analyzeImage

Analyze an image using a vision model based on a text prompt.

mindstudio.analyzeImage({ prompt }) → Result

Runs a vision model over an image against a text prompt and returns its reading as text — describe, classify, extract fields, or answer a question about what is shown. Use a model override when you need a specific vision model.

Parameters

prompt

string

RequiredInstructions describing what to look for or extract from the image

imageUrl

string

URL of a single image to analyze. Kept for backward compatibility; prefer imageUrls.

imageUrls

string[]

One or more image URLs to analyze together in a single model request

visionModelOverride

object

Optional model configuration override. Uses the workflow's default vision model if not specified

Call from a method

import { mindstudio } from '@mindstudio-ai/agent';

const result = await mindstudio.analyzeImage({
  prompt: /* ... */
});