Glossary

Vision capability

The model accepts images alongside text input.

The model accepts images alongside text. Quality varies hugely — text-recognition (OCR) is largely solved across major models; nuanced visual reasoning (charts, diagrams, UI screenshots) is not.

Keyboard shortcuts

?: Show this overlay
/: Focus the first form field
g h: Go to / (home)
g b: Go to /best-llm-for
g c: Go to /cost
g s: Go to /self-hosted
g x: Go to /compliance
Esc: Close any overlay

Inspired by Linear and GitHub conventions. The two-key sequences (g then h) work within ~1 second.