{"uid":"cap_9p4tnw07wdAUE5yIwxSxz","slug":"walletforge-text-normalize-extract-89c08ec7","name":"WalletForge Text Normalize & Extract","description":"Normalize text and extract emails, URLs, phones","url":"https://api.walletforge.app/v1/normalize","method":"POST","headers":{},"bodySchema":null,"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_QKU9AAaDgQGYD7xBQ4DBF","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":"Normalizes raw text and extracts structured entities including email addresses, URLs, and phone numbers","exampleAgentPrompt":"Can you normalize this text and pull out all the email addresses, phone numbers, and URLs from it: 'Contact John at john.doe@example.com or call +1 (555) 867-5309, or visit http://example.com for more info.'","exampleUseCases":[{"title":"Extracting contacts from scraped content","prompt":"I just scraped a company's about page and the text is messy — can you clean it up and extract every email address and phone number you find in it?"},{"title":"Parsing emails from user submissions","prompt":"I have a block of raw user-submitted text from a support form and I need all the email addresses, phone numbers, and links pulled out as structured data so I can follow up."},{"title":"Normalizing CRM import data","prompt":"I've got a bunch of unstructured notes copied from old CRM entries — can you normalize the text and give me a clean list of any emails, phone numbers, and URLs embedded in them?"}],"resultDescription":"Returns normalized/cleaned version of the input text along with structured arrays of extracted entities: email addresses, URLs, and phone numbers found within the text.","failureModes":["Empty or missing input text returns an error","Malformed request body results in 400 response","Payment failure (insufficient USDC balance) blocks the call via x402","No entities found returns empty arrays rather than an error","Very long input text may exceed payload limits"],"whenToPreferThis":"Choose this endpoint when you need to both normalize raw text and extract multiple contact entity types (emails, phones, URLs) in a single call. Ideal for processing scraped web content, user-submitted forms, or unstructured documents where contact details are embedded in noisy text. The x402 micropayment model ($0.01/call) makes it cost-effective for high-volume extraction pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T12:34:17.752Z","isFirstParty":false}