# AgentsTools Dedupe – Name & Address Deduplication

> AgentsTools Dedupe – Name & Address Deduplication is a paid API for AI agents from api.agentstools.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Deduplicates a list of names or addresses into clusters of likely duplicates, returning a canonical representative per cluster plus summary statistics.

## Facts

- Endpoint: POST https://api.agentstools.dev/match/dedupe
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentstools-dedupe-name-address-deduplication-cdde38a6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_gvyPUCsJRCfL4fzkVvj1W

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 agentstools-dedupe-name-address-deduplication-cdde38a6 -d '<json body>'
```

Example prompt: Can you deduplicate this list of company names for me — ['Acme Corp', 'Acme Corporation', 'ACME corp.', 'Widget Co', 'Widget Company Inc'] — and group the ones that are likely the same company together?

## When to prefer this

Choose this endpoint when you have a raw list of names, addresses, or organization strings that may contain near-duplicates and you need fast probabilistic clustering without standing up your own record-linkage pipeline. Ideal for pre-processing CRM imports, mailing lists, vendor databases, or any scenario where string normalization and fuzzy matching across entity types (person, company, address, product, org) is needed in a single API call.

## Known failure modes

- Empty or single-item list returns no clusters
- Highly abbreviated or truncated inputs may fail to match obvious duplicates
- Very large lists may hit payload limits
- min_score set too high causes under-clustering; too low causes over-clustering
- Non-standard characters or mixed scripts may reduce match quality

## How this service works

Deduplicate a list of names or addresses into clusters of likely duplicates. Blocks by similarity key then confirms pairwise inside each block, returning clusters with a canonical representative plus a summary of input, cluster and duplicate counts. Similarity indicators, not authoritative identity resolution.

## Output

Returns clusters of likely-duplicate strings, each with a canonical representative, plus a summary of total input count, number of clusters, and number of duplicates found. Similarity is probabilistic (not authoritative identity resolution).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "type": {
   "enum": [
    "person",
    "company",
    "address",
    "product",
    "org"
   ],
   "type": "string",
   "description": "Entity type selecting the normalization pipeline (default company)"
  },
  "items": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "The list of strings to deduplicate"
  },
  "min_score": {
   "type": "integer",
   "description": "Optional match threshold 0-100 (default is the per-type threshold)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentstools-dedupe-name-address-deduplication-cdde38a6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentstools.dev](https://www.zero.xyz/host/api.agentstools.dev/llms.txt)