Markdown for LLMs

When feeding web pages into an LLM, raw HTML wastes tokens and confuses the model. Set format: markdown and the Web Access API distills the page to clean, readable Markdown — boilerplate removed, structure and data preserved.

curl https://request.usestring.ai/v1/fetch \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "url": "https://example.com/article", "format": "markdown" }'

What you get

• Navigation, ads, and boilerplate stripped (content-dense pages keep their body).
• Headings, lists, links, tables, code blocks, and inline formatting preserved.
• Relative URLs rewritten against the page origin.
• Embedded structured data preserved as fenced JSON code blocks.

If you need specific fields rather than the whole page, use structured extraction instead.