# Sift Web Tools – /v1/extract

> Sift Web Tools – /v1/extract is a paid API for AI agents from sift.srv1996466.hstgr.cloud, paid per call via x402, $0.015/call, status unknown (last checked 2026-10-23).

Extracts named fields as structured JSON from any web page by specifying a comma-separated list of field names and a URL

## Facts

- Endpoint: GET https://sift.srv1996466.hstgr.cloud/v1/extract?utm_source=zero.xyz
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sift-web-tools-v1-extract-4677a0c3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eaWY_qnt5yjQlxouPE4al

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 sift-web-tools-v1-extract-4677a0c3
```

Example prompt: Extract the fields 'latest_version', 'release_date', and 'download_url' from https://www.python.org/downloads/ and return them as JSON.

## When to prefer this

Choose this endpoint when you need to extract specific, named data fields from a web page and receive them as structured JSON — ideal for data pipelines, agent workflows that need machine-readable output, or situations where parsing raw HTML is impractical. Prefer /v1/extract over /v1/fetch (which returns raw readable text) or /v1/summarize (which returns prose) when you know exactly which fields you want and need them in a structured, programmatically usable format. Best for pages with clearly labeled data like product listings, software download pages, job postings, company profiles, or news articles.

## Known failure modes

- Page is behind a login wall or paywalled — extraction may return empty or incomplete fields
- Requested field names do not match any discernible content on the page — fields return null or empty strings
- Page uses heavy JavaScript rendering that is not fully executed — dynamic content may be missing
- URL is unreachable or returns a non-200 status — call is not charged but no data is returned
- Ambiguous field names may match unintended page content — returns best-guess values
- Rate limiting or bot detection on the target site may block the fetch — results in failure response

## How this service works

AI extraction of named fields from any web page as JSON. Give a URL and comma-separated field names; get a JSON object with the best value per field, plus a list of records when the page lists many (products, people, events).

## Output

A JSON object containing the requested named fields and their extracted values from the target web page. The response includes a 'data' key with field-value pairs, and an 'items' array for list-type results. For example: {"data": {"latest_version": "3.14.0", "release_date": "2025-10-07", "download_url": "https://..."}, "items": []}

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url",
      "fields"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Page URL"
      },
      "fields": {
       "type": "string",
       "description": "Comma-separated field names"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "download_url": "https://www.python.org/ftp/python/...",
   "release_date": "2025-10-07",
   "latest_version": "3.14.0"
  },
  "items": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sift-web-tools-v1-extract-4677a0c3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sift.srv1996466.hstgr.cloud](https://www.zero.xyz/host/sift.srv1996466.hstgr.cloud/llms.txt)