onlyMainContent | true | Keep the main content, without menus, headers, footers and ads. false keeps the whole page. |
onlyCleanContent | false | Needs a key. A model removes cookie banners, ads, share widgets, breadcrumbs, sign up and comment prompts and related article lists from the Markdown. It removes whole paragraphs and lists only, never rewrites, and keeps code blocks. Not with zeroDataRetention. |
includeTags | none | Keep only parts that match these CSS selectors, such as article or .price. onlyMainContent is then not applied. |
excludeTags | none | Remove parts that match these selectors, such as .comments. |
removeBase64Images | true | Drops data:image images. false keeps them in Markdown and HTML. |
imageUrls | false | An image in the Markdown is its alt text. true keeps . Ask for images to get every image URL. |
linkStyle | inline | inline keeps [text](url). numbered writes Pricing⟨3⟩ and lists each URL once at the end. none keeps the link text only, which makes link heavy pages 10 to 70% shorter. Ask for links to get the URLs. |
maxChars | none | Cut the Markdown at this many characters, 500 to 1,000,000. |
offset | 0 | Start this many characters into the page, PDF or file. Not with query. |
query | none | What you are looking for, such as refund window. A page longer than maxChars (8,000 by default) comes back as the matching passages in page order, each with its surrounding text and table header. A shorter page comes back whole. Not with offset. |