Guide EN-05

AI API Relay Risks

AI API relays can be useful, but users should check pricing anomalies, model substitution, prompt logging, balance loss, and enterprise compliance boundaries.

Reasonable use

Low-risk, repeatable, non-sensitive personal tasks.

Verify first

Model behavior, latency, error rate, refunds, terms, privacy, and ownership.

Avoid

Customer data, company source code, internal docs, and production decisions.

Risk checklist

These signals matter more than the discount.

RiskSignalHow to verifyImpactAction
Model substitutionClaimed model underperformsCompare fixed prompts with official APIUnreliable outputHigh risk
Balance lossNo refunds or unreachable supportCheck history and refund rulesFinancial lossHigh risk
Prompt loggingNo retention policyRead privacy and logging termsData exposureHigh risk
Extreme pricingFar below rational costCompare official and aggregator pricesUnknown supplyNeeds explanation

Self-check

Spend ten minutes before adding balance.

  1. Check legal entity, terms, privacy policy, refund rules, and update date.
  2. Run fixed prompts with small requests before larger tasks.
  3. Test streaming, rate limits, and error behavior.
  4. Do not upload private source code or customer data.

Use boundary

Personal low-risk

Small tests can be reasonable.

Team development

Prefer BYOK or official channels.

Enterprise buying

Require contracts, DPA, SLA, and invoices.

Public ranking

Show evidence and verification dates.

Submit risk sample

Contribute