{"slug":"api-maximusmediahouse-com-v1-dedupe-1b38a8","title":"Near-duplicate detection across a batch of documents","host":"api.maximusmediahouse.com","method":"POST","resource":"https://api.maximusmediahouse.com/v1/dedupe","category":"other","description":"Near-duplicate detection across a batch of documents. Exact Jaccard similarity over word-3-shingle sets decides duplication; a 64-bit SimHash is returned per document as a compact content fingerprint. Up to 200 documents per call.","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":345,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"documents":["the quick brown fox jumps over the lazy dog","the quick brown fox jumped over a lazy dog"],"threshold":60},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"documents":{"description":"Documents to compare.","items":{"type":"string"},"maxItems":200,"minItems":1,"type":"array"},"threshold":{"default":60,"description":"Minimum Jaccard similarity percent to count as a duplicate.","maximum":100,"minimum":0,"type":"integer"}},"required":["documents"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":345,"error":null}],"description_full":"Near-duplicate detection across a batch of documents. Exact Jaccard similarity over word-3-shingle sets decides duplication; a 64-bit SimHash is returned per document as a compact content fingerprint. Up to 200 documents per call.","last_updated":"2026-10-24T00:06:12.757Z","schemes":["exact"]}