Navigate to [https://openai.com/api/](https://openai.com/api/)

Introducing ChatGPT research release
Try Learn more
API
RESEARCH
BLOG
ABOUT
OVERVIEW
PRICING
DOCS
EXAMPLES
LOG IN SIGN UP
Build next-gen apps with
OpenAI’s powerful models.
Access GPT-3, which performs a variety of natural language tasks, Codex, which translates natural language to code, and DALL·E, which creates and edits original images.
GET STARTED READ DOCUMENTATION
Developers can now begin
building apps with the DALL·E API.
More than 3 million people are already using DALL·E to extend their creativity and speed up their workflows, generating over 4 million images a day. Get started with this same technology in a matter of minutes.
GET STARTED LEARN MORE
Start building with
a simple API call.
GET STARTED READ DOCUMENTATION
import openai

openai.Completion.create(
  engine="davinci",
  prompt="Make a list of astronomical observatories:"
)
COPYWRITING SUMMARIZATION PARSING UNSTRUCTURED TEXT CLASSIFICATION TRANSLATION
Create promo copy for the FamilyTime mobile application. It allows unlimited uploading, special filters and makes it easy to create albums of photos and videos. It runs on iOS and Android:
FamilyTime is the perfect app to share and create memories with your family. FamilyTime is a free, unlimited photo and video editor that allows you to create albums of your memories. It has a special filter for the perfect summer look and is so simple to use.
Perform a wide variety
of natural language
tasks with GPT-3.
GET STARTED SEE MORE EXAMPLES
Translate natural
language to code
with Codex.
LEARN MORE SEE MORE EXAMPLES
TEXT TO SQL TRANSLATION CALLING AN API VIA NATURAL LANGUAGE CODE CONTINUATION
"""
Table customers, columns = [CustomerId, FirstName, LastName, Company, Address, City, State, Country, PostalCode, Phone, Fax, Email, SupportRepId, TotalSpend]

Create a MySQL query for all customers in Texas who have spent over five thousand dollars.
"""

query = "SELECT * FROM customers WHERE State = 'TX' AND TotalSpend > 5000"
lightning
Fast
Our advanced inference infrastructure provides extremely short response 

Creating an OpenAI API Key