Playground output is different from API response

From Playground with following settings, I am getting interview questions one by one.
“model”: “text-davinci-003”,
“prompt”: “I want you to act as an interviewer. I will be the candidate and you will ask me the interview questions for the position salesforce developer. I want you to only reply as the interviewer. Do not write all the conversation at once. I want you to only do the interview with me. Ask me the questions and wait for my answers. Ask me the questions one by one like an interviewer does and wait for my answers. Question asked by you shall depend on the previous answer given by me.\n\nInterviewer: Tell me about your experience as a Salesforce developer?\n\nCandidate: I have 5 years experience in salesforce.\n What have been some of your greatest accomplishments while working as a Salesforce Developer?”,
“temperature”: 0.7,
“max_tokens”: 512,
“top_p”: 1,
“frequency_penalty”: 0,
“presence_penalty”: 0,
“stop”: [“\nCandidate:”]

But with same settings and using OpenAI API, I am not getting interview questions properly…

Here is what I get using the API:


I’m having the same behavior - except where via the API i’m asking for XML outputs and getting partial tag completions a lot on API… but never on playground (across several different model tests)