# SimHash Fingerprint & Near-Duplicate Detection

> SimHash Fingerprint & Near-Duplicate Detection is a paid API for AI agents from api.24klabs.ai, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-13).

Computes a 64-bit SimHash fingerprint for text content, or compares two texts returning Hamming distance and a 0–1 similarity score for near-duplicate detection.

## Facts

- Endpoint: POST https://api.24klabs.ai/api/simhash-dedup
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/simhash-fingerprint-near-duplicate-detection-2c202448
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wUAMg1WYCHY30RA8hgsBs

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 simhash-fingerprint-near-duplicate-detection-2c202448 -d '<json body>'
```

Example prompt: Compute a SimHash fingerprint for this article text, then compare it with yesterday's version and give me the Hamming distance and similarity score so I can tell if they're near-duplicates: [text A] vs [text B].

## When to prefer this

Choose this endpoint when you need fast, deterministic near-duplicate detection for text without requiring semantic understanding — ideal for deduplication of crawled web pages, news feeds, user-generated content, or document archives. Prefer it over cosine similarity or embedding-based approaches when speed and exact fingerprint reproducibility matter more than semantic nuance, and when you want a single cheap hash you can store and compare later.

## Known failure modes

- Empty or missing text input returns a 400 validation error
- Extremely short texts (1–2 words) may produce unreliable similarity scores
- Non-textual binary content causes parsing errors
- Rate limiting or payment failure results in 402/429 responses
- Very large text inputs may be truncated or rejected with a payload-size error

## How this service works

Compute a 64-bit SimHash fingerprint for content, or compare two texts and return the Hamming distance and a 0-1 similarity score for near-duplicate detection.

## Output

For a single text input: a 64-bit SimHash fingerprint (integer or hex string). For a two-text comparison: the Hamming distance (integer, 0–64) between the two fingerprints and a normalized 0–1 similarity score where values near 1 indicate near-duplicates.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "a": {
   "type": "string"
  },
  "b": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "distance": 3,
  "similarity": 0.95
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/simhash-fingerprint-near-duplicate-detection-2c202448/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.24klabs.ai](https://www.zero.xyz/host/api.24klabs.ai/llms.txt)