{"uid":"cap_3XwchAHAbgGiQyRf4OG2-","slug":"tavily-extract-clean-page-content-from-urls-77fd5229","name":"Tavily Extract – Clean Page Content from URLs","description":"Tavily — extract clean page content (JS handled) from up to 5 URLs you already have, in one 1¢ call. Pass `urls` (array, ≤5); optional `format` (markdown default | text). For bigger batches make multiple calls. Alternative to exa/contents (0.1¢/url, no JS) and firecrawl/scrape (1¢/url, full rendering).","url":"https://vaaya.ai/api/run/tavily/extract","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["urls"],"properties":{"urls":{"type":"array","items":{"type":"string","format":"uri"},"maxItems":5,"minItems":1},"format":{"enum":["markdown","text"],"type":"string"}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"pathParams":{"type":"object"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_5R9H23eeqiTQEZgxxm1zn","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts clean, JavaScript-rendered page content from up to 5 URLs in a single call, returning markdown or plain text.","exampleAgentPrompt":"Can you fetch the clean readable content from these three URLs — https://example.com/article1, https://example.com/article2, and https://example.com/article3 — and return it as markdown?","exampleUseCases":[{"title":"Summarize competitor blog posts","prompt":"Pull the full text from these four competitor blog posts and give me a summary of each: https://competitor1.com/post-a, https://competitor2.com/post-b, https://competitor3.com/post-c, https://competitor4.com/post-d — return as markdown please."},{"title":"Extract article body for RAG pipeline","prompt":"Grab the readable text content from https://techcrunch.com/2024/05/ai-funding-roundup and https://venturebeat.com/2024/05/llm-update so I can index them into my knowledge base."},{"title":"Fact-check claims against source pages","prompt":"I have these two source URLs that were cited in a report — https://who.int/news/item/123 and https://cdc.gov/report/456 — can you extract the full page content from both so I can verify the claims?"}],"resultDescription":"Returns the extracted clean content for each submitted URL, with JavaScript fully rendered. Each URL's content is provided in the requested format (markdown by default, or plain text), suitable for reading, indexing, or summarization. Up to 5 URLs are processed per call.","failureModes":["URL is unreachable or returns a 4xx/5xx error — that URL's content may be null or omitted","More than 5 URLs submitted — caller must split into multiple requests","JavaScript-heavy SPA with anti-bot protection may return incomplete or empty content","Paywalled or login-gated pages return only publicly visible content","Malformed URL in the array may cause partial or full call failure"],"whenToPreferThis":"Choose this endpoint when you already have specific URLs and need JS-rendered page content — it handles dynamic sites that static fetchers can't parse. At $0.01 per call for up to 5 URLs (0.2¢/URL), it's cheaper than Firecrawl (1¢/URL) and more capable than Exa contents (no JS). Prefer it when you need rendered content from JavaScript-heavy pages. Use Exa/contents for large static batches where JS is not needed, or Firecrawl when you need full rendering with screenshots or structured extraction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:47:06.199Z","isFirstParty":false}