# Delx Similarity

> Delx Similarity is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-13).

Computes normalized Levenshtein string similarity between two input strings, returning a score between 0 and 1.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/similarity
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-similarity-4868077b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pb1I72Tgy4rcElqOmFJAV

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 delx-similarity-4868077b -d '<json body>'
```

Example prompt: How similar are the strings 'restaurant' and 'restaurent'? Give me a normalized Levenshtein similarity score.

## When to prefer this

Use this endpoint when you need a quick, normalized string similarity score based on character-level edit distance (Levenshtein) — ideal for fuzzy deduplication, spell-check validation, name matching, or any scenario where you need a single 0–1 similarity metric without setting up a local NLP library. Prefer it over semantic similarity endpoints when character-level closeness (typos, minor spelling variants) matters more than meaning.

## Known failure modes

- Missing or empty input strings returns a validation error
- Non-string inputs may cause a 400 bad request
- Payment failure or insufficient USDC balance causes a 402 Payment Required response
- Extremely long strings may time out or be rejected due to size limits

## How this service works

Normalized string similarity (Levenshtein) for $0.001 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

## Output

Returns a normalized floating-point similarity score between 0.0 (completely different) and 1.0 (identical) based on the Levenshtein edit distance between the two input strings, along with potentially the raw edit distance count.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input",
  "output"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "additionalProperties": true
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type",
    "example"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "json"
    },
    "example": {
     "type": "object",
     "additionalProperties": true
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {}
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-similarity-4868077b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)