# Hallucination Detection API

> Hallucination Detection API is a paid API for AI agents from hallucination-detection-api.johntaylor1online.workers.dev, paid per call via x402, $1/call, status unknown (last checked 2026-09-15).

Runs a full hallucination verification pipeline on text: extracts claims, verifies them against evidence, and returns a credibility score

## Facts

- Endpoint: POST https://hallucination-detection-api.johntaylor1online.workers.dev/verify
- Price: $1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/hallucination-detection-api-d57fe60b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_SEHodjofl9gxpCdL_3mNt

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 hallucination-detection-api-d57fe60b -d '<json body>'
```

Example prompt: Can you check this paragraph from my AI assistant's response for hallucinations — extract all the factual claims, verify each one, and give me a score for how trustworthy the whole thing is?

## When to prefer this

Choose this endpoint when you need an end-to-end hallucination verification pipeline that handles claim extraction, individual verification, and scoring in a single call — particularly useful for AI agent outputs, LLM-generated summaries, or any text where factual accuracy is critical before downstream use or publication.

## Known failure modes

- Empty or missing input text returns a validation error
- Extremely long text may exceed processing limits
- Ambiguous or highly subjective claims may receive low-confidence verification results
- Network timeouts on the Cloudflare Workers edge may return 5xx errors
- Payment not received or invalid x402 payment header returns a 402 response

## How this service works

Full hallucination verification pipeline — extract claims, verify, score

## Output

Returns a structured verification report containing extracted claims from the input text, individual verification results for each claim, and an overall hallucination/credibility score indicating how trustworthy the content is.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input",
  "output"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/hallucination-detection-api-d57fe60b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from hallucination-detection-api.johntaylor1online.workers.dev](https://www.zero.xyz/host/hallucination-detection-api.johntaylor1online.workers.dev/llms.txt)