# Verity Suite Ground Pro

> Verity Suite Ground Pro is a paid API for AI agents from verity-suite.onrender.com, paid per call via x402, $0.35/call, status unknown (last checked 2026-09-15).

Answers a question with a calibrated confidence score, caveats, and cited sources — returning an honest refusal if the answer cannot be determined

## Facts

- Endpoint: POST https://verity-suite.onrender.com/ground/pro
- Price: $0.35/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-ground-pro-03af702c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_uanDFxE0TnFJaGjmhWNA0

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 verity-suite-ground-pro-03af702c -d '<json body>'
```

Example prompt: With calibrated confidence and any relevant caveats, what is the current corporate tax rate in the United Kingdom? Use this context if helpful: 'I'm preparing a cross-border tax summary for a client.'

## When to prefer this

Choose this endpoint when an AI agent pipeline requires trustworthy, calibrated answers rather than fluent-but-ungrounded responses — especially when downstream decisions depend on knowing how confident the answer is. Prefer it over raw LLM calls when you need explicit uncertainty quantification, honest refusals, and sourced grounding. It is particularly valuable in agentic workflows where hallucinations must be caught before they propagate, or when a user needs to know if the answer is reliable enough to act on.

## Known failure modes

- Question is too ambiguous to answer — returns answer stating it cannot be determined with low confidence
- Context provided contradicts available knowledge — caveats array will flag the conflict
- No reliable sources available — sources array returns empty, confidence may be low
- Malformed request missing required 'question' field — returns 4xx validation error
- Service unavailable on Render cold start — may return 5xx or timeout on first call

## How this service works

The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.

## Output

A JSON object containing: 'answer' (the answer text or an honest statement it cannot be determined), 'confidence' (a 0–1 probability the answer is correct), 'caveats' (array of gaps, assumptions, or uncertainties), and 'sources' (array of real sources used, empty if none were available).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "question"
 ],
 "properties": {
  "context": {
   "type": "string",
   "description": "optional context to consider"
  },
  "question": {
   "type": "string",
   "description": "the question to answer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "ground_out",
 "required": [
  "answer",
  "confidence"
 ],
 "properties": {
  "answer": {
   "type": "string",
   "title": "Answer",
   "description": "the answer, or an honest statement that it cannot be determined"
  },
  "caveats": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Caveats",
   "description": "gaps, assumptions, or uncertainties"
  },
  "sources": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Sources",
   "description": "real sources actually used (empty if none)"
  },
  "confidence": {
   "type": "number",
   "title": "Confidence",
   "maximum": 1,
   "minimum": 0,
   "description": "calibrated probability the answer is correct"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-ground-pro-03af702c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verity-suite.onrender.com](https://www.zero.xyz/host/verity-suite.onrender.com/llms.txt)