# capi2 Evidence Extraction

> capi2 Evidence Extraction is a paid API for AI agents from capi2-demand-tools.onrender.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-16).

Fetches a public web URL and extracts the most relevant text passages that support or answer a given claim, question, or evidence query.

## Facts

- Endpoint: POST https://capi2-demand-tools.onrender.com/v1/evidence/extract
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/capi2-evidence-extraction-7f417c9d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_gvVWlCF_mKg1uhqUA1GlC

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 capi2-evidence-extraction-7f417c9d -d '<json body>'
```

Example prompt: Go to https://en.wikipedia.org/wiki/Climate_change and pull out the top 5 passages that best support the claim 'human activity is the primary driver of recent global warming'.

## When to prefer this

Choose this endpoint when you need to extract semantically relevant text passages from a specific known public URL to support, verify, or investigate a claim or question — particularly for fact-checking, research evidence gathering, or auditing web content. Prefer it over general web search when you already have the source URL and need targeted, scored excerpts rather than broad discovery.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status — extraction fails with an error
- URL points to a paywalled, login-required, or bot-blocked page — no content extractable
- Query string is too short (under 2 characters) or too long (over 1000 characters) — validation error
- max_passages value is out of range (must be 1–10) — validation error
- Page contains no parseable text (e.g. pure image, Flash, or heavily JavaScript-rendered) — empty or poor passages returned
- Network timeout fetching the remote URL — request fails
- Invalid URI format for the url field — schema validation error

## How this service works

Paid x402 utilities and live intelligence for autonomous agents: hashing/encoding plus public web lookup, domain intelligence, API discovery audit, evidence extraction and x402 health.

## Output

Returns a list of ranked text passages extracted from the given URL that are most semantically relevant to the query, each with a relevance score, along with the source URL and total passage count returned.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Public source URL."
  },
  "query": {
   "type": "string",
   "maxLength": 1000,
   "minLength": 2,
   "description": "Claim, question or evidence terms."
  },
  "max_passages": {
   "type": "integer",
   "default": 5,
   "maximum": 10,
   "minimum": 1
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "passages": [
   {
    "text": "Example Domain",
    "score": 1
   }
  ],
  "source_url": "https://example.com",
  "passage_count": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/capi2-evidence-extraction-7f417c9d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from capi2-demand-tools.onrender.com](https://www.zero.xyz/host/capi2-demand-tools.onrender.com/llms.txt)