Does anyone have solution for token per minute problem when running Chat GPT via the Open AI Key? Already upgraded from tier 1 to tier 2 in Open AI to increase the limit but this didn’t solve it.
I think you need to be at tier 4
👋 Hey there! Our support team has got your message - we'll be back in touch within 24 hours (often sooner!). If you haven't already, please include the URL of your table in this thread so that we can help you as quickly as possible!
Hey there, thanks for reaching out - it looks like you hit the daily rate limits associated to your personal OpenAI api key here: https://downloads.intercomcdn.com/i/o/w28k1kwz/1231837649/7eb5dc2fdf0ea13f2fc30afdd3f0/CleanShot+2024-10-28+at+15_52_41%402x.png?expires=1730147400&signature=02c3705f67ad07680e9164245f382a0e74f69c93fedb03347be677ac1c1812a4&req=dSIkF8F9modbUPMW1HO4zbPAhGmuxu2M9YrBtqex%2BKjHaVAf3DKZANONJjSu%0AWI5V%0A We now require 30,000 TPM (tokens per minute) for ChatGPT columns and 450,000 TPM for Claygent. You can check your ChatGPT usage or limits at the following links: • Usage • Limits • Usage Tiers Their support team will always grant you the request if you have prepaid the minimum amount required and they’ll be quick to assist if you need to increase your limits or troubleshoot any issues.
That's right! The limit is 450,000 tokens per minute, but you had used 446,852 tokens here and attempted to process an additional 25,196 tokens, causing the request to be denied. I suggest re-running all rows which have caused errors as follows: https://downloads.intercomcdn.com/i/o/w28k1kwz/1232761997/7631d08d8fbdd20d06c8072f324d/CleanShot+2024-10-29+at+10_51_23%402x.png?expires=1730214900&signature=46dea7d612c310ba6b351d25332d01b9823b2198d23362375db7eb02a7f9dbc5&req=dSIkFM54nIhWXvMW1HO4zQkyqYSJgRRKm4pfIzigg6bT40ezFEClmlh4aIrb%0Ax%2FV6%0A I hope this was helpful. If there's anything else I can assist you with, please let me know!
That’s what I’m currently doing but the same error keeps happening. Only 5-10% run successfully and the rest has an error. So this is quite a manual process to get though all rows. Any other solutions to this?
This issue is related to the rate limits on your API keys, so there's not much our team can do on our end. However, you could try running the column using Clay’s shared API key as a workaround. I hope this was helpful. If there's anything else I can assist you with, please let me know!
Is there an option to batch the request in to smaller batches that automatically run sequentially one after the other? That could be solution in Clay directly
There isn’t currently an option to batch requests into smaller, automatically sequential batches in Clay directly. Let me know if there’s anything else you’d like help with!