TypeScript icon, indicating that this package has built-in type declarations

4.20.1 • Public • Published

OpenAI Node API Library

NPM version

This library provides convenient access to the OpenAI REST API from TypeScript or JavaScript.

It is generated from our OpenAPI specification with Stainless.

To learn how to use the OpenAI API, check out our API Reference and Documentation.


npm install --save openai
# or
yarn add openai

You can import in Deno via:

import OpenAI from '';


The full API of this library can be found in file along with many code examples. The code below shows how to get started using the chat completions API.

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'My API Key', // defaults to process.env["OPENAI_API_KEY"]

async function main() {
  const chatCompletion = await{
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'gpt-3.5-turbo',


Streaming Responses

We provide support for streaming responses using Server Sent Events (SSE).

import OpenAI from 'openai';

const openai = new OpenAI();

async function main() {
  const stream = await{
    model: 'gpt-4',
    messages: [{ role: 'user', content: 'Say this is a test' }],
    stream: true,
  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');


If you need to cancel a stream, you can break from the loop or call stream.controller.abort().

Request & Response types

This library includes TypeScript definitions for all request params and response fields. You may import and use them like so:

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'My API Key', // defaults to process.env["OPENAI_API_KEY"]

async function main() {
  const params: OpenAI.Chat.ChatCompletionCreateParams = {
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'gpt-3.5-turbo',
  const chatCompletion: OpenAI.Chat.ChatCompletion = await;


Documentation for each method, request param, and response field are available in docstrings and will appear on hover in most modern editors.

[!IMPORTANT] Previous versions of this SDK used a Configuration class. See the v3 to v4 migration guide.

Streaming responses

This library provides several conveniences for streaming chat completions, for example:

import OpenAI from 'openai';

const openai = new OpenAI();

async function main() {
  const stream = await{
    model: 'gpt-4',
    messages: [{ role: 'user', content: 'Say this is a test' }],
    stream: true,

  stream.on('content', (delta, snapshot) => {

  // or, equivalently:
  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');

  const chatCompletion = await stream.finalChatCompletion();
  console.log(chatCompletion); // {id: "…", choices: […], …}


Streaming with{…}) exposes various helpers for your convenience including event handlers and promises.

Alternatively, you can use{ stream: true, … }) which only returns an async iterable of the chunks in the stream and thus uses less memory (it does not build up a final chat completion object for you).

If you need to cancel a stream, you can break from a for await loop or call stream.abort().

Automated function calls

We provide{…}) and{…}) convenience helpers for using function calls with the /chat/completions endpoint which automatically call the JavaScript functions you provide and sends their results back to the /chat/completions endpoint, looping as long as the model requests function calls.

If you pass a parse function, it will automatically parse the arguments for you and returns any parsing errors to the model to attempt auto-recovery. Otherwise, the args will be passed to the function you provide as a string.

If you pass function_call: {name: …} or tool_choice: {function: {name: …}} instead of auto, it returns immediately after calling that function (and only loops to auto-recover parsing errors).

import OpenAI from 'openai';

const client = new OpenAI();

async function main() {
  const runner =
      model: 'gpt-3.5-turbo',
      messages: [{ role: 'user', content: 'How is the weather this week?' }],
      functions: [
          function: getCurrentLocation,
          parameters: { type: 'object', properties: {} },
          function: getWeather,
          parse: JSON.parse, // or use a validation library like zod for typesafe parsing.
          parameters: {
            type: 'object',
            properties: {
              location: { type: 'string' },
    .on('message', (message) => console.log(message));

  const finalContent = await runner.finalContent();
  console.log('Final content:', finalContent);

async function getCurrentLocation() {
  return 'Boston'; // Simulate lookup

async function getWeather(args: { location: string }) {
  const { location } = args;
  // … do lookup …
  return { temperature, precipitation };


// {role: "user",      content: "How's the weather this week?"}
// {role: "assistant", function_call: "getCurrentLocation", arguments: "{}"}
// {role: "function",  name: "getCurrentLocation", content: "Boston"}
// {role: "assistant", function_call: "getWeather", arguments: '{"location": "Boston"}'}
// {role: "function",  name: "getWeather", content: '{"temperature": "50degF", "preciptation": "high"}'}
// {role: "assistant", content: "It's looking cold and rainy - you might want to wear a jacket!"}
// Final content: "It's looking cold and rainy - you might want to wear a jacket!"

