Hello there, running the bamlcode repo with the BrainOpenAI client, and I keep running into rate limit issues with OpenAI. What's the remedy here? https://cdn.discordapp.com/attachments/1532470005562868005/1532470005961330831/image.png?ex=6a6cf769&is=6a6ba5e9&hm=1911f6fb99f17318608c9e179a3f1da25ffd0ceacaa02915adbf6bfc1a0c8d4c&

i think openai has some system where you get higher rate limits the more you spend

It does seem like the requests are finishing faster than Sonnet - Could also be too fast.

They also want to get people off the old models, so I would expect 4o to have more painful limits than say 5.6 terra

Pretty sure I ran into the same problem with 5, but I will redo setup and try again

Oh, I expect both the 5* models and the old models to have rate limits, I just expect the 4o rate limit to hurt more