{"uid":"cap_ylavYqsdULGCJ9f5mdl3r","slug":"sitecheck-entity-extraction-5b4d6547","name":"SiteCheck Entity Extraction","description":"Named entities in a text or a page: people, organisations, places, dates and money amounts (from the chat model), plus e-mail addresses, URLs and phone numbers (from patterns), each de-duplicated with a count. With url, the page's readable text is used (robots.txt is respected).","url":"https://api.sitecheck-api.workers.dev/api/entities?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"Or a page address, https://…"},"text":{"type":"string","description":"Text, up to 12,000 characters"}}},"responseSchema":{"type":"json","example":{"url":null,"urls":[],"dates":[{"name":"1843","count":1}],"model":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","money":[],"emails":[{"count":1,"value":"ada@example.org"}],"people":[{"name":"Ada Lovelace","count":1},{"name":"Charles Babbage","count":1}],"phones":[{"count":1,"value":"+442079460958"}],"places":[{"name":"London","count":1}],"source":"chat model (Workers AI, Groq fallback) for names; regex and libphonenumber for e-mails, URLs and phones","checkedAt":"2026-10-14T07:05:00.000Z","organisations":[]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_eCbMrRfSLh6uMNybkEIoL","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts named entities (people, places, organisations, emails, phones, dates, money, URLs) from a URL or raw text using an LLM plus regex/libphonenumber","exampleAgentPrompt":"Can you extract all the people, organisations, email addresses, phone numbers, and places mentioned on https://example.com/about-us and give me a structured list?","exampleUseCases":[{"title":"Contact details from a company page","prompt":"Pull all email addresses, phone numbers, and people's names from https://acme-corp.com/contact and list them for me."},{"title":"People and orgs in a press release","prompt":"Here's a press release text — can you identify every person, organisation, and location mentioned in it? 'Acme Corp CEO Jane Smith announced a partnership with Global Industries in London today...' (up to the full text)"},{"title":"Entity extraction from a research article","prompt":"Extract all named people, places, dates, and money amounts from this article text: 'In 1843, Ada Lovelace collaborated with Charles Babbage in London on a project funded with £200...'"}],"resultDescription":"A JSON object with arrays for people, places, organisations, emails, phones, dates, money, and URLs — each entry includes the entity value and a count of occurrences. Also includes the model used, data source description, and a checkedAt timestamp.","failureModes":["Text exceeds 12,000 character limit — request rejected or truncated","URL is inaccessible or returns non-HTML content — may return empty entity arrays","LLM hallucination of entity names not present in source text","Regex misses non-standard phone/email formats","Payment not received — HTTP 402 returned before processing","Groq fallback unavailable — increased latency or failure"],"whenToPreferThis":"Choose this endpoint when you need structured named-entity extraction from either a live URL or raw text in a single pay-per-call step, without managing your own NLP pipeline. It combines LLM-based name extraction with regex/libphonenumber for contacts, making it stronger than pure-regex approaches for mixed content. Prefer it over general LLM chat when you want a guaranteed structured JSON response with deduplicated, counted entities rather than free-text output.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T06:43:49.249Z","isFirstParty":false,"canonicalSlug":"sitecheck-entity-extraction-5b4d6547"}