The OpenAI Node.js library provides convenient access to the OpenAI API from Node.js applications. Most of the code in this library is generated from our OpenAPI specification.

Important note: this library is meant for server-side usage only, as using it in client-side browser code will expose your secret API key. See here for more details.

$ npm install openai

The library needs to be configured with your account's secret key, which is available on the website. We recommend setting it as an environment variable. Here's an example of initializing the library with the API key loaded from an environment variable and creating a completion:

const { Configuration, OpenAIApi } = require("openai");

const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

const completion = await openai.createCompletion({
  model: "text-davinci-003",
  prompt: "Hello world",
});
console.log(completion.data.choices[0].text);

Check out the full API documentation for examples of all the available functions.

All of the available API request functions additionally contain an optional final parameter where you can pass custom axios request options, for example:

const completion = await openai.createCompletion(
  {
    model: "text-davinci-003",
    prompt: "Hello world",
  },
  {
    timeout: 1000,
    headers: {
      "Example-Header": "example",
    },
  }
);

API requests can potentially return errors due to invalid inputs or other issues. These errors can be handled with a try...catch statement, and the error details can be found in either error.response or error.message:

try {
  const completion = await openai.createCompletion({
    model: "text-davinci-003",
    prompt: "Hello world",
  });
  console.log(completion.data.choices[0].text);
} catch (error) {
  if (error.response) {
    console.log(error.response.status);
    console.log(error.response.data);
  } else {
    console.log(error.message);
  }
}

All breaking changes for major version releases are listed below.

• The function signature of createCompletion(engineId, params) changed to createCompletion(params). The value previously passed in as the engineId argument should now be passed in as model in the params object (e.g. createCompletion({ model: "text-davinci-003", ... }))
• Replace any createCompletionFromModel(params) calls with createCompletion(params)

Thank you to ceifa for creating and maintaining the original unofficial openai npm package before we released this official library! ceifa's original package has been renamed to gpt-x.