AIQB
TutorialsOrdinary

This LLM cost function looks right. Can you spot the bug?

Source: DEV Community·

Summary

OpenAI counts reasoning tokens inside output_tokens, and Gemini counts thinking tokens separately. A short puzzle, the answer, and code you can run.
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-94733ada97854e365f7d41ff