The Responses API: a Developer's Best Friend

Working with the OpenAI Responses API

James Chapman

AI Curriculum Manager, DataCamp

OpenAI and the Start of the Generative AI Race

¹ Credit: portkey.ai (as of January, 2025)

OpenAI's API Evolution

Responses API x Developers

Simple, developer-friendly interface

¹ Image Credit: helicone.ai

Our First Responses API Request

from openai import OpenAI

client = OpenAI(api_key="...")


response = client.responses.create(

    model="gpt-5-mini",

    reasoning={"effort": "minimal"},
    max_output_tokens=60,

    instructions="Be concise.",
    input="Explain LLMs to a 6yr old."

)

Client: Configure environment to communicate with the API
API key is not required 🎉
Reduce reasoning "effort" and max_output_tokens for faster responses
instructions → clear requirements on how to behave
input → the task or question at-hand
instructions > input

print(responses.output_text)

Imagine a very smart pretend friend...

print(responses.usage.output_tokens)

print(responses.id)

resp_0776f5d708d30043006917035...

response.output

[ResponseReasoningItem(
     id='...',
     summary=[],
     type='reasoning',
     content=None,
     encrypted_content=None,
     status=None),
 ResponseOutputMessage(
     id='...',
     content=ResponseOutputText(text='Imagi...'
         type='output_text', logprobs=[])],
     role='assistant',
     status='incomplete',
     type='message')]

Let's practice!

Working with the OpenAI Responses API