Know a great AI tool or AI news source? Submit it to AiByts
Stackness10 min read

Run your own LLM proxy to track token usage: LiteLLM in front of Claude Code and Codex

A local LiteLLM proxy logs one row per agent request with tokens, cost, key and session. Setup in about 15 minutes, tested on LiteLLM 1.106.0, October 2026.

By Sergei GordeichukStackness Blog
Run your own LLM proxy to track token usage: LiteLLM in front of Claude Code and Codex

Read the full story

Originally published by Stackness Blog on Oct 19, 2026.

Read on Stackness Blog(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.