Implementation:Openai Openai node Completions Create

Knowledge Sources	openai-node Chat Completions API
Domains	NLP, API_Design
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete tool for invoking the Chat Completions endpoint provided by the openai-node SDK.

Description

The Completions.create() method sends a POST request to /chat/completions with the given request body. It supports three overloaded signatures: non-streaming (returns APIPromise<ChatCompletion>), streaming (returns APIPromise<Stream<ChatCompletionChunk>>), and a generic union. The method delegates to the internal HTTP client with retry and timeout handling.

Usage

Call this method to generate text from any OpenAI chat model. For streaming responses with high-level event handling, prefer completions.stream() instead.

Code Reference

Source Location

• Repository: openai-node
• File: src/resources/chat/completions/completions.ts
• Lines: L55-71

Signature

class Completions extends APIResource {
  // Non-streaming overload
  create(
    body: ChatCompletionCreateParamsNonStreaming,
    options?: RequestOptions,
  ): APIPromise<ChatCompletion>;

  // Streaming overload
  create(
    body: ChatCompletionCreateParamsStreaming,
    options?: RequestOptions,
  ): APIPromise<Stream<ChatCompletionChunk>>;

  // Union overload (implementation)
  create(
    body: ChatCompletionCreateParams,
    options?: RequestOptions,
  ): APIPromise<ChatCompletion> | APIPromise<Stream<ChatCompletionChunk>>;
}

Import

import OpenAI from 'openai';
// Access via: client.chat.completions.create(...)

I/O Contract

Inputs

Name	Type	Required	Description
body	ChatCompletionCreateParams	Yes	Request body with messages, model, and optional parameters
options	RequestOptions	No	Per-request overrides (headers, signal, timeout)

Outputs

Name	Type	Description
(non-streaming)	APIPromise<ChatCompletion>	Complete response with choices[].message.content
(streaming)	APIPromise<Stream<ChatCompletionChunk>>	Async iterable of incremental chunks

Usage Examples

Non-Streaming

import OpenAI from 'openai';

const client = new OpenAI();

const completion = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of France?' },
  ],
});

console.log(completion.choices[0].message.content);

Low-Level Streaming

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Count to 10.' }],
  stream: true,
});

for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta?.content;
  if (delta) process.stdout.write(delta);
}

Related Pages

Implements Principle

• Principle:Openai_Openai_node_Chat_Completion_Invocation

Requires Environment

• Environment:Openai_Openai_node_Node_20_Runtime