# PayAI Dedupe – Name & Address Deduplication

> PayAI Dedupe – Name & Address Deduplication is a paid API for AI agents from payai.agentstools.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

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

## Facts

- Endpoint: POST https://payai.agentstools.dev/match/dedupe
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/payai-dedupe-name-address-deduplication-0f057154
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_MGkxHpg3P9RLQ7_IJkflO

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 payai-dedupe-name-address-deduplication-0f057154 -d '<json body>'
```

Example prompt: I have a list of 200 customer names that I think has a lot of duplicates — things like 'John Smith', 'J. Smith', 'Jon Smith'. Can you run deduplication on them and tell me how many unique people there are, with a canonical name for each cluster?

## When to prefer this

Choose this endpoint when you need fast, affordable fuzzy deduplication of names or addresses without setting up a full entity-resolution pipeline. Ideal for one-off data cleaning tasks, pre-processing before database import, or quick duplicate detection on lists of up to hundreds of entries. Prefer this over exact-match deduplication when spelling variations, abbreviations, and typos are expected. Not suitable when authoritative identity resolution or legal-grade matching is required.

## Known failure modes

- Empty or malformed input list returns a validation error
- Extremely large lists may exceed processing limits or timeout
- Very short or highly abbreviated inputs may produce low-confidence groupings
- Inputs mixing multiple languages or scripts may reduce match accuracy
- This service provides similarity indicators, not authoritative identity resolution — false positives and false negatives are possible

## 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 an array of clusters, each containing a canonical representative name or address, the list of input entries grouped into that cluster, similarity indicators explaining why they were grouped, and a top-level summary with total input count, number of unique clusters, and number of duplicates detected.

## 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/payai-dedupe-name-address-deduplication-0f057154/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from payai.agentstools.dev](https://www.zero.xyz/host/payai.agentstools.dev/llms.txt)