# Is it me or everyone else? GPT api doesn't work any more
**URL:** https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220
**Category:** API
**Created:** [November 11, 2023, 2:46am UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220 "2023-11-11T02:46:30Z")
**Posts on this page:** 14
**Page:** 1
### Author:  [@will007](https://community.openai.com/u/will007)
#### Post date: [November 11, 2023, 2:46am UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/1 "2023-11-11T02:46:30Z")
it always gives me this, and I follow the document it still doesn’t work.
APIRemovedInV1:
You tried to access openai.Completion, but this is no longer supported in openai\>=1.0.0 - see the README at [GitHub - openai/openai-python: The official Python library for the OpenAI API](https://github.com/openai/openai-python) for the API.
You can run `openai migrate` to automatically upgrade your codebase to use the 1.0.0 interface.
Alternatively, you can pin your installation to the old version, e.g. `pip install openai==0.28`
A detailed migration guide is available here: [v1.0.0 Migration Guide · openai/openai-python · Discussion #742 · GitHub](https://github.com/openai/openai-python/discussions/742)
---
### Author:  [@g11920.keshan](https://community.openai.com/u/g11920.keshan)
#### Post date: [November 11, 2023, 7:42am UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/2 "2023-11-11T07:42:11Z")
Same here, lloking for a solution ASAP
---
### Author:  [@koshilasandaru](https://community.openai.com/u/koshilasandaru)
#### Post date: [November 13, 2023, 6:27am UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/3 "2023-11-13T06:27:20Z")
Same over here its working locally but after creating the docker image this error occurs, is there a solution yet?
---
### Author:  [@pq8tmhx6k6](https://community.openai.com/u/pq8tmhx6k6)
#### Post date: [November 13, 2023, 3:00pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/4 "2023-11-13T15:00:42Z")
I have the same error… found an answer yet?
---
### Author:  [@will007](https://community.openai.com/u/will007)
#### Post date: [November 13, 2023, 10:34pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/5 "2023-11-13T22:34:56Z")
do this guys, you need to strictly follow the guide [GitHub - openai/openai-python: The official Python library for the OpenAI API](https://github.com/openai/openai-python)
[v1.0.0 Migration Guide · openai/openai-python · Discussion #742 · GitHub](https://github.com/openai/openai-python/discussions/742)
---
### Author:  [@atebst1](https://community.openai.com/u/atebst1)
#### Post date: [November 19, 2023, 5:49pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/6 "2023-11-19T17:49:24Z")
hi, i have it set as an env var for my app and still getting this error.
---
### Author:  [@\_j](https://community.openai.com/u/_j)
#### Post date: [November 19, 2023, 6:09pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/7 "2023-11-19T18:09:25Z")
```python
'''example completion with openai > 1.1'''
from openai import OpenAI
client = OpenAI()
prompt = "True or false: a banana is smaller than a lemon.\n\n"
response = client.completions.create(
prompt=prompt,
model="gpt-3.5-turbo-instruct",
top_p=0.5, max_tokens=50,
stream=True)
for part in response:
print(part.choices[0].text or "")
```
> False
---
### Author:  [@atebst1](https://community.openai.com/u/atebst1)
#### Post date: [November 19, 2023, 7:21pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/8 "2023-11-19T19:21:26Z")
It worked for me, thanks. Wasn’t referencing the message object under response
---
### Author:  [@paulkiragu621](https://community.openai.com/u/paulkiragu621)
#### Post date: [November 20, 2023, 8:40pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/9 "2023-11-20T20:40:24Z")
You can alternatively run
`openai migrate`
This will automatically update all your existing old code.
---
### Author:  [@munashemuchinako741](https://community.openai.com/u/munashemuchinako741)
#### Post date: [December 20, 2023, 8:56am UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/10 "2023-12-20T08:56:12Z")
i am still having the same issue here , please assist me on how i should get rid of it, which file should i edit to troubleshoot this problem?
---
### Author:  [@EricGT](https://community.openai.com/u/EricGT)
#### Post date: [December 20, 2023, 2:29pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/11 "2023-12-20T14:29:42Z")
@will007
As this topic has a selected [solution](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220), can it be closed?
---
### Author:  [@dilwolf](https://community.openai.com/u/dilwolf)
#### Post date: [December 21, 2023, 5:50am UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/12 "2023-12-21T05:50:24Z")
It worked for me. I had problems with using " \* `openai.Completion.create()` → `client.completions.create()`"
Thanks
---
### Author:  [@\_j](https://community.openai.com/u/_j)
#### Post date: [December 21, 2023, 6:16am UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/13 "2023-12-21T06:16:30Z")
That’s great to hear! The code snippet above, mind you, is for `gpt-3.5-turbo-instruct`, a special “completion” model that operates a bit differently than the “chat” you may be expecting.
Here’s getting a response from the chat `gpt-3.5-turbo` AI with the latest Python openai library:
```auto
from openai import OpenAI
client = OpenAI()
system = [{"role": "system", "content": "You are HappyBot."}]
chat_history = [] # past user and assistant turns for AI memory
user = [{"role": "user", "content": "Are you fully operational?"}]
chat_completion = client.chat.completions.create(
messages = system + chat_history + user,
model="gpt-3.5-turbo",
max_tokens=25, top_p=0.9,
)
print(chat_completion.choices[0].message.content)
```
---
### Author:  [@EricGT](https://community.openai.com/u/EricGT)
#### Post date: [January 29, 2024, 4:07pm UTC](https://community.openai.com/t/is-it-me-or-everyone-else-gpt-api-doesnt-work-any-more/494220/14 "2024-01-29T16:07:16Z")