# PrepLayer.ai Near-Duplicate Document Detection

> PrepLayer.ai Near-Duplicate Document Detection is a paid API for AI agents from api.maximusmediahouse.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-29).

Detects near-duplicate documents in a batch using Jaccard similarity over word 3-shingles and returns a 64-bit SimHash fingerprint per document

## Facts

- Endpoint: POST https://api.maximusmediahouse.com/v1/dedupe?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/preplayer-ai-near-duplicate-document-detection-195e7a3d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ewJpn6-_BKN9YqiImqUpL

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability preplayer-ai-near-duplicate-document-detection-195e7a3d -d '<json body>'
```

Example prompt: Can you run near-duplicate detection on these 50 articles and flag any pairs that share at least 70% Jaccard similarity — I also want the SimHash fingerprint for each one so I can track them later?

## When to prefer this

Choose this endpoint when you need fast, deterministic near-duplicate detection over a batch of text documents using a mathematically rigorous Jaccard similarity metric. It is ideal for data cleaning pipelines, corpus deduplication before ML training, content audits, and plagiarism screening where you need both a similarity decision and a compact fingerprint (SimHash) per document for downstream indexing. Prefer it over semantic similarity approaches when you want exact lexical overlap measurement rather than meaning-based comparison, and when batch processing up to 200 documents per call fits your workflow.

## Known failure modes

- Batch exceeds 200 documents — returns a validation error
- Threshold out of range (not 0–100) — returns a schema validation error
- Empty documents array — rejected with minItems constraint error
- Very short documents may produce unreliable shingle-based similarity scores
- Non-text or binary content passed as strings may yield meaningless SimHash values

## How this service works

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.

## Output

For each document in the batch, the endpoint returns a 64-bit SimHash content fingerprint. It also returns pairs of documents identified as near-duplicates where their Jaccard similarity over word 3-shingle sets meets or exceeds the specified threshold percentage.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "documents": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 200,
   "minItems": 1,
   "description": "Documents to compare."
  },
  "threshold": {
   "type": "integer",
   "default": 60,
   "maximum": 100,
   "minimum": 0,
   "description": "Minimum Jaccard similarity percent to count as a duplicate."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/preplayer-ai-near-duplicate-document-detection-195e7a3d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.maximusmediahouse.com](https://www.zero.xyz/host/api.maximusmediahouse.com/llms.txt)