Tagged
#context-window
4 articles
models
The cost of a token: how model pricing works
"Model bills are measured in tokens, not words or requests. Understanding what a token is, and which ones you pay for, is how you keep costs predictable."
#tokens#pricing#cost-management
06-12 15:45·7 min read
research
Why context length is hard to scale
A longer context window sounds like a simple knob to turn. Underneath it fights a cost that grows faster than the text — and attention that spreads thin.
#context-window#attention#scaling
06-08 18:48·7 min read
models
Context windows explained: tokens, attention, and where long context breaks
A bigger context window is not the same as better memory. Here is what a context window really is, why long inputs degrade, and how to design around it.
#context-window#tokens#attention
06-02 10:06·7 min read
models
Tokens and tokenization: why models see text strangely
Models don't read letters or words — they read tokens. Understanding that one fact explains spelling slips, odd costs, and why context limits work as they do.
#tokens#tokenization#context-window
05-14 16:37·7 min read