Paste your code. See where the money goes.

CostPilot finds the LLM calls in your code, prices them against public rate cards, and shows what a conservative model downgrade would save. It never modifies your code.

1Paste Python code→ 2Click Analyze→ 3Read the cost report

scan only: no LLM calls, no git operations, nothing is stored

expected saving per 1K calls

beforeafter

Call sites

Line	Model	Source	Per call	Suggestion	Decision