> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vellum.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vellum.ai/_mcp/server.

# Summarize Images of Websites

> Learn how to process and analyze website screenshots using multi-modal LLMs to extract meaningful insights and generate concise summaries of visual web content.

Concepts: Image Analysis, Website Content Extraction, Visual Summarization, Multi-Modal AI

This example demonstrates how to use multi-modal LLMs to analyze and summarize website screenshots. Learn how to extract meaningful information from visual web content, process complex layouts, and generate concise, accurate summaries of what appears in website images, enabling automated visual content analysis at scale.

We use [Firecrawl](https://firecrawl.dev/) to scrape websites and capture screenshots, providing the visual input for analysis.