How can you have a rate limit error, when you've never made a successful API call? (Paid plan AND API credits!)

API
1

I used the default ChatGPT API test script and got the error below…

RateLimitError: You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.

I tried a friend’s API key and it works fine. If anyone could advise why my API keys (I’ve tried making 5 different keys) do not work and how to resolve, I’d appreciate!

Strangest thing is that I’ve never made a successful API call, and have a paid account, yet am somehow considered over the limit.

2

Welcome to the community!

You need to deposit at least $5 in your account.

3

I’ve had $10 in my account since I set it up. :pensive:

4

Experiencing the same issue here. Topped up $25, updated API keys, explicitly allowed the GPT models I want to use, and I’m still being told that I’m “exceeding the current quota”. This is despite there being absolutely no usage showing on the dashboard.

The request I’m sending to initialise the call is extremely simple:
{
“model”: “gpt-3.5-turbo”,
“prompt”: “Summarize this simple text.”,
“temperature”: 0.7,
“max_tokens”: 50
}

So looks like an error on OpenAI’s end - hope it’s fixed soon!