex analysis requests Example: “Analyze these product images and identify: 1. Product features and quality 2. Any defects or issues 3. Compliance with brand guidelines” |
model | string or SelectableOption | Yes | - | The AI model to use for image analysis. Some available options: ‘gpt-4.1’ (DEFAULT) - Balanced performance ‘gpt-4.1-mini’ - Cost-effective |
images | array of string | Yes | - | List of image URLs to analyze (maximum 5 images). You can reference images from upstream nodes using {{nodeId__data}} syntax. Supported formats: JPEG, PNG, GIF, WebP Images can be from URLs, file uploads through the UI, or outputs from other workflow nodes. Example: [“https://example.com/image1.jpg”, “{{imageNodeId__data.url}}“] |
