Tools
Vision Tool
Tool that analyzes images using AI to extract useful information and answer questions about images.
Category: Tools · Plans: Trial, Pro, Premium, Enterprise · Type: VisionTool
Inputs#
| Field | Type | Required | Default | What it does |
|---|---|---|---|---|
| Prompt | Text | Yes | {input} | The prompt describing what information to extract from the image. |
| Image URL | Text | No | (empty) | URL of the image to analyze (optional if using attachments). |
| Attachment ID | Text | No | (empty) | Optional file ID to scope vision analysis to a specific attachment. |
| Model | Choice | No | gpt-4.1 | The AI model to use for vision analysis. Options: default, flowhunt-recommended, flowhunt-cheapest, flowhunt-smartest, gpt-4o-mini, gpt-4.1, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5.2, gpt-5.4, gpt-5.4-mini and 59 more |
Outputs#
| Output | Type |
|---|---|
| Prompt | Any |
| Image Url | Any |
| Model Name | Any |
| Analysis | Any |
Use as an agent tool#
Tool name: visiontool
Analyze IMAGE attachments (PNG, JPG, JPEG, GIF, WEBP) or an image URL using AI vision: read text in the image, describe its content, and answer questions about it. Whenever the user uploads or references an image, use this tool — prefer it over FileAttachmentRetriever, which cannot read images.