# Foundry CSV Grouped Balance Reconciliation

> Foundry CSV Grouped Balance Reconciliation is a paid API for AI agents from foundry-par007-machine-revenue-mainnet.inference-chip-index.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Reconciles two CSVs (a detail file and a summary file) by grouping detail rows and comparing summed amounts to summary totals, returning match status, mismatches, and SHA-256 hashes of both inputs.

## Facts

- Endpoint: POST https://foundry-par007-machine-revenue-mainnet.inference-chip-index.workers.dev/v2/data/csv-grouped-balance-reconciliation
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/foundry-csv-grouped-balance-reconciliation-0e5b3ad4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_MEGRsB_iEZ8oVWyfFBKH6

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 foundry-csv-grouped-balance-reconciliation-0e5b3ad4 -d '<json body>'
```

Example prompt: Can you reconcile my transactions CSV against my monthly summary CSV? The detail file groups by 'account_id' and the amount column is 'transaction_amount'; the summary file groups by 'account_id' and its amount column is 'balance' — use 2 decimal places and tell me if everything matches or flag any discrepancies.

## When to prefer this

Use this endpoint when you need a pay-per-request, auditable reconciliation of two CSVs where one represents granular transaction detail and the other summarizes grouped totals. It is ideal for automated financial auditing pipelines, accounting close processes, and compliance workflows that require SHA-256 evidence hashes and a clear MATCH/MISMATCH verdict with explicit mismatches listed. Prefer it over general-purpose data tools when you need deterministic, reproducible results with provenance — and when CSV sizes fit within the 12,000-character per-file limit.

## Known failure modes

- Missing required fields (detail_csv, summary_csv, detail_group, detail_amount, summary_group, summary_amount) returns an error
- CSV content exceeds 12,000-character limit per file, causing rejection
- Column name not found in the provided CSV results in an error
- Malformed CSV (unquoted commas, mismatched columns) may cause parse failures
- Non-numeric amount values in the specified amount column cause computation errors
- decimal_places value outside 0–6 range is rejected

## How this service works

Pay-per-request evidence and data tools: CSV validation and reconciliation, DNS/email configuration evidence, and bounded official weather, earthquake, vehicle, company and study records. Exact USDC prices, explicit JSON contracts and source provenance. No mailbox, ownership, medical or safety guarantees.

## Output

Returns a JSON object with a 'status' field ('MATCH' or 'MISMATCH'), a list of any mismatches (group key plus detail-sum vs summary-amount), row counts for both CSVs, group count, mismatch count, SHA-256 hashes of both input CSVs for evidence provenance, the number of decimal places used, whether evidence was truncated, any limitations, and an observed_at timestamp.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "detail_csv": {
   "type": "string",
   "maxLength": 12000,
   "minLength": 1
  },
  "summary_csv": {
   "type": "string",
   "maxLength": 12000,
   "minLength": 1
  },
  "detail_group": {
   "type": "string",
   "maxLength": 100,
   "minLength": 1
  },
  "detail_amount": {
   "type": "string",
   "maxLength": 100,
   "minLength": 1
  },
  "summary_group": {
   "type": "string",
   "maxLength": 100,
   "minLength": 1
  },
  "decimal_places": {
   "type": "integer",
   "maximum": 6,
   "minimum": 0
  },
  "summary_amount": {
   "type": "string",
   "maxLength": 100,
   "minLength": 1
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "route": "csv-grouped-balance-reconciliation",
  "result": {
   "status": "MATCH",
   "mismatches": [],
   "detail_rows": 2,
   "group_count": 1,
   "limitations": [
    "Synthetic example hashes."
   ],
   "summary_rows": 1,
   "detail_sha256": "0000000000000000000000000000000000000000000000000000000000000000",
   "decimal_places": 2,
   "mismatch_count": 0,
   "summary_sha256": "0000000000000000000000000000000000000000000000000000000000000000",
   "evidence_truncated": false
  },
  "observed_at": "2026-09-06T00:00:00Z"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/foundry-csv-grouped-balance-reconciliation-0e5b3ad4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from foundry-par007-machine-revenue-mainnet.inference-chip-index.workers.dev](https://www.zero.xyz/host/foundry-par007-machine-revenue-mainnet.inference-chip-index.workers.dev/llms.txt)