Docs

Documentation

Data retention policies

ModelRiver retains request data for observability and debugging. Understand what is stored and how to manage retention.

What is retained

ModelRiver stores the following data for every processed request:

Data typePurposeRetention
Request payloadsDebugging and replayConfigurable
AI responsesObservability and auditingConfigurable
Token usageCost analytics and billingPersistent
Cache fieldsCustomer data echoTied to request
Webhook delivery logsDelivery status tracking30 days
Timeline eventsRequest lifecycle tracingTied to request

Managing retention

  • Per-project purge: Contact support to purge logs for specific projects when policies require it.
  • Custom retention windows: Enterprise plans support custom retention periods.
  • Selective caching: Use cache fields selectively and redact sensitive data before sending to ModelRiver.

Data minimisation

Best practices for minimising data exposure:

  • Avoid logging PII: Strip personally identifiable information from request payloads before sending.
  • Use cache fields selectively: Only cache the business identifiers you need for observability.
  • Redact before sending: Process sensitive content on your side before including it in AI requests.
  • Separate environments: Use distinct projects for development, staging, and production to isolate data.

Deletion requests

To request data deletion:

  1. Email [email protected] with your project name and the scope of deletion
  2. Include specific date ranges or request IDs if applicable
  3. Deletion is processed within 7 business days
  4. You'll receive confirmation once complete

Next steps