For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Trust CenterStatusSupportGet a demoPlatform
DocumentationEvals API ReferenceIntegrations & OTELPlatform SettingsSelf-HostingChangelog
DocumentationEvals API ReferenceIntegrations & OTELPlatform SettingsSelf-HostingChangelog
    • Platform Settings
    • Data Residency
    • RBAC
  • Project Settings
    • API Keys
    • Team Members
    • Roles & Permissions
    • Transformers
    • Integrations
    • Alerts
    • AI Connections
    • Model Costs
    • Data Usage
    • Evaluation Models
    • Evaluation Rules
    • Annotation Options
    • Classifiers
    • Data Sources
    • Data Retention
    • Audit Logs
  • Organization Settings
    • Projects
    • Users
    • Roles & Permissions
    • Model Credentials
    • SSO
    • Data Retention
    • Audit Logs
    • Feature Access
LogoLogo
Trust CenterStatusSupportGet a demoPlatform
On this page
  • Inherit from Organization
  • Retention Categories
  • Setting a Retention Period
  • How Deletion Works
Project Settings

Data Retention

Configure data retention policies to manage how long your project data is stored.
Was this page helpful?
Previous

Audit Logs

View a log of all actions performed in your project.
Next
Built with

Data retention policies let you control how long different types of data are stored in your project before being automatically deleted.

Data Retention

Inherit from Organization

Each project can optionally inherit its retention policies from the organization. When enabled, the project uses the organization-level retention settings and individual controls are disabled. Toggle Inherit from organization off to configure project-specific retention periods.

Retention Categories

You can set a separate retention period for each of the following data types:

Data TypeWhat Gets Deleted
Traces & SpansTraces and spans older than the retention period are permanently deleted. Shorter retention reduces storage costs.
Test RunsTest runs past the retention period are removed along with their test cases and metrics.
DatasetsInactive datasets with no activity beyond the retention period are permanently deleted.
PromptsInactive prompts with no activity beyond the retention period are permanently deleted.

Setting a Retention Period

For each data type, choose one of:

  • Forever — Data is never automatically deleted.
  • Days — Enter a number of days (e.g., 30).
  • Months — Enter a number of months (e.g., 6).
  • Years — Enter a number of years (e.g., 2).

You select one unit per data type — these are not combined. For example, you set traces & spans to “2 Years”, not “2 Years and 30 Days”.

To configure retention:

  1. Navigate to Project Settings → Data Usage → Retention tab
  2. Optionally toggle off Inherit from organization to set project-specific policies
  3. For each data type, select the unit (Forever, Days, Months, or Years) and enter a duration
  4. Click Save

Retention cleanup happens daily at midnight UTC. Changing retention settings will not trigger an immediate deletion — stale data will be removed during the next cleanup cycle.

How Deletion Works

When data is deleted, any child data associated with it gets deleted too. Here’s how the hierarchy works:

  • Test Runs — Deleting a test run also removes its associated metrics, test cases, traces, spans, and threads.
  • Threads — Deleting a thread removes all traces, spans, and metrics within it.
  • Traces — Deleting a trace removes its spans and metrics, but leaves the parent thread intact.

For example, if you set your trace & span retention to 14 days, any traces older than 14 days will be deleted along with all their associated spans and metrics.