$/token is meaningless; use $/attempt for cost evaluation
srchvrs · x · 2026-08-27
The author argues that $/token is an arbitrary metric for internalizing costs, highlighting that models like Opus 5 can use five times more tokens than GPT 5.6 Sol for similar tasks. Due to varying caching strategies and prices, $/attempt is proposed as a much more meaningful metric for evaluating costs.
More from Models
- Meta officially launches Muse Spark Open: 816B total, 42B active, 1M context — airesearch12 · 2026-10-16
- OpenAI simplifies API usage tiers into Build/Launch/Grow with automatic upgrades at $5/$100/$500 — prd_008 · 2026-10-16
- Xiaomi's MiMo RL dashboard reveals $3.47M spent on just 30 training steps — bycloud · 2026-10-16
- Analyst: in a year, models 2-3x better across the board at 10x lower cost, token use up 10-20x — DeryaTR_ · 2026-10-16
- Google revamps Gemma docs, site teases Gemma 4 open models — rseroter · 2026-10-16
- Respan's Span-02 brings anytime reasoning: interrupt it mid-thought and still get the best answer — techNmak · 2026-10-16