Token Audit breaks every LLM API request into question / thinking / reply tokens and shows where your money goes. Reasoning models like o1 burn up to 77% of tokens on hidden thinking — at premium prices. The tool estimates costs across 14 models, fires alerts on wasteful patterns (high reasoning ratio, runaway automation), and its AI Advisor suggests cheaper alternatives. CSV import, spend by model/task, 14-day trend. Runs 100% locally — no sign-up, no API keys.
I was reviewing my team's o1 API bill and noticed something wild — most of the money was going to hidden "thinking" tokens we never even saw. A simple chat was burning 77% of its tokens inside the model's reasoning loop, at 15x the cost of normal output.
So I built Token Audit — it breaks every request into question / thinking / reply tokens, estimates cost across 14 models, and flags wasteful patterns before they become a bill shock.
Runs 100% locally, no sign-up, no API keys. Would love feedback from fellow API spenders!
Report
No reviews yetBe the first to leave a review for Token Audit