{"uid":"cap_Zu4lUqRNMYjyPTnSTTOAV","slug":"x402-deployer-x402-deployer-workers-dev-e2c60509","name":"SimHash Content Fingerprinting & Near-Duplicate Detection","description":"SimHash / 64-bit content fingerprint / near-duplicate detection / dedup hashing / locality-sensitive hash. Pure-local 64-bit SimHash over token-level k-shingles (default k=3) using FNV-1a. Two SimHashes are 'close' (small Hamming distance) iff the underlying texts share many shingles. Returns hex + decimal forms plus token + shingle counts. Useful for content dedup pipelines, plagiarism detection, and bot-content clustering.","url":"https://x402-deployer.x402-deployer.workers.dev/content-simhash","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":{"required":["text"],"properties":{"text":{"type":"string","description":"Text to hash. Up to 500,000 chars."},"shingle_size":{"type":"number","description":"k-gram size for shingles. Range [1, 8]. Default 3."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"source":{"type":"string"},"hash_hex":{"type":"string"},"hash_int":{"type":"string"},"bit_count":{"type":"integer"},"text_chars":{"type":"integer"},"token_count":{"type":"integer"},"shingle_size":{"type":"integer"},"shingle_count":{"type":"integer"}}}}}}},"responseSchema":null,"example":{"request":{"k":3,"text":"Artificial intelligence is transforming the way we work, live, and communicate with each other every day."},"response":{"source":"DIY SimHash (FNV-1a 64)","hash_hex":"0x5b37c9ff1edccc9d","hash_int":"6572944278742158493","bit_count":64,"text_chars":105,"token_count":16,"shingle_size":3,"shingle_count":14}},"exampleRequest":{"k":3,"text":"Artificial intelligence is transforming the way we work, live, and communicate with each other every day."},"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_oL1MhwfERa2Dn4xqNh8mq","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Computes a 64-bit SimHash fingerprint over token-level k-shingles (default k=3) for near-duplicate content detection, returning hex and decimal forms plus token and shingle counts.","exampleAgentPrompt":"Compute a SimHash fingerprint for this article text using k=3 shingles so I can check it against other documents for near-duplicates: 'Artificial intelligence is transforming the way we work, live, and communicate with each other every day.'","exampleUseCases":null,"resultDescription":"Returns a 64-bit SimHash of the input text in both hex and decimal forms, along with the number of tokens and shingles processed. Two results with a small Hamming distance indicate the underlying texts share many shingles and are likely near-duplicates.","failureModes":["Empty or missing text body — returns error indicating no content to hash","Extremely short text with fewer tokens than k — may produce degenerate shingle set","Invalid k value (non-integer or negative) — returns validation error","Request timeout for very large documents","Payment not included or insufficient — x402 payment required error"],"whenToPreferThis":"Use this endpoint when you need a fast, purely local (no external model calls) 64-bit fuzzy fingerprint for text similarity or deduplication. Prefer it over exact hash functions (MD5/SHA) when you want near-duplicate detection that tolerates minor edits, and over embedding-based similarity when you want a lightweight, deterministic, reproducible signal without LLM costs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:47:44.892Z","isFirstParty":false}