Experimenting with More Powerful Models
Let's experiment with some of the different LLMs that OpenAI has to offer. All of these models have reasoning capabilities, but to make the differences between the base models clearer, keep the reasoning effort to 'minimal'.
In this exercise, you can enter any prompts you wish, but try to use the same one in each step to make a clearer comparison! If you're struggling for ideas, you can use the one provided.
This exercise is part of the course
Working with the OpenAI Responses API
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Prompt gpt-5-nano with minimal reasoning
response = client.responses.create(
____="____",
input='Write the same sentence in three tones: professional, sarcastic, and poetic. The sentence is: "The meeting could have been an email."',
reasoning={"effort": "minimal"}
)
print(response.output_text)