#context window
4 articles tagged context window. At twelve articles this topic starts lifting the whole site in search.
Timeline
-
What an AI token is — how much text $10 per million tokens actually buys
-
What AI token pricing is — why output costs about 5× input
-
DeepSeek V4-Pro launches — 1.6 trillion parameters, 49 billion switched on
-
What is a context window — a model does not read all million tokens
All articles
-
Tech · 4 min readWhat an AI token is — how much text $10 per million tokens actually buys
Unit — a token is a word fragment, not a word, and counts differ sharply by language
-
Tech · 5 min readWhat AI token pricing is — why output costs about 5× input
Billing is per token, with separate input and output rates — output typically costs four to five times input
-
Tech · 4 min readDeepSeek V4-Pro launches — 1.6 trillion parameters, 49 billion switched on
V4-Pro-0813: 1.6tn total parameters, 49bn active per token, 1M-token context, 384K max output
-
Tech · 4 min readWhat is a context window — a model does not read all million tokens
Context window = total tokens visible in one request, input and output combined