Using at Scale (1M+ rows in DB)
This document is a guide for using LiteLLM Proxy once you have crossed 1M+ rows in the LiteLLM Spend Logs Database.
Why is UI Usage Tracking disabled?​
- Heavy database queries on
LiteLLM_Spend_Logs(once it has 1M+ rows) can slow down your LLM API requests. We do not want this happening
Solutions for Usage Tracking​
Step 1. Export Logs to Cloud Storage
Step 2. Analyze Data
- Use tools like Redash, Databricks, Snowflake to analyze exported logs
[Optional] Step 3. Disable Spend + Error Logs to LiteLLM DB
Disabling this will prevent your LiteLLM DB from growing in size, which will help with performance (prevent health checks from failing).
Need an Integration? Get in Touch​
- Request a logging integration on Github Issues
- Get in touch with LiteLLM Founders
- Get a 7-day free trial of LiteLLM here