[pkaye]

Above 200k token context they charge a premium. I think its $10/M tokens of input.

[_ink_]

Interesting. Is it because they can or is it really more expensive for them to process bigger context?

[cube2222]

Attention is, at its core, quadratic wrt context length. So I'd believe that to be the case, yeah.

[pkaye]

I've read that compute costs for LLMs go up O(n^2) with context window size. But I think it is also a combination of limited compute availability, users preference for Anthropic models and Anthropic planning to go IPO.