> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Data privacy and security

> Control what Toqan Router stores from traces, how long observability data is kept, and which compliance, secret and access controls apply to a workspace.

**AI Observability** stores traces, spans and logs so they can be debugged, evaluated and reviewed. The pages below cover keeping sensitive content out of stored traces, how long observability data is kept, and the compliance, residency and access controls that apply.

## What is stored and for how long

**Toqan Router** keeps each trace for the retention period of the subscription plan: 14 days on Free, 30 days on Pay as you go, and a custom period up to 365 days on Enterprise plans. Data retention lists what automatic deletion removes and what stays until deleted manually.

Spans store the model output, reasoning text included: the thinking blocks and summaries a model returns, plus reasoning token counts. Reasoning expires with the trace it belongs to, and output masking blanks the reasoning text stored with the response. [What each value masks](/docs/ai-gateway/features/security.md#what-each-value-masks) covers the rest.

## Keep sensitive content out of stored traces

> [card] [Trace Scrubbing](/docs/ai-gateway/features/plugins/trace-scrubbing.md)
>
> Mask selected fields in stored traces using the `trace_scrubbing` plugin.

> [card] [Trace Data Masking](/docs/ai-gateway/features/security.md)
>
> Control which request and response content is written to stored traces, without changing live output.

> [card] [PII Redaction](/docs/ai-gateway/features/plugins/pii-redaction.md)
>
> Redact personally identifiable information before requests reach the provider, then restore values in the response.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.