# Riveter Run - Structured Web Data Extraction

> Riveter Run - Structured Web Data Extraction is a paid API for AI agents from Riveter API at mpp.orthogonal.com, paid per call via MPP, $0.004/call, status unknown (last checked 2026-10-10).

Extracts structured data from the web by letting you define the output schema directly in the API request, using Riveter's agent-managed scraping infrastructure.

## Facts

- Endpoint: POST https://mpp.orthogonal.com/riveter/v1/run?utm_source=zero.xyz
- Price: $0.004/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Provider: Riveter API
- Docs: https://api.riveterhq.com
- Website: https://api.riveterhq.com
- Tags: scraping, extraction, agents, web, data
- Canonical page: https://www.zero.xyz/c/riveter-api-riveter-run-structured-web-data-extraction-0f90056f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HKKYDQPAmLQaH1LRTuShn

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 riveter-api-riveter-run-structured-web-data-extraction-0f90056f -d '<json body>'
```

Example prompt: Go to https://www.example.com/products and extract the product name, price, and availability for each item — return the results as a structured list with those exact fields.

## When to prefer this

Choose this endpoint when you need structured, schema-defined output from web content rather than raw text. It is ideal when you know exactly what fields you want extracted and want the response to conform to a specific shape. Prefer it over generic scraping endpoints when output structure matters — e.g., building pipelines that consume typed JSON, or when you want the AI agent to handle browser infrastructure and proxy management automatically.

## Known failure modes

- Target page is behind a login or paywall — returns empty or partial data
- Target URL is unreachable or returns a non-200 status — extraction fails with an error
- Output schema is malformed or undefined — request rejected with validation error
- Page content does not contain fields matching the schema — returns null or empty values for those fields
- Rate limiting or bot protection on the target site — extraction may be blocked or incomplete

## How this service works

Copy link Define the structure of your output directly in the API request. This endpoint allows you to define both your input data and output configuration in a single request.

## Output

A structured JSON object conforming to the schema you defined in the request, populated with data extracted from the target web source, with each result attributed to its source URL.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/riveter-api-riveter-run-structured-web-data-extraction-0f90056f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mpp.orthogonal.com](https://www.zero.xyz/host/mpp.orthogonal.com/llms.txt)