# Vextorium Text Similarity

> Vextorium Text Similarity is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-28).

Computes multi-metric text similarity between two strings, returning TF-IDF cosine, Jaccard scores, common words, and a similarity verdict

## Facts

- Endpoint: POST https://api.vextorium.com/v1/text-similarity?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-text-similarity-102ee3e7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pbjfWI5lNudVTeyKylFyU

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 vextorium-text-similarity-102ee3e7 -d '<json body>'
```

Example prompt: Compare these two texts for similarity and tell me the cosine score, Jaccard overlap, and whether they're considered similar or different: text A is 'pay per call APIs for AI agents' and text B is 'per call payment APIs for developers'.

## When to prefer this

Choose this endpoint when you need multi-dimensional text similarity covering lexical overlap (Jaccard) and semantic frequency weighting (TF-IDF cosine) together in a single call, without standing up your own NLP infrastructure. It is especially useful for lightweight duplicate detection, content matching, or relevance scoring tasks where you need a fast, pay-per-call solution without managing embeddings or vector databases.

## Known failure modes

- Missing text_a or text_b fields returns a validation error
- Empty strings may produce zero-score outputs with a dissimilar verdict
- Very long texts may degrade performance or hit payload limits
- Non-UTF-8 or malformed input may cause parsing errors

## How this service works

244 pay-per-call data APIs for AI agents: official statistics and economy (ECB, Fed, Eurostat, World Bank, SEC, BOE, INE), crypto prices and sentiment, Spanish public data, compliance (sanctions, VAT, IBAN, LEI), science, weather, web and developer tools and local AI text tools. Pay in USDC via x402.

## Output

Returns a JSON object with: a text verdict (e.g. 'similar' or 'distintos'), an array of the most common shared words, TF-IDF cosine similarity score (0–1), count of words in common, characters Jaccard similarity (0–1), and vocabulary Jaccard similarity (0–1).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text_a": {
   "type": "string"
  },
  "text_b": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "verdict": "distintos",
  "most_common": [
   "pay",
   "per"
  ],
  "tfidf_cosine": 0.2316,
  "words_in_common": 3,
  "characters_jaccard": 0.2609,
  "vocabulary_jaccard": 0.3
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-text-similarity-102ee3e7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.vextorium.com](https://www.zero.xyz/host/api.vextorium.com/llms.txt)