AI Request Logs

AI request logs capture every AI request processed through the Cencori gateway. Each log entry includes the full request and response details — model, tokens, cost, latency, provider, status, and security metadata.

[!NOTE] This page covers AI request/response logs (what your users sent and received). For organization-level change tracking (who modified settings, keys, or rules), see Audit Logs.

What Gets Logged

Request Information

• Prompt text and messages
• Model and parameters (temperature, max_tokens)
• API key used
• User/session identifier
• Timestamp (millisecond precision)
• IP address and geolocation

Response Information

• AI-generated content
• Token usage (input/output/total)
• Cost calculation (provider cost and Cencori charge)
• Latency metrics
• Provider used (including failover details)
• Status code (success/error)

Security Metadata

• PII detection results
• Content filter flags
• Prompt injection score
• Security incidents linked

Viewing Logs in the Dashboard

1. Navigate to your project in the dashboard
2. Click Logs in the sidebar
3. Use filters to narrow results:
   • Date range
   • Model
   • Status (success/error)
   • API key
   • Cost range
4. Click any log entry to view full details

Searching Logs

Search through logs using full-text search to:

• Find specific keywords in prompts
• Identify all requests from a specific user
• Locate expensive queries (high token usage)
• Debug failed requests by error message

Exporting Logs

Export logs for archival or external analysis:

CSV Export

Download as CSV for Excel or Google Sheets analysis. Includes all fields except full prompt text (for PII protection).

JSON Export

Complete log data including prompts and responses. Useful for data warehouses or custom analysis.

Log Retention

Retention periods vary based on your plan:

[!NOTE] After the retention period, logs are permanently deleted. Export important logs before they expire.

Best Practices

• Export logs monthly for long-term archival
• Use search to identify expensive or slow queries
• Review error logs weekly to catch issues early
• Set up alerts for unusual patterns (cost spikes, error rate increases)
• Document your log retention policy for compliance
• Redact sensitive data before sharing logs with third parties

Related

• Audit Logs — organization-level change tracking (who modified what)
• Observability — metrics, dashboards, and alerting
• Security — PII detection and content filtering