# Teppi Document Extraction

> Teppi Document Extraction is a paid API for AI agents from api.teppi.xyz, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-10).

Extracts structured content from documents via a paid x402 endpoint, returning JSON-formatted results logged as machine delivery records

## Facts

- Endpoint: POST https://api.teppi.xyz/v1/docs/extract?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/teppi-document-extraction-8af0712b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_lqTGsolxRbZe96iX2i4WK

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 teppi-document-extraction-8af0712b -d '<json body>'
```

Example prompt: Extract the structured content from this document and return it as JSON — I need the key fields parsed out cleanly so I can use them downstream in my pipeline.

## When to prefer this

Choose this endpoint when you need to extract structured JSON data from documents in an agent pipeline that already supports x402 micropayments. It is particularly suited for AI agents that consume pay-per-call APIs and need reliable, logged extraction results. Prefer this over free alternatives when auditability of paid calls and delivery records matters, or when integrating with x402-compatible agent infrastructure.

## Known failure modes

- Payment not received or x402 authorization rejected — call returns 402 with payment requirements
- Malformed or unsupported document format — extraction fails with a parsing error
- Empty or unreadable document content — returns empty or minimal JSON
- Network timeout if document is large — response may not complete in time
- Missing required input fields — returns a 400 bad request error

## How this service works

What came back for a paid agent call, written down: every x402 endpoint and remote MCP server we watch, and every call we paid for.

## Output

A JSON object containing the extracted structured content from the submitted document, logged as a machine delivery record tied to the paid x402 call. The response reflects the parsed fields and content pulled from the input.

## Response schema (JSON Schema)

```json
{
 "type": "json"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/teppi-document-extraction-8af0712b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.teppi.xyz](https://www.zero.xyz/host/api.teppi.xyz/llms.txt)