# gateway.apiosk.com – Data Deduplication (data-clean/dedupe)

> gateway.apiosk.com – Data Deduplication (data-clean/dedupe) is a paid API for AI agents from gateway.apiosk.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Deduplicates an array of records by clustering near-duplicate entries based on a similarity threshold, returning cluster assignments for each record.

## Facts

- Endpoint: POST https://gateway.apiosk.com/data-clean/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/gateway-apiosk-com-data-deduplication-data-clean-dedupe-220d4bb1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oMUjmX9o3_Ue7NzIE42Kf

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 gateway-apiosk-com-data-deduplication-data-clean-dedupe-220d4bb1 -d '<json body>'
```

Example prompt: I have a list of customer records and I want to find the duplicates — can you deduplicate them using a similarity threshold of 0.8 and tell me which ones cluster together?

## When to prefer this

Choose this endpoint when you need to programmatically deduplicate or cluster an array of records by similarity — especially for entity resolution, data cleaning pipelines, or merging near-duplicate entries. Prefer it over exact-match deduplication when fuzzy/approximate matching is needed, controlled by the threshold parameter.

## Known failure modes

- Empty or missing records array returns an error
- Non-numeric threshold value causes validation failure
- Threshold outside valid range (e.g. >1 or <0) may return error or unexpected clusters
- Very large record arrays may time out or exceed payload limits
- Malformed record objects may cause partial processing or error
- Network/payment failure (x402) if USDC balance is insufficient

## How this service works

Fuzzy-match a submitted record set and return cluster ids for likely duplicates.

## Output

Returns a JSON object with ok status, total record count, per-record cluster assignments (each record gets a cluster_id), and the total number of clusters found. Records sharing the same cluster_id are considered duplicates or near-duplicates of each other.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gateway-apiosk-com-data-deduplication-data-clean-dedupe-220d4bb1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gateway.apiosk.com](https://www.zero.xyz/host/gateway.apiosk.com/llms.txt)