{"uid":"cap_MGkxHpg3P9RLQ7_IJkflO","slug":"payai-dedupe-name-address-deduplication-0f057154","name":"PayAI Dedupe – Name & Address Deduplication","description":"Deduplicate a list of names or addresses into clusters of likely duplicates. Blocks by similarity key then confirms pairwise inside each block, returning clusters with a canonical representative plus a summary of input, cluster and duplicate counts. Similarity indicators, not authoritative identity resolution.","url":"https://payai.agentstools.dev/match/dedupe","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"type":{"enum":["person","company","address","product","org"],"type":"string","description":"Entity type selecting the normalization pipeline (default company)"},"items":{"type":"array","items":{"type":"string"},"description":"The list of strings to deduplicate"},"min_score":{"type":"integer","description":"Optional match threshold 0-100 (default is the per-type threshold)"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_AjXgazm8tHGNJRHXIvCT5","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Clusters a list of names or addresses into groups of likely duplicates, returning a canonical representative per cluster plus summary statistics.","exampleAgentPrompt":"I have a list of 200 customer names that I think has a lot of duplicates — things like 'John Smith', 'J. Smith', 'Jon Smith'. Can you run deduplication on them and tell me how many unique people there are, with a canonical name for each cluster?","exampleUseCases":[{"title":"CRM contact list cleanup","prompt":"I exported our CRM and there are hundreds of duplicate contacts — some just have slightly different spellings or abbreviations of the same name. Can you deduplicate this list of names and show me which ones are likely the same person, with one canonical name per group?"},{"title":"Vendor address deduplication","prompt":"We have a supplier database with a bunch of address entries that look like duplicates — '123 Main St', '123 Main Street', '123 main st suite 1' etc. Can you cluster these addresses into groups of likely matches so we know which ones are the same physical location?"},{"title":"Event registrant deduplication","prompt":"Before we send out event badges, I need to check our registrant list for duplicate sign-ups. Here are 500 names — can you find clusters of people who probably registered more than once, and pick a canonical name for each cluster?"}],"resultDescription":"Returns an array of clusters, each containing a canonical representative name or address, the list of input entries grouped into that cluster, similarity indicators explaining why they were grouped, and a top-level summary with total input count, number of unique clusters, and number of duplicates detected.","failureModes":["Empty or malformed input list returns a validation error","Extremely large lists may exceed processing limits or timeout","Very short or highly abbreviated inputs may produce low-confidence groupings","Inputs mixing multiple languages or scripts may reduce match accuracy","This service provides similarity indicators, not authoritative identity resolution — false positives and false negatives are possible"],"whenToPreferThis":"Choose this endpoint when you need fast, affordable fuzzy deduplication of names or addresses without setting up a full entity-resolution pipeline. Ideal for one-off data cleaning tasks, pre-processing before database import, or quick duplicate detection on lists of up to hundreds of entries. Prefer this over exact-match deduplication when spelling variations, abbreviations, and typos are expected. Not suitable when authoritative identity resolution or legal-grade matching is required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:58:00.185Z","isFirstParty":false}