LiteLLM adds a tab that shows AI cost savings

LiteLLM’s Cost Savings tab shows how much usage and spending its cost controls have reduced. It reports the tokens and money saved through , which makes AI inputs shorter.

It also tracks savings from , where a cache hit avoids processing a repeated prompt again. Teams can compare the contribution of both methods over time, and a short Loom demonstration and related are available.

Key points

  • The new tab separates savings by cost method.
  • savings include reductions in token use and cost.
  • savings come from avoiding repeated processing after a cache hit.
  • The dashboard shows how the value of each method changes over time.
Read original