Exceeding tokens

OKay, so we are mid dev on this app and now running into the dreaded “too many tokens” errors (Claude 3.5, GPT 4 family so far). I’m reading that there is a limit in Bolt, and I know about the limits with the LLMS.

Here’s the error from GPT4.0turbo:

“There was an error processing your request: Custom error: Failed after 3 attempts. Last error: Request too large for gpt-4-turbo-preview in organization (redacted) on tokens per min (TPM): Limit 30000, Requested 144831. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.”

Stuck here. Any ideas? This is not a huge codebase by any means (552,862 bytes in the project folder overall) and connected to a minimal Supabase. Happens when synching a local folder or pulling from Github, after restarts, and after clearing chat histories.

Cheers. I’m going to bed.

Hi @alliemetcalf,
if you use the “main” branch, you can enable “Context Optimization” in Settings, which will drastically reduce token usage.
This should normally help.
Within the stable branch, there is at the moment nothing you can do.

OMFG you are a rockstar. Hopefully I can help you some day, nailed it! THANK YOU!!!

1 Like