The main and best model according to many is Claude 3.5. But it provides maximum of 200k [1]. While I understand cost effectiveness and other limitations with embeddings. But maximum context of just 5% is probably too low with any standard.

[1] https://support.anthropic.com/en/articles/7996856-what-is-th...

You have to switch to long context chat to get the full 200k (I don’t think this works for Composer though).