Error: you requested 7409 tokens (1345 in the messages, 64 in the functions, and "6000" in the completion)

That might cause the error.

Hiragana: Unicode: 3040-309F
Katakana: Unicode: 30A0–30FF

I mean, I saw something alike in chinese translation responses. I guess GPT-3 can’t identify words in japanese, or at least not reliable enough.

And cause of that max_tokens is taken.

You’ve put a 4k limit and the answer is transscripted to unicode?

@logankilpatrick ?