Node.js SDK Integration

When using the official OpenAI Node.js SDK, simply replace apiKey, baseURL, and model with CoreRouter information.

Installation

npm install openai

Or with Bun:

bun add openai

To directly read from a .env file, also install dotenv:

npm install dotenv

Or:

bun add dotenv

Basic Usage

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.COREROUTER_API_KEY,
  baseURL: "https://api.corerouter.cloud/v1",
});

const completion = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages: [
    { role: "user", content: "Hello, please introduce yourself." },
  ],
});

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

Streaming Output

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.COREROUTER_API_KEY,
  baseURL: "https://api.corerouter.cloud/v1",
});

const stream = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages: [
    { role: "user", content: "Introduce CoreRouter in three sentences." },
  ],
  stream: true,
});

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

Multi-Turn Conversation

import type { ChatCompletionMessageParam } from "openai/resources/chat/completions";

const messages: ChatCompletionMessageParam[] = [
  { role: "user", content: "Hello" },
];

let completion = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages,
});

messages.push({
  role: "assistant",
  content: completion.choices[0].message.content ?? "",
});
messages.push({ role: "user", content: "Please write a TypeScript hello function." });

completion = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages,
});

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

Tool Calling

const completion = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages: [{ role: "user", content: "What's the weather like in Beijing?" }],
  tools: [
    {
      type: "function",
      function: {
        name: "get_weather",
        description: "Get weather information for a specified city",
        parameters: {
          type: "object",
          properties: {
            city: { type: "string", description: "City name" },
          },
          required: ["city"],
        },
      },
    },
  ],
});

const toolCall = completion.choices[0].message.tool_calls?.[0];
if (toolCall) {
  console.log(toolCall.function.name);
  console.log(toolCