Last updated: August 2026

Zero prompt retention by Lithune: prompt and completion content is processed in memory, is not written to Lithune's persistent storage and is never used for training.

Inference flow

Requests may reach Lithune through OpenRouter and Cloudflare. Once received by Lithune, the request is sent only to the model running on Lithune-owned hardware in Türkiye. Lithune does not forward prompt content to an external model API, cloud GPU or model-training provider.

Training policy

Retention schedule

DataStored by Lithune?RetentionPurpose
Prompt content and attachmentsNo persistent storageIn-memory processing onlyGenerate the requested response
Completion contentNo persistent storageIn-memory processing onlyDeliver the response
Per-request token counts and timestampYesMost recent 200 records across the service and no more than 30 days, whichever limit is reached firstOperations and troubleshooting
Aggregate request and token totals per API credentialYesUntil the corresponding API-key record is manually deletedUsage accounting and capacity planning
API credential used for the requestYesFor the same period as the associated request record or aggregateAssociate usage with an authorised credential
Public website and API access logsNoDisabled
Nginx technical error logOnly when errors occurDaily rotation; up to 14 rotations normally retainedFailure diagnosis and security

Infrastructure and other providers

Security controls

Controls include TLS in transit, restricted infrastructure access, API authentication, request limiting, short-lived operational logs and separation between public routing and the private model process. Security practices are reviewed as the service changes.

More information

This technical policy supplements the Privacy Notice. Data-related requests can currently be submitted through the official Lithune OpenRouter profile.