Vibeleaderboard
← All Intel
Intel / article

llm-gemini 0.38.1

Source
simonwillison.net
Date
Why it matters

Shows that Gemini 4 Hydrogen at xhigh uses about six times the output and cost of high (31,477 vs 5,311 tokens, 23.61 vs 3.99 cents), so reasoning level choice matters for budgets.

Terms in this piece · Glossary
  • Large language model — A model trained on large amounts of data to process and generate language.
  • Token — A piece of text, such as a word, part of a word or a punctuation mark, that a language model represents as numbers and handles as a unit.
Read the source simonwillison.net
Recommended reads
Comments

Checking sign-in…

Loading comments…