Building AI applications has never been easier with the Responses API! Learn how to prompt models using a simple interface, best practices for working with reasoning models, and how to build back-and-forth conversations with LLMs.

The Responses API: a Developer's Best Friend

Your First Responses API Call

Adding Model Instructions

Extracting Information from the Response

Mastering Response Parameters

Experimenting with More Powerful Models

Reasoning About Reasoning

Conversation Chaining

From One Message to Another

Conversation

Enabling Chat Conversations

Getting Started with the Responses API

LLMs are powerful, but they're even more powerful once tools are introduced! Learn how to integrate web search with your LLM systems with no additional API keys or credentials. Discover that tools can be, well... pretty much anything! Build your own tools for LLMs to call to go beyond the model's base capabilities.

Response Items: The Building Blocks

Extracting Output Items and Their Contents

Using Items for Custom Handling

Web Search That Just Works

Combining LLMs and Web Search

Building Confidence with LLM Sources

Function-Calling Tools: Defining the Function

The Function-Calling Tool Workflow

Defining a Function for Converting Timezones

Function-Calling Tools: The Full Workflow

Building the OpenAI Tool Definition

Integrating Function-Calling Tools

Building Tools for LLMs

Move your LLM systems from proof-of-concept to production with three key design paradigms. Learn how to generate consistent and reliable structured outputs, like JSON, using LLMs. You'll also use semantic events to stream updates to your users, creating interactive and enjoyable experiences. Finally, go multi-modal and learn how to combine text and images with OpenAI's GPT-5 models.

Generating Structured Outputs

Consistent Outputs, Every Time!

Nesting Pydantic Classes

Streaming with Semantic Events

Streaming OpenAI Responses

Streaming Semantic Events

Streaming with Function Calls

Input Flexibility and Multimodality

Role-Based Inputs

Prompting with Images from URLs

Prompting with Local Image Files

Congratulations!

Advanced Patterns for Production

Building AI applications has never been more accessible with the Responses API! In this course, you’ll learn how to prompt models through a simple interface, follow best practices for reasoning models, and design natural back-and-forth conversations with LLMs. You’ll unlock the full power of LLMs by integrating tools&mdash;like web search with no extra API keys or credentials&mdash;and by building your own to extend model capabilities beyond their base knowledge. You’ll also learn how to take your applications from prototype to production with three key design paradigms, generate reliable structured outputs like JSON, stream real-time semantic events for interactive user experiences, and go multi-modal by combining text and images using OpenAI’s GPT-5 models.

Working with the OpenAI API

Build smart, interactive, and reliable AI applications easier than ever before with the OpenAI Responses API and GPT-5.

Working with the OpenAI Responses API

sys_prompt = "..."
latest_response_id = None 

while True:

user_input = input("You: ").strip()
if user_input.lower() == "exit":
    break

response = client.responses.create(
    model="gpt-5-mini",
    instructions=sys_prompt,
    input=user_input,
    previous_response_id=latest_response_id
)

print(f"\nAssistant: {response.output_text}\n")
latest_response_id = response.id

Enabling Chat Conversations

Working with the OpenAI Responses API

Hands-on interactive exercise