Developer quickstart
Take your first steps with the OpenAI API.
Overview
Developer quickstart
Take your first steps with the OpenAI API.
The OpenAI API provides a simple interface to state-of-the-art AI models for text generation, natural language processing, computer vision, and more. This example generates text output from a prompt, as you might using ChatGPT.
Generate text from a model
JavaScript
const client = new OpenAI();
const response = await client.responses.create({
model: "gpt-4.1",
input: "Write a one-sentence bedtime story about a unicorn."
});
console.log(response.output_text);
Python
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-4.1",
input="Write a one-sentence bedtime story about a unicorn."
)
print(response.output_text)
cURL
curl "https://api.openai.com/v1/responses" \\
-H "Content-Type: application/json" \\
-H "Authorization: Bearer $OPENAI_API_KEY" \\
-d '{
"model": "gpt-4.1",
"input": "Write a one-sentence bedtime story about a unicorn."
}'
Data retention for model responses
Response objects are saved for 30 days by default. They can be viewed in the dashboard
logs page or
retrieved via the API.
You can disable this behavior by setting store to false
when creating a Response.
OpenAI does not use data sent via API to train our models without your explicit consent— learn more.
Analyze image inputs
You can provide image inputs to the model as well. Scan receipts, analyze screenshots, or find objects in the real world with computer vision.
Analyze the content of an image
JavaScript
const client = new OpenAI();
const response = await client.responses.create({
model: "gpt-4.1",
input: [
{ role: "user", content: "What two teams are playing in this photo?" },
{
role: "user",
content: [
{
type: "input_image",
image_url: "https://upload.wikimedia.org/wikipedia/commons/3/3b/LeBron_James_Layup_%28Cleveland_vs_Brooklyn_2018%29.jpg",
}
],
},
],
});
console.log(response.output_text);
Python
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-4.1",
input=[
{"role": "user", "content": "what teams are playing in this image?"},
{
"role": "user",
"content": [
{
"type": "input_image",
"image_url": "https://upload.wikimedia.org/wikipedia/commons/3/3b/LeBron_James_Layup_%28Cleveland_vs_Brooklyn_2018%29.jpg"
}
]
}
]
)
print(response.output_text)
cURL
curl "https://api.openai.com/v1/responses" \\
-H "Content-Type: application/json" \\
-H "Authorization: Bearer $OPENAI_API_KEY" \\
-d '{
"model": "gpt-4.1",
"input": [
{
"role": "user",
"content": "What two teams are playing in this photo?"
},
{
"role": "user",
"content": [
{
"type": "input_image",
"image_url": "https://upload.wikimedia.org/wikipedia/commons/3/3b/LeBron_James_Layup_%28Cleveland_vs_Brooklyn_2018%29.jpg"
}
]
}
]
}'
Extend the model with tools
Give the model access to new data and capabilities using tools. You can either call your own custom code, or use one of OpenAI's powerful built-in tools. This example uses web search to give the model access to the latest information on the Internet.
Get information for the response from the Internet
JavaScript
const client = new OpenAI();
const response = await client.responses.create({
model: "gpt-4.1",
tools: [ { type: "web_search_preview" } ],
input: "What was a positive news story from today?",
});
console.log(response.output_text);
Python
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-4.1",
tools=[{"type": "web_search_preview"}],
input="What was a positive news story from today?"
)
print(response.output_text)
cURL
curl "https://api.openai.com/v1/responses" \\
-H "Content-Type: application/json" \\
-H "Authorization: Bearer $OPENAI_API_KEY" \\
-d '{
"model": "gpt-4.1",
"tools": [{"type": "web_search_preview"}],
"input": "what was a positive news story from today?"
}'
Deliver blazing fast AI experiences
Using either the new Realtime API or server-sent streaming events, you can build high performance, low-latency experiences for your users.
Stream server-sent events from the API
JavaScript
const client = new OpenAI();
const stream = await client.responses.create({
model: "gpt-4.1",
input: [
{
role: "user",
content: "Say 'double bubble bath' ten times fast.",
},
],
stream: true,
});
for await (const event of stream) {
console.log(event);
}
Python
from openai import OpenAI
client = OpenAI()
stream = client.responses.create(
model="gpt-4.1",
input=[
{
"role": "user",
"content": "Say 'double bubble bath' ten times fast.",
},
],
stream=True,
)
for event in stream:
print(event)
Build agents
Use the OpenAI platform to build agents capable of taking action—like controlling computers—on behalf of your users. Use the Agents SDK for Python or TypeScript to create orchestration logic on the backend.
Build a language triage agent
JavaScript
const spanishAgent = new Agent({
name: 'Spanish agent',
instructions: 'You only speak Spanish.',
});
const englishAgent = new Agent({
name: 'English agent',
instructions: 'You only speak English',
});
const triageAgent = new Agent({
name: 'Triage agent',
instructions:
'Handoff to the appropriate agent based on the language of the request.',
handoffs: [spanishAgent, englishAgent],
});
const result = await run(triageAgent, 'Hola, ¿cómo estás?');
console.log(result.finalOutput);
Python
from agents import Agent, Runner
spanish_agent = Agent(
name="Spanish agent",
instructions="You only speak Spanish.",
)
english_agent = Agent(
name="English agent",
instructions="You only speak English",
)
triage_agent = Agent(
name="Triage agent",
instructions="Handoff to the appropriate agent based on the language of the request.",
handoffs=[spanish_agent, english_agent],
)
async def main():
result = await Runner.run(triage_agent, input="Hola, ¿cómo estás?")
print(result.final_output)
if __name__ == "__main__":
asyncio.run(main())
Explore further
We've barely scratched the surface of what's possible with the OpenAI platform. Here are some resources you might want to explore next.
- Go deeper with prompting and text generation - Learn more about prompting, message roles, and building conversational apps like chat bots.
- Analyze the content of images - Learn to use image inputs to the model and extract meaning from images.
- Generate structured JSON data from the model - Generate JSON data from the model that conforms to a JSON schema you specify.
- Call custom code to help generate a response - Empower the model to invoke your own custom code to help generate a response. Do this to give the model access to data or systems it wouldn't be able to access otherwise.
- Search the web or use your own data in responses - Try out powerful built-in tools to extend the capabilities of the models. Search the web or your own data for up-to-date information the model can use to generate responses.
- Responses starter app - Start building with the Responses API
- Build agents - Explore interfaces to build powerful AI agents that can take action on behalf of users. Control a computer to take action on behalf of a user, or orchestrate multi-agent flows with the Agents SDK.
- Full API Reference - View the full API reference for the OpenAI platform.