# FinOps Token Spend Audit

> FinOps Token Spend Audit is a paid API for AI agents from api.craigmbrown.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Audits an AI agent's actual token usage and cost against its declared budget and task scope, surfacing overruns and scope creep.

## Facts

- Endpoint: POST https://api.craigmbrown.com/v1/services/finops.token-spend-audit
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/finops-token-spend-audit-023c8412
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__IRM8oJZJLKXIyuJH_uSs

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 finops-token-spend-audit-023c8412 -d '<json body>'
```

Example prompt: Run an independent token spend audit on the usage records from the last 30 days — check whether the agent named 'research-bot' using GPT-4o stayed within the $500 monthly budget threshold and flag any cost overruns or scope creep I wouldn't otherwise see.

## When to prefer this

Choose this endpoint when you need an independent, verifiable audit of an agent's token expenditure that a counterparty can trust — particularly for accountability between agent operators and clients, compliance checks against declared budgets, or detecting cost growth that internal dashboards might obscure. It is purpose-built for FinOps on LLM workloads rather than general-purpose analytics.

## Known failure modes

- Empty or malformed records array yields no findings but may return a vacuous pass status
- Timestamps outside the declared window_days range may be silently excluded from totals
- Missing price_book causes cost calculations to fall back to defaults that may not match actual provider pricing
- Records exceeding the 10,000 item limit are rejected with a validation error
- Incomplete agent or model fields reduce attribution accuracy in per-agent breakdowns

## How this service works

Independent audit of an agent's actual token spend against its budget and declared task scope — surfaces cost overruns or scope creep a counterparty wouldn't otherwise see.

## Output

Returns a JSON object with the overall audit status, cost totals for the period, spending growth metrics, an array of specific findings (overruns, anomalies, scope creep events), projected monthly savings in USD, a trust score from BlindOracle, underlying assumptions, and a verify_recipe string so the counterparty can independently confirm the audit.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "records": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "ts"
    ],
    "properties": {
     "ts": {
      "type": "string"
     },
     "agent": {
      "type": "string"
     },
     "model": {
      "type": "string"
     },
     "cost_usd": {
      "type": "number",
      "minimum": 0
     },
     "provider": {
      "type": "string"
     },
     "max_tokens": {
      "type": "integer",
      "minimum": 0
     },
     "input_tokens": {
      "type": "integer",
      "minimum": 0
     },
     "output_tokens": {
      "type": "integer",
      "minimum": 0
     },
     "prompt_sha256": {
      "type": "string"
     }
    }
   },
   "maxItems": 10000
  },
  "price_book": {
   "type": "object"
  },
  "thresholds": {
   "type": "object"
  },
  "window_days": {
   "type": "number",
   "minimum": 0
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "schema": {
  "type": "object",
  "properties": {
   "growth": {
    "type": "object"
   },
   "period": {
    "type": "object"
   },
   "status": {
    "type": "string"
   },
   "totals": {
    "type": "object"
   },
   "asserts": {
    "type": "string"
   },
   "bo_trust": {
    "type": "object"
   },
   "findings": {
    "type": "array",
    "items": {
     "type": "object"
    }
   },
   "assumptions": {
    "type": "array",
    "items": {
     "type": "string"
    }
   },
   "verify_recipe": {
    "type": "string"
   },
   "deliverable_type": {
    "type": "string"
   },
   "projected_monthly_saving_usd": {
    "type": "number"
   }
  }
 },
 "example": {
  "deliverable_type": "..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/finops-token-spend-audit-023c8412/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.craigmbrown.com](https://www.zero.xyz/host/api.craigmbrown.com/llms.txt)