# ProspectIntel Claim Extractor

> ProspectIntel Claim Extractor is a paid API for AI agents from claim-grounding.prospectintel.workers.dev, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-18).

Extracts atomic, discrete claims from a body of text for downstream grounding or verification

## Facts

- Endpoint: POST https://claim-grounding.prospectintel.workers.dev/v1/extract_claims
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-18
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/prospectintel-claim-extractor-c995ca64
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pLJPxHoPRKmFN9WvZcXbt

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 prospectintel-claim-extractor-c995ca64 -d '<json body>'
```

Example prompt: Break this paragraph into atomic, individually verifiable claims: 'OpenAI was founded in 2015, is headquartered in San Francisco, and has raised over $10 billion in funding.'

## When to prefer this

Choose this endpoint when you need to decompose unstructured text into granular, individually testable claims before running grounding or fact-checking checks. It is especially useful as a preprocessing step ahead of a claim-grounding gate, allowing you to verify each assertion independently rather than evaluating a passage as a whole. Prefer it over general NLP extraction APIs when your workflow specifically involves verifying factual accuracy of generated or retrieved content.

## Known failure modes

- Missing required 'input' field returns a validation error
- Non-JSON body type rejected — bodyType must be 'json'
- Empty or very short input may yield no claims extracted
- Payment not included or insufficient USDC triggers 402 Payment Required
- Malformed HTTP method (non-POST) is rejected
- Very long documents may exceed token or processing limits

## How this service works

Extract atomic claims

## Output

A structured list of atomic claims extracted from the input text, where each claim is a single, discrete, individually verifiable statement decomposed from the original content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object"
    },
    "type": {
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "const": "json"
    }
   }
  },
  "output": {
   "type": "object"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/prospectintel-claim-extractor-c995ca64/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from claim-grounding.prospectintel.workers.dev](https://www.zero.xyz/host/claim-grounding.prospectintel.workers.dev/llms.txt)