Skip to main content

Privacy and Security

Prompt plaintext is not persisted during normal routing. Semantic caching is disabled for the first launch. If it is explicitly enabled for eligible Growth+ requests, prompts are sent to OpenAI for embeddings; hashes and unencrypted embeddings are retained and cached responses are encrypted per-customer. Retention is enforced and there is no separate opt-out for that enabled processing path.

Requests still leave Makas for your selected upstream provider; that provider's policies and your agreement apply. Treat prompts and model output according to your own data policy.

API keys belong on the server. The service credential is removed before upstream forwarding, provider credentials use native headers, and diagnostic paths redact sensitive values. Management access remains customer-scoped. Accounts in EU and US are independent; selecting a region in these docs does not move accounts or data.

Semantic caching is disabled for the first launch. Founding does not include semantic caching. The exact-request cache is a separate in-memory optimization for eligible identical requests; its eligibility depends on request shape and provider cache directives. Do not rely on a cache hit for correctness or assume every request is cached.

There is no customer Settings → Caching control. These docs do not promise a cache-hit response header.

See caching and the conditional response headers.