Like with .stream(), we provide a variety of helpers and events.

Read more about various examples such as with integrating with zod, next.js, and proxying a stream to the browser.

File Uploads

Request parameters that correspond to file uploads can be passed in many different forms:

  • File (or an object with the same structure)
  • a fetch Response (or an object with the same structure)
  • an fs.ReadStream
  • the return value of our toFile helper
import fs from 'fs';
import fetch from 'node-fetch';
import OpenAI, { toFile } from 'openai';

const openai = new OpenAI();

// If you have access to Node `fs` we recommend using `fs.createReadStream()`:
await openai.files.create({ file: fs.createReadStream('input.jsonl'), purpose: 'fine-tune' });

// Or if you have the web `File` API you can pass a `File` instance:
await openai.files.create({ file: new File(['my bytes'], 'input.jsonl'), purpose: 'fine-tune' });

// You can also pass a `fetch` `Response`:
await openai.files.create({ file: await fetch('https://somesite/input.jsonl'), purpose: 'fine-tune' });

// Finally, if none of the above are convenient, you can use our `toFile` helper:
await openai.files.create({
  file: await toFile(Buffer.from('my bytes'), 'input.jsonl'),
  purpose: 'fine-tune',
await openai.files.create({
  file: await toFile(new Uint8Array([0, 1, 2]), 'input.jsonl'),
  purpose: 'fine-tune',

Handling errors

When the library is unable to connect to the API, or if the API returns a non-success status code (i.e., 4xx or 5xx response), a subclass of APIError will be thrown:

async function main() {
  const fineTune = await openai.fineTunes
    .create({ training_file: 'file-XGinujblHPwGLSztz8cPS8XY' })
    .catch((err) => {
      if (err instanceof OpenAI.APIError) {
        console.log(err.status); // 400
        console.log(; // BadRequestError
        console.log(err.headers); // {server: 'nginx', ...}
      } else {
        throw err;


Error codes are as followed:

Status Code Error Type
400 BadRequestError
401 AuthenticationError
403 PermissionDeniedError
404 NotFoundError
422 UnprocessableEntityError
429 RateLimitError
>=500 InternalServerError
N/A APIConnectionError

Azure OpenAI

An example of using this library with Azure OpenAI can be found here.

Please note there are subtle differences in API shape & behavior between the Azure OpenAI API and the OpenAI API, so using this library with Azure OpenAI may result in incorrect types, which can lead to bugs.

See @azure/openai for an Azure-specific SDK provided by Microsoft.


Certain errors will be automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors will all be retried by default.

You can use the maxRetries option to configure or disable this:

// Configure the default for all requests:
const openai = new OpenAI({
  maxRetries: 0, // default is 2

// Or, configure per-request:
await{ messages: [{ role: 'user', content: 'How can I get the name of the current day in Node.js?' }], model: 'gpt-3.5-turbo' }, {
  maxRetries: 5,


Requests time out after 10 minutes by default. You can configure this with a timeout option:

// Configure the default for all requests:
const openai = new OpenAI({
  timeout: 20 * 1000, // 20 seconds (default is 10 minutes)

// Override per-request:
await{ messages: [{ role: 'user', content: 'How can I list all files in a directory using Python?' }], model: 'gpt-3.5-turbo' }, {
  timeout: 5 * 1000,

On timeout, an APIConnectionTimeoutError is thrown.

Note that requests which time out will be retried twice by default.


