Short answer: Drop the "Groq → Groq Analyze Image" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Model model | options | Optional | Model. Options: Llama 3.2 90B Vision, Llama 3.2 11B Vision |
Image URL image_url | string | Required | Image URL (required) |
Prompt prompt | string | Required | Describe what's in this image |
Max Tokens max_tokens | string | Optional | Max Tokens |
{"model": "{{trigger.model}}","image_url": "e.g. https://example.com/path","prompt": "Describe what's in this image","max_tokens": "{{trigger.max_tokens}}"}
{"id": "chatcmpl_abc","usage": {"total_tokens": 110,"prompt_tokens": 100,"completion_tokens": 10},"choices": [{"message": {"content": "A cat on a windowsill"},"finish_reason": "stop"}]}
Use these fields in downstream nodes for routing, logging, or error handling.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.