We cache verified answers. Your account history holds no prompt text. Most security pages are written to make you stop asking. This one answers the question, then tells you how to check.
Data handling, in one line. We do not store the text of your prompts or answers in your account records; only metered metadata (token counts, timings, cost) persists there, for billing and abuse prevention. Your prompt text is stored elsewhere, in the shared cache: when an answer passes verification we keep it together with the prompt that produced it, in a store that is shared by default. Send tirtha.no_cache to skip the cache for a request. We never train on your data, and our serving provider's no-training and retention terms are verified in writing. Full detail: privacy policy.
Your keys, revoked any time. Your spend, capped and enforced on our servers. Your participation: the beta is invite-only and opt-in from the very first touch.
A per-key switch so your answers never enter the shared cache. Spend caps you set yourself. A view of exactly what we hold about your account. One-click export and deletion.
Every control we add follows one rule: it can only reduce what we hold, or show you what we already do. We do not add levers that reach into your data.
Every claim on this page is written to be checkable, and we would rather show you than promise you. Email [email protected] and ask how any of this works. A real person answers, and if we get something wrong we will say so in public. Last week we caught our own best benchmark result being false and published the finding the same day. That is the standard we hold ourselves to, so you can imagine how we treat your data.
Pre-beta honesty: Tīrtha is a small company. We would rather earn trust slowly with mechanisms you can check than quickly with promises you cannot. · Where your code goes → · Back to overview