The response for the prompt not correct or not relative with my prompt by api call

API
1

I call like:
def translate(text):

model_engine = "text-davinci-003"  

#prompt = (f"please translate to Chinese:\n{text}\n")

print(f"prompt: {text}")
response = openai.Completion.create(
    model=model_engine,
    prompt=text,
    temperature=0.8,
    max_tokens=300,
    #top_p=1,
    frequency_penalty=0,
    presence_penalty=0
)

return response.choices[0].text.strip()

it work fine with my friend’s API_KEY, but the response always not relative with my prompt by API Call.

Can’t figure out how to solve this problem.