{"uid":"cap_trQcVVQKRHGC8kwjIBcA-","slug":"model-attestation-substitution-detection-5646d4f8","name":"Model Attestation & Substitution Detection","description":"Proof-of-Model: detect silent model substitution at any OpenAI-compatible inference endpoint. mode=fingerprint records what a seller serves today; mode=verify re-probes later and proves whether the weights changed. Deterministic, evidence included, no model used to judge.","url":"https://dev-5090-box.tailfb4c1f.ts.net/v1/attest/model?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"kind":{"type":"string"},"claim":{"type":"string"},"verdict":{"type":"string"},"comparisons":{"type":"array"},"mean_similarity":{"type":"number"},"self_consistency_now":{"type":"number"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.1","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":"$0.1/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_f0pQ9B_xhkGvM-bLW6rNw","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.1","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fingerprints or verifies an OpenAI-compatible inference endpoint to detect silent model substitution by the seller","exampleAgentPrompt":"Fingerprint the inference endpoint at https://api.example.com/v1 right now so I have a baseline record of what model they're actually serving, then later re-verify it to prove whether they've silently swapped the model.","exampleUseCases":[{"title":"Baseline model fingerprint before purchase","prompt":"I'm about to start paying for inference from a vendor claiming they run Qwen3-72B — fingerprint their endpoint now in mode=fingerprint so I have a cryptographic record of what they're actually serving today."},{"title":"Verify model hasn't been swapped mid-contract","prompt":"It's been two weeks since I fingerprinted that vendor's endpoint — re-probe it in mode=verify and tell me whether the mean_similarity score confirms they're still serving the same model or if there's been a substitution."},{"title":"Audit third-party AI reseller integrity","prompt":"I'm reselling inference from a third-party provider and my customers are complaining the outputs feel different — run an attestation check and give me the verdict and self_consistency_now score so I can prove whether the underlying model changed."}],"resultDescription":"Returns a structured attestation result including a kind field indicating the probe type, a claim about the model identity, a verdict on whether the model matches the fingerprint, an array of per-sample comparison results, a mean_similarity score, and a self_consistency_now score reflecting current output stability.","failureModes":["Endpoint unreachable or returns non-200 — attestation cannot complete","Model serves stochastic outputs causing low similarity scores even without substitution","Seller applies output filtering that defeats fingerprinting probes","mean_similarity near threshold makes verdict ambiguous","Payment of 0.1 USDC not processed — request blocked by x402 paywall"],"whenToPreferThis":"Use this endpoint when you need cryptographic or statistical proof that an inference provider is actually serving the model they claim — especially before signing contracts, after suspicious output quality changes, or as a recurring integrity check in automated AI procurement pipelines. Prefer this over manual output inspection when you need a quantified similarity verdict and documented evidence of substitution.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T12:46:54.186Z","isFirstParty":false,"canonicalSlug":"model-attestation-substitution-detection-5646d4f8"}