How to check the validity of the OpenAI key from python?

Question

https://pypi.org/project/openai/

"The library needs to be configured with your account's secret key which is available on the website. [...] Set it as the OPENAI_API_KEY environment variable"

When I ask Chat GPT to complete a message

import openai
response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "What are the trade-offs around deadwood in forests?"}]
)
print(response)

I get a RateLimitError: You exceeded your current quota, please check your plan and billing details.

Is there a python method to check that the key is valid?

In [35]: openai.api_key
Out[35]: 'sk-...'

The issue is that ChatGPT API is not included inside ChatGPT Plus: "Please note that the ChatGPT API is not included in the ChatGPT Plus subscription and are billed separately. The API has its own [pricing](https://openai.com/pricing) [...]. The ChatGPT Plus subscription covers usage on chat.openai.com only and costs $20/month." https://help.openai.com/en/articles/7039783-how-can-i-access-the-chatgpt-api — Paul Rougieux, Jun 21 '23 at 12:32

score 0 · Answer 1 · answered Jun 21 '23 at 11:32

0

To check if your OpenAI API key is valid, you can try making a test API call and see if it works without any errors. Here's a simple code example:

import openai

openai.api_key = 'YOUR_API_KEY'

def is_api_key_valid():
    try:
        response = openai.Completion.create(
            engine="davinci",
            prompt="This is a test.",
            max_tokens=5
        )
    except:
        return False
    else:
        return True

# Check the validity of the API key
api_key_valid = is_api_key_valid()
print("API key is valid:", api_key_valid)

Replace 'YOUR_API_KEY' with your actual OpenAI API key. The is_api_key_valid function attempts a simple test API call. If the call succeeds without any errors, it means your API key is valid, and the function returns True. However, if any error occurs during the API call, it means the key is likely invalid, and the function returns False.

By running the code and checking the value of api_key_valid, you can determine if your OpenAI API key is valid.

answered Jun 21 '23 at 11:32

Facundo Goiriz

1
1

Thanks. `response = openai.Completion.create(engine="davinci", prompt="Test")` returns `RateLimitError: You exceeded your current quota, please check your plan and billing details.`. – Paul Rougieux Jun 21 '23 at 12:35
You probably need to buy OpenAI Tokens to use the API, but that error message means that your API key is valid after all – Facundo Goiriz Jun 21 '23 at 12:50
Did you generate this answer using an ai like ChatGPT? – 0stone0 Jun 21 '23 at 13:03
No, I work building things with OpenAI, I have my own set of openai_utilts.py – Facundo Goiriz Jun 21 '23 at 13:27

Wolfgang Fahl · Answer 2 · 2023-06-29T12:35:27.117

The two ways via curl and python below both work to theck the API.

./testopenai

testopenai

#!/bin/bash
# WF 2023-06-21
if [ "$OPENAI_API_KEY" == "" ]
then
  echo "OPENAI_API_KEY env variable needs to be set to a key see https://platform.openai.com/account/api-keys"
  echo "export OPENAI_API_KEY="
  exit 1
fi
if [ "$OPENAI_API_ORG" == "" ]
then
  echo "OPENAI_API_ORG env variable needs to be set  see https://platform.openai.com/account/org-settings"
  echo "export OPENAI_API_ORG="
  exit 1
fi

#
# test via curl
#
viacurl() {
    curl https://api.openai.com/v1/completions \
      -H 'Content-Type: application/json' \
      -H "Authorization: Bearer [$OPENAI_API_KEY]" \
    -H "OpenAI-Organization: $OPENAI_API_ORG" \
      -d '{
      "model": "text-davinci-003",
      "prompt": "Hello World?",
      "max_tokens": 4000,
      "temperature": 1.0
    }' \
    --insecure
}

#
# test via python
#
viapython() {
  code="/tmp/testopenai.py"
cat << EOF > $code
import os
import openai
# https://platform.openai.com/docs/api-reference/authentication
openai.api_key = os.getenv('OPENAI_API_KEY')
openai.organization = os.getenv('OPENAI_ORG')

# list models
models = openai.Model.list()

# print the first model's id
print(models.data[0].id)

# create a chat completion
chat_completion = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])

# print the chat completion
print(chat_completion.choices[0].message.content)
EOF
python $code
}

viacurl
viapython

The issue above was created by me when i still got openai.error.AuthenticationError: Incorrect API key provided: cmdftp@e******.com. You can find your API key at https://platform.openai.com/account/api-keys. Due to a .netrc file — Wolfgang Fahl, Jun 29 '23 at 12:36

How to check the validity of the OpenAI key from python?

2 Answers2