Hello, I am currently using the Claude 3 model.
Claude3’s max token is 4096 tokens.
In other words, Claude 3 can produce a maximum length of 4096 tokens when outputting once.
I asked Claude3 to translate a huge amount of documents, but because Claude3’s max token is 4096, the model is not outputting the entire length.
How can I continue to receive answers after Max Token?