$ man model-selection

Model Selection

Choosing which AI model to use based on task complexity and cost.

by Shawn Tenam

Opus is smarter but expensive. Sonnet is fast and cheap. For simple tasks (reformatting, scanning), use Sonnet. For complex reasoning (architecting, debugging), use Opus. Wrong model = wasted money or bad output.

The daily tracker logs model usage. Opus sessions cost $12-15. Sonnet sessions cost $3-5. Track your spend. Optimize your model picks. Don't use Opus to count words.