AI Relay CheckIndependent AI API relay reviews
REVIEW METHODOLOGY

AI API Relay Review Methodology

Read how AI Relay Check evaluates uptime, actual cost, model identity, task performance, support, and commercial independence.

Evidence levels

Paid model requests, website probes, provider-published material, third-party records, and unverified submissions use different labels. Only timestamped model requests count as API verification.

Failure threshold

One model failure remains a sample. Verification is removed only after every configured model in the same provider family fails at least four consecutive times.

Pricing rules

Input and output rates remain separate, as do pay-as-you-go prices, full-use subscription equivalents, and observed wallet charges. Different routes and client restrictions do not share one price rank.

Commercial independence

Affiliate commissions, advertising, and provider test credit do not change samples, score weights, or ranking order.

Evidence layers and decision boundaries

EvidenceHow collectedStored fieldsDoes not prove
Website reachabilityScheduled HTTPS requestHTTP result, final hostname, timestampDoes not prove API availability
Model API verificationPaid request with a dedicated test keyModel ID, protocol, success/failure, latency, tokensDoes not prove model identity
Published pricingProvider-owned page or endpointInput/output rate, group, capture date, source URLDoes not equal observed billing
Billing reconciliationFixed request plus balance before/afterTokens, cache fields, expected and observed chargeValid only for the tested route
Model identityRepeated capability and consistency probesCross-run behavior and control-task evidenceNever inferred from the response model name alone

Failed paid requests remain in the sample. Price, uptime, API success, billing, and model identity are never substituted for one another. Affiliate links and test credit do not change score weights.

Related pages