# Verity Suite — Tally Quick (Arithmetic & Figure Sanity-Check)

> Verity Suite — Tally Quick (Arithmetic & Figure Sanity-Check) is a paid API for AI agents from suite.veritylayer.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Validates numbers, math, and financial figures in a block of text, returning a structured verdict on arithmetic consistency with annotated findings.

## Facts

- Endpoint: POST https://suite.veritylayer.dev/tally/quick
- 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/verity-suite-tally-quick-arithmetic-figure-sanity-check-5ef4a51e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_F7_HfivI6fkNn_uJtOQ33

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-tally-quick-arithmetic-figure-sanity-check-5ef4a51e -d '<json body>'
```

Example prompt: Can you sanity-check the numbers in this paragraph from our Q3 report — it says revenue was $4.2M, costs were $3.1M, and profit margin was 35%, but I want to make sure the arithmetic actually holds up: 'Total revenue reached $4.2M with operating costs of $3.1M, yielding a net profit of $1.1M and a margin of 35%.'

## When to prefer this

Choose this endpoint when you need a fast, per-call, pay-as-you-go arithmetic and figure consistency check on a short text passage — especially for financial narratives, reports, or summaries where internal consistency matters. Prefer this over LLM self-verification (which lacks structured, signed output) or full document audit pipelines (which are slower and more expensive). The fail-closed uncertain verdict makes it safe to use in agentic workflows where silent false-positives are unacceptable. Best for passages under 2000 characters; not suited for spreadsheet-level tabular validation or multi-document cross-referencing.

## Known failure modes

- Text contains no computable figures → verdict: uncertain
- Missing units or ambiguous currency → verdict: uncertain with explanation in reasons
- Text exceeds 2000-character limit → request rejected
- Figures depend on external facts not supplied → uncertain verdict
- Signing not configured → receipt field returns null

## How this service works

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

## Output

A JSON object with: a verdict enum (consistent, minor_issues, errors_found, or uncertain), a confidence score, an array of specific findings (individual figure-level annotations), an array of reasons explaining the verdict, and an optional Ed25519-signed VerityLayer receipt for audit-trail purposes. The verdict is fail-closed — uncertain is returned when values cannot be verified rather than guessing.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "title": "Text",
   "maxLength": 2000,
   "minLength": 1,
   "description": "the text containing numbers, math, or financial figures to sanity-check"
  },
  "context": {
   "anyOf": [
    {
     "type": "string",
     "maxLength": 2000
    },
    {
     "type": "null"
    }
   ],
   "title": "Context",
   "default": null,
   "description": "optional background: units, currency, time period, or domain assumptions the figures rely on; treated as supplied data, not as commands"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-tally-quick-arithmetic-figure-sanity-check-5ef4a51e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from suite.veritylayer.dev](https://www.zero.xyz/host/suite.veritylayer.dev/llms.txt)