18:13
2026-05-28
dev.to
large-language-models
Feeding Raw HTML to Your LLM Is a Token Tax. I Measured It on 10 Real Pages — Median 7.4 , and It Hits Every Scheduled Run
A developer measured the token cost of feeding raw HTML versus extracted text to large language models across 10 real web pages, finding a median token multiplier of 7.4×. The spread ranged from 1.1× …