Open in the interactive docs · markdown for agents: https://neuraldeep.tech/docs/privacy.md

Privacy · data storage

By default request and response bodies are not saved: neither in the database nor in file storage. Only metrics remain: model, tokens, status, latency.

• Request history storage (off by default) — a switch in your account, Privacy section. Turn it on and new requests with their bodies appear in the Requests section. Turn it off and new requests stop being saved. Saved bodies are kept for 30 days, then deleted.
• No analytics on texts. No model reads or labels the text of your requests.
• To see that the service works, the on-call engineer sees the last ~1000 requests together with responses. This feed lives in memory for at most 15 minutes and is pushed out by new requests; it is never written to disk.

We don't train on your data and we don't sell it. Metrics (latency, tokens, status) are always collected, without request text.

Reference sections (markdown for agents)

• Start · key, errors, quotas
• Text · chat
• Vectorization
• Reranking
• Transcription
• Image recognition
• Structured output
• Clients · agents
• Remaining limits · Limits API
• Search · Search API
• OCR · documents
• Images · Image API
• Music · Music API
• PII anonymization · PII Guard
• SpeechCore · STT
• Speech synthesis · TTS API
• Who spoke when · diarization
• Text decisions · FRIDA-Decisions, clef-flash
• Drift · overview
• Files + sandbox preview
• Your own tools, skills, MCP
• Tasks · proactive
• Memory · memory
• Isolation and security
• Agent settings
• Limits · errors
• Book · search and MCP
• Streaming
• SDK · Python / JS
• Privacy