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)→
More from Models
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26