SimHash fingerprint API

Computes a SimHash fingerprint of a text and, if a second text is given, the Hamming distance / similarity for near-duplicate detection. Answers 'What is the SimHash of this text?', 'Are these two documents near-duplicates?'.

Price$0.02per request

MethodPOST

Route/v1/retrieval/simhash

StatusLive

MIME typeapplication/json

Rate limit120/minute

Cache0s public

simhashfingerprintnear-duplicatehammingdeduphashtextrag

API URLhttps://x402.hexl.dev/v1/retrieval/simhash

Integration docs

Example request

{
  "text": "the quick brown fox",
  "compareTo": "the quick brown foxes"
}

Example response

{
  "simhash": 3023737612,
  "hex": "b43a930c",
  "bits": 32,
  "compareTo": {
    "hammingDistance": 4,
    "similarity": 0.875,
    "isNearDuplicate": false
  }
}

Input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string"
    },
    "compareTo": {
      "type": "string"
    }
  }
}

Output schema

{
  "type": "object",
  "additionalProperties": true
}