{"uid":"cap_yJUF55GFnlucBZmvoEn9j","slug":"proof-of-model-ai-model-substitution-detector-bf6182fb","name":"Proof-of-Model: AI Model Substitution Detector","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://linked-aimed-reproduced-changing.trycloudflare.com/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_l7mKiMLKO_Y09_LN4NVKp","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":"Detects silent model substitution at any OpenAI-compatible inference endpoint by fingerprinting model weights and verifying they haven't changed over time.","exampleAgentPrompt":"Fingerprint the model currently being served at my OpenAI-compatible endpoint https://api.myprovider.com and record today's baseline so we can verify later whether they secretly swap out the weights.","exampleUseCases":[{"title":"Initial model fingerprint baseline","prompt":"Run a fingerprint attestation on the inference endpoint at https://api.someprovider.com/v1 so we have a recorded baseline of what model they're serving today — I want to be able to catch it if they ever quietly swap the weights."},{"title":"Verify model hasn't changed since last audit","prompt":"Re-probe https://api.someprovider.com/v1 in verify mode and compare it against the fingerprint I captured last month — tell me whether the model weights are still the same or if something changed, and include the evidence."},{"title":"Catch bait-and-switch before paying for inference","prompt":"Before I commit to this new AI API vendor, use verify mode to check that the endpoint at https://api.newvendor.com actually serves the model they claim, using these prior comparisons from my test run: [comparisons array] — I need proof, not just their word."}],"resultDescription":"Returns a structured attestation object containing: a verdict (weights match or changed), the kind of check performed (fingerprint or verify), the model claim being tested, an array of deterministic comparisons used as evidence, a mean similarity score, and a self-consistency score — all without using another model to judge the result.","failureModes":["Unreachable or non-OpenAI-compatible target endpoint returns connection error","Insufficient probe responses to compute a statistically reliable fingerprint","Mean similarity score falls in ambiguous range making verdict inconclusive","Target endpoint rate-limits or blocks the probing requests","Payment of 0.1 USDC not confirmed, request rejected","Baseline fingerprint missing when verify mode is requested"],"whenToPreferThis":"Choose this endpoint when you need deterministic, evidence-backed proof that an OpenAI-compatible inference endpoint is serving the model it claims — particularly before signing SLAs with AI vendors, after vendor infrastructure changes, or for ongoing model integrity monitoring. Unlike model-based evaluation approaches, this endpoint uses no AI judge, making it tamper-resistant and fully auditable.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T18:41:34.889Z","isFirstParty":false,"canonicalSlug":"proof-of-model-ai-model-substitution-detector-bf6182fb"}