# gateway.apiosk.com Trust-Checks Knowledge Validator

> gateway.apiosk.com Trust-Checks Knowledge Validator is a paid API for AI agents from gateway.apiosk.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Validates an AI-generated answer against approved facts and forbidden claims, returning issues and matched facts

## Facts

- Endpoint: POST https://gateway.apiosk.com/trust-checks/knowledge
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gateway-apiosk-com-trust-checks-knowledge-validator-d2855493
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7IODcRNS37kcvgxosbDqZ

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 gateway-apiosk-com-trust-checks-knowledge-validator-d2855493 -d '<json body>'
```

Example prompt: Before I send this answer to the user — 'Our Pro plan costs $20/month and includes unlimited seats' — can you trust-check it against these approved facts: ['The plan costs 20 dollars per month', 'Seats are limited to 10 users'] and flag it if it contains any of these forbidden claims: ['unlimited seats', 'free trial included']?

## When to prefer this

Use this endpoint when you need to validate AI-generated or agent-produced answers against a curated set of ground-truth facts and a blocklist of prohibited claims before delivering the response to end users — especially in customer support, compliance, or product documentation contexts where factual accuracy and policy adherence are critical.

## Known failure modes

- Missing 'answer' field returns validation error
- Empty approved_facts array may result in no matched_facts
- Forbidden claims list not provided may skip claim checking
- Network timeout on large answer texts
- Ambiguous or overlapping facts and forbidden claims may produce inconsistent results

## How this service works

Check a generated answer against a set of approved facts and forbidden claims to catch ungrounded or off-limits statements. Flags forbidden claims found in the answer and warns when the answer matches none of the approved facts.

## Output

Returns a JSON object with a boolean 'valid' field indicating whether the answer passed, an 'issues' array listing any detected problems (e.g. forbidden claims found), a 'matched_facts' array showing which approved facts were confirmed, and the endpoint name.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gateway-apiosk-com-trust-checks-knowledge-validator-d2855493/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gateway.apiosk.com](https://www.zero.xyz/host/gateway.apiosk.com/llms.txt)