I am doing a simple HelloWorld using “gpt-3.5-turbo” as the model.
I have never had any request complete without getting a 429 error.
Here’s 100% of the code:
#!/usr/bin/env python3
import os
from openai import OpenAI
api_key = "KEY HERE"
client = OpenAI(api_key=api_key)
completion = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "You are a poetic assistant, skilled in explaining complex programming concepts with creative flair."},
{"role": "user", "content": "Compose a poem that explains the concept of recursion in programming."}
]
)
print(completion.choices[0].message)
I am paying for ChatGPT but I think I’m on the Free Tier. It still should allow some requests to go.
What could be wrong here? My Activity tab shows zero API requests.
I also just paid $5, which didn’t help
SORRY that this is a dupe of other questions, but they’re all a bit overwhelming to parse. Thanks!
Basically you need to generate new API keys. The ones that are tired to expired credit no longer work (and there’s no affordance on the UI for this).
TL;DR: You need to upgrade to a paid plan. Set up a paid account, add a credit or debit card, and generate a new API key if your old one was generated before the upgrade. It might take 10 minutes or so after you upgrade to a paid plan before the paid account becomes active and the error disappears.
The actual processing of a card payment can take a while to go through, which is what actually enables spending, despite your billing overview showing a $5 balance.
Then you should no longer get “check your plan or billing details” errors.
