Discussion: Tokens Are the Wrong Unit to Measure LLM Costs

willccbb · x · 2026-07-19

The author points out that while it's inaccurate to simply claim "smaller models are better," large models like GPT-4.5 and Llama-405B are actually less efficient than smaller versions within their respective series.

They emphasize that cost is a key factor when evaluating models, and the industry's current standard of pricing by token is flawed. This approach fails to offer a fair and intuitive apples-to-apples comparison of actual efficiency across models with varying parameter sizes.

Related event: Evaluating Token as a Flawed Metric for LLM Costs(2 posts)→

Original post →

More from Models

Models channel →