{"uid":"cap_QTyBRFBq9SJ77KOBEyxgu","slug":"toll402-web-page-reader-c16542cf","name":"Toll402 Web Page Reader","description":"Fetch any public web page (or PDF) and return clean, LLM-ready Markdown with title, metadata and links. Boilerplate, ads and scripts removed.","url":"https://toll402.dev/v1/read","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","description":"Public http(s) URL to read"},"format":{"enum":["markdown","text","both"],"type":"string","default":"markdown","description":"Which body format(s) to return"},"maxChars":{"type":"integer","default":200000,"maximum":500000,"minimum":500,"description":"Truncate body to this many characters"},"includeLinks":{"type":"boolean","default":true},"includeImages":{"type":"boolean","default":false}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"ms":{"type":"integer"},"ok":{"type":"boolean"},"tool":{"type":"string"},"result":{"type":"object","properties":{"url":{"type":"string"},"links":{"type":"array","items":{"type":"object","properties":{"href":{"type":"string"},"text":{"type":"string"}}}},"title":{"type":"string"},"markdown":{"type":"string"},"wordCount":{"type":"integer"}}}}}}}}},"responseSchema":{"type":"json","example":{"url":"https://en.wikipedia.org/wiki/HTTP_402","links":[{"href":"https://x402.org","text":"x402"}],"title":"HTTP 402","markdown":"# HTTP 402\n\n...","wordCount":812}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Db-990lnn2I4HCzTyKukp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches any public web page or PDF URL and returns clean, LLM-ready Markdown with title, metadata, and links — boilerplate, ads, and scripts stripped out.","exampleAgentPrompt":"Fetch the content of https://example.com/article and give me the clean markdown version with all the links included.","exampleUseCases":[{"title":"Summarize a news article","prompt":"Grab the content from https://techcrunch.com/2024/05/01/openai-news/ and return the clean readable text so I can summarize it."},{"title":"Research from a documentation page","prompt":"Read https://docs.python.org/3/library/asyncio.html and give me the full markdown content with links so I can understand the asyncio API."},{"title":"Extract readable content from PDF","prompt":"Fetch the PDF at https://arxiv.org/pdf/2310.06825 and return the clean text and title so I can analyze the paper."}],"resultDescription":"Returns a JSON object containing: the final resolved URL, page title, full body in Markdown (and/or plain text), an array of extracted hyperlinks (each with href and anchor text), word count, and the time taken in milliseconds. Boilerplate, navigation, ads, and scripts are removed.","failureModes":["URL is not publicly accessible or requires authentication — returns an error or empty content","Page is JavaScript-rendered only and content cannot be extracted server-side","PDF is encrypted or corrupted and cannot be parsed","URL times out or returns a non-200 HTTP status","maxChars truncation cuts off content mid-sentence if the page is very large","malformed or invalid URL returns a validation error"],"whenToPreferThis":"Choose this endpoint when you need to ingest a specific public web page or PDF URL into an LLM pipeline as clean, structured Markdown — especially when you want boilerplate and ads stripped automatically. Prefer it over raw HTTP fetches when you need title, links, and word count alongside the body. If you need to extract structured JSON matching a custom schema, use the Toll402 structured extraction sibling instead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T19:03:41.998Z","isFirstParty":false}