Home › Docs › Security and privacy
Control and visibilitySecurity and privacy
Your prompts and outputs pass straight through by default. Here is exactly what apicuts keeps, what we never store, and how inference keys are protected.
Prompts and outputs pass through to authorized model providers and are not stored by apicuts. Only request metadata is logged.
Company inference keys (ack_...) are hashed before storage and kept strictly separate from workspace management sessions in /app/keys.
Model providers apply their own retention policies to the requests they receive, including ephemeral prompt-cache TTLs. Routing uses only providers you approve.
Server-enforced workspace membership controls who on your team can access keys, usage reports, and funding.
Authorized API supply, lawful resale where applicable, and clear data-handling terms.
Requests to https://apicuts.ai/v1 and https://apicuts.ai travel over HTTPS (TLS).
Nothing you send through apicuts is used by us to train models.
A mutual NDA before kickoff and a Data Processing Agreement on request via [email protected].
Our audit is underway. See the Trust Center for every control and its status.
How logging, caching and provider retention fit together
- apicuts logs request metadata only: request ID, timestamp, model, endpoint, token and cache counts, latency, and cost.
- Provider prompt caching is handled inside the upstream provider for that provider's short ephemeral cache window; apicuts does not maintain a gateway response cache.
- Model providers each apply their own retention policy to the requests they receive. You choose which providers your traffic may use.
Want us to find your 20%+?
Get a free 360° cost report. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.
Get a Free 360° Cost Report