web

AgentSearch Web Extract

Fetch a URL and get it back ready for an LLM or RAG pipeline: clean markdown (headings and links kept), plain text, the title, the page's links and fetch metadata. POST /v1/extract with {url} and optional formats and max_chars. JSON in, JSON out, errors included. Pay per request in USDC; no account, no API key.

post/v1/agentsearch-web-extract-v1

Request

  • Base URL: https://agent.pocket.network
  • URL: https://agent.pocket.network/v1/agentsearch-web-extract-v1
  • Auth: none required

Request body

urlstring required

The page to fetch (http or https).

formatsstring[]

Which renderings to return. Defaults to the service's own choice.

max_charsinteger

Cap on returned characters (default 50000).

Response

The upstream response, served after payment settles.

object required

For POST /v1/extract, a JSON object with request_id, url, title, markdown, text, links (href and text), meta (status_code, content_type, fetched_at, chars, truncated) and error (null on success). A bad request answers 400 with { error: { code, message, request_id } }.

Changes

No recorded changes to this operation across all 1 revision of this API.