Hello everyone,
I’m experiencing an issue with the ChatGPT API where I receive the following error in response to my requests:
• Response Message: “You exceeded your current quota…”
• Response Code: rate_limit_exceeded
A few details about my account setup:
• Account Tier: 5
• Monthly Budget Limit: $1500
• GPT Models: gpt-4o + Audio Model + RealTime
Given my current tier and budget, I’m unsure why I’m hitting this rate limit. I’ve checked my usage and it doesn’t seem to align with the limit warnings. Is there a way to verify which specific quota I’m exceeding? Also, are there any suggestions on how to adjust or optimize my API requests to avoid this issue?
Thanks in advance for any insights or advice!
1 Like
Hi and welcome to the developer forum,
The only thing I can think you might be running into is the 2M tokens per min limit of the realtime preview endpoint.
Is that likley to happen given your current testing setup?
I see 32k unCached and half a mill ish Cashed, wondering if your numbers get close to the 2M per min limit.
If you are confident you are not going anywhere near the 2M per min limit please let me know.
3 Likes
I’m not quite sure that I am running into some limitations. but on the other hand I can not see anything related in the “Usage” section of my account.
you mentioned may I am exceeding 2M tokens per minute while the above chart time frame is hourly.
the maximum number shows around 753K tokens usage in all models per one hour.
+I am getting this error in all API requests related to “Chat” with the models, even in the v1/chat/completions endpoint.
