# fittings Text Similarity

> fittings Text Similarity is a paid API for AI agents from fittings.sh, paid per call via x402, $0.004052/call, status unknown (last checked 2026-10-12).

Computes Jaro-Winkler, token-sorted, and Levenshtein similarity ratios between two text strings, returning all three scores plus the strongest as the headline match score.

## Facts

- Endpoint: POST https://fittings.sh/v1/text/similarity?utm_source=zero.xyz
- Price: $0.004052/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/fittings-text-similarity-f2e4ee7d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FyR5f9k7vjXSzI15iR6_Z

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 fittings-text-similarity-f2e4ee7d -d '<json body>'
```

Example prompt: How similar are the strings 'Jonathan Smith' and 'Jon Smyth'? Give me the Jaro-Winkler, token-sorted, and Levenshtein scores, and flag it as a match if the headline score is above 0.85.

## When to prefer this

Choose this endpoint when you need multi-algorithm fuzzy string similarity in a single call — especially when Jaro-Winkler alone is insufficient for token-order-variant inputs (e.g. 'Smith, John' vs 'John Smith'), or when you want to pick the strongest of three algorithms without running them separately. Prefer over single-metric APIs when robustness across different string variation types matters.

## Known failure modes

- Input string exceeds 512 characters — request rejected
- Missing required field 'a' or 'b' — validation error returned
- Threshold outside 0–1 range — bad request error
- Non-string input for 'a' or 'b' — type error

## How this service works

Similarity of two records from 0 to 1: Jaro-Winkler, token-sorted and Levenshtein ratios, and the strongest of the three as the headline score.

## Output

Returns a JSON object containing three similarity scores (Jaro-Winkler ratio, token-sorted ratio, and Levenshtein ratio), each as a float between 0 and 1, plus a headline score representing the strongest of the three. Optionally includes a boolean match result if a threshold was supplied.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "a": {
   "type": "string",
   "description": "Up to 512 characters"
  },
  "b": {
   "type": "string",
   "description": "Up to 512 characters"
  },
  "threshold": {
   "type": "number",
   "description": "Match cutoff from 0 to 1. Default 0.85."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/fittings-text-similarity-f2e4ee7d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from fittings.sh](https://www.zero.xyz/host/fittings.sh/llms.txt)