{"uid":"cap__IRM8oJZJLKXIyuJH_uSs","slug":"finops-token-spend-audit-023c8412","name":"FinOps Token Spend Audit","description":"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.","url":"https://api.craigmbrown.com/v1/services/finops.token-spend-audit","method":"POST","headers":{},"bodySchema":{"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}}},"responseSchema":{"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":"..."}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_XAwUMSI7OKve8CK3I4Pr7","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Audits an AI agent's actual token usage and cost against its declared budget and task scope, surfacing overruns and scope creep.","exampleAgentPrompt":"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.","exampleUseCases":[{"title":"Monthly budget compliance check","prompt":"Audit the past 30 days of token usage for my 'data-pipeline-agent' using Claude Sonnet — I set a $200/month budget and want to know if it stayed within bounds or if there are any overruns I should be aware of."},{"title":"Detecting unexpected agent scope creep","prompt":"Something feels off with my agent fleet — can you run a token spend audit over the last 7 days across all agents and tell me if any of them are doing significantly more work than their declared task scope would justify?"},{"title":"Projecting cost savings before contract renewal","prompt":"I want to renegotiate my LLM provider contract — can you audit 90 days of token spend records across our agents and give me a projected monthly savings figure if we cut the identified inefficiencies?"}],"resultDescription":"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.","failureModes":["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"],"whenToPreferThis":"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.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:46:42.415Z","isFirstParty":false}