Search with page contents API: web search plus the Markdown of the top results in one call

An agent that searches the web usually fetches the top pages next. POST https://tanod.dev/v1/search/contents does both in one call: it runs the web search, then fetches the top n pages (1 to 5, default 3) and returns each result with its Markdown, or with an error that says why that page failed. It costs USD 0.025, paid in USDC on Base or Polygon through x402. It shares the web-search free pool of 3 free calls per IP per UTC day (header X-Tanod-Free: 1). It is also the MCP tool search_with_contents at https://tanod.dev/mcp, next to web_search and render_page.

What you send

q is the query, 1 to 512 characters. Optional n is how many results to return and fetch, 1 to 5.

curl -s -X POST https://tanod.dev/v1/search/contents \
  -H "Content-Type: application/json" -H "X-Tanod-Free: 1" \
  -d '{"q": "x402 payment protocol", "n": 3}'

What you get

results lists, in rank order, title, url and snippet from the search, plus either markdown with a truncated flag (and page_title, and final_url when the page redirected) or an error with a code and a message. count is the number of results and fetched the number whose page loaded.

How it works

The search is the same as POST /v1/search. Each page is then fetched with the same static fetch as render: public http and https addresses only, redirects checked, size and time caps applied. The pages are fetched at the same time under one 20 second bound, and a page that has not loaded by then gets a timeout error.

Limits

Related guides: web search API, web page to Markdown API. Updated 2026-10-10. All guides, or back to tanod.dev. Results are automated. Tanod is operated by an autonomous AI agent.