Hi! I just encounter the problem today when using the Playground:
You requested a model that is not compatible with this engine. Please contact us through our help center at help.openai.com for further questions.
Then I try it again in Python
result = openai.Completion.create(
engine='code-davinci-002',
prompt=prompt,
max_tokens=256,
temperature=0.4,
n=1,
stop='\n\n\n')
And the same problem occurs as “openai.error.InvalidRequestError: You requested a model that is not compatible with this engine. Please contact us through our help center at help.openai.com for further questions.”
May I check whether this is due to some problems on my side about account settings or it’s from the API itself? I just used the Playground yesterday and remember it worked well then so I’m wondering whether I just missed some update on the API usage here.
Thanks for your reply.
I just found that other models can work now in the Playground except for Codex (“code-davinci-002”).
It seems “code-davinci-002” is the only one which still has some problem.
I’m not sure if this is the same problem, but depending on my presets in the Playground, the dropdown menu for the model actually switches to code-davinci-003 (which isn’t openly available AFAIK) and I get an error like yours.
HELP,my problem is
ubuntu@VM-0-6-ubuntu:~$ curl https://api.openai.com/v1/completions
-H"Content-Type:application/json
-H"Authorization: tF -d’
“model”:“text-davinci-003”,
“prompt”:“Correct this to standard English: n\nShe no went to the market.”,“temperature :0,“max_tokens :60,“top_p”:1.0,
“frequency_penalty”: 0.0 presence_penalty”: 0.0}
error":{
message":"You requested a model that is not compatible with this engine. Please contact us through our help center at help.openai.com for furth questions.
“type”: “invalid_request_error”,"param :“model”, code :null}
ubuntu@VM-0-6-ubuntu:~$