List methods in the OpenAI API are paginated. You can use for await … of syntax to iterate through items across all pages:

async function fetchAllFineTuningJobs(params) {
  const allFineTuningJobs = [];
  // Automatically fetches more pages as needed.
  for await (const fineTuningJob of{ limit: 20 })) {
  return allFineTuningJobs;

Alternatively, you can make request a single page at a time:

let page = await{ limit: 20 });
for (const fineTuningJob of {

// Convenience methods are provided for manually paginating:
while (page.hasNextPage()) {
  page = page.getNextPage();
  // ...

Advanced Usage

Accessing raw Response data (e.g., headers)

The "raw" Response returned by fetch() can be accessed through the .asResponse() method on the APIPromise type that all methods return.

You can also use the .withResponse() method to get the raw Response along with the parsed data.

const openai = new OpenAI();

const response = await
  .create({ messages: [{ role: 'user', content: 'Say this is a test' }], model: 'gpt-3.5-turbo' })
console.log(response.statusText); // access the underlying Response object

const { data: chatCompletion, response: raw } = await
  .create({ messages: [{ role: 'user', content: 'Say this is a test' }], model: 'gpt-3.5-turbo' })

Customizing the fetch client

By default, this library uses node-fetch in Node, and expects a global fetch function in other environments.

If you would prefer to use a global, web-standards-compliant fetch function even in a Node environment, (for example, if you are running Node with --experimental-fetch or using NextJS which polyfills with undici), add the following import before your first import from "OpenAI":

// Tell TypeScript and the package to use the global web fetch instead of node-fetch.
// Note, despite the name, this does not add any polyfills, but expects them to be provided if needed.
import "openai/shims/web";
import OpenAI from "openai";

To do the inverse, add import "openai/shims/node" (which does import polyfills). This can also be useful if you are getting the wrong TypeScript types for Response - more details here.

You may also provide a custom fetch function when instantiating the client, which can be used to inspect or alter the Request or Response before/after each request:

import { fetch } from 'undici'; // as one example
import OpenAI from 'openai';

const client = new OpenAI({
  fetch: (url: RequestInfo, init?: RequestInfo): Response => {
    console.log('About to make request', url, init);
    const response = await fetch(url, init);
    console.log('Got response', response);
    return response;

Note that if given a DEBUG=true environment variable, this library will log all requests and responses automatically. This is intended for debugging purposes only and may change in the future without notice.

Configuring an HTTP(S) Agent (e.g., for proxies)

By default, this library uses a stable agent for all http/https requests to reuse TCP connections, eliminating many TCP & TLS handshakes and shaving around 100ms off most requests.

If you would like to disable or customize this behavior, for example to use the API behind a proxy, you can pass an httpAgent which is used for all requests (be they http or https), for example:

import http from 'http';
import HttpsProxyAgent from 'https-proxy-agent';

// Configure the default for all requests:
const openai = new OpenAI({
  httpAgent: new HttpsProxyAgent(process.env.PROXY_URL),

// Override per-request:
await openai.models.list({
  baseURL: 'http://localhost:8080/test-api',
  httpAgent: new http.Agent({ keepAlive: false }),

Semantic Versioning

This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:

  1. Changes that only affect static types, without breaking runtime behavior.
  2. Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals).
  3. Changes that we do not expect to impact the vast majority of users in practice.

We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.

We are keen for your feedback; please open an issue with questions, bugs, or suggestions.


TypeScript >= 4.5 is supported.

The following runtimes are supported:

  • Node.js 18 LTS or later (non-EOL) versions.
  • Deno v1.28.0 or higher, using import OpenAI from "npm:openai".
  • Bun 1.0 or later.
  • Cloudflare Workers.
  • Vercel Edge Runtime.
  • Jest 28 or greater with the "node" environment ("jsdom" is not supported at this time).
  • Nitro v2.6 or greater.

Note that React Native is not supported at this time.

If you are interested in other runtime environments, please open or upvote an issue on GitHub.




Package Sidebar


npm i openai

Weekly Downloads






Unpacked Size

1.67 MB

Total Files


Last publish


  • dschnurr
  • jeevnayak
  • knight-oai
  • mario-oai
  • dschnurr-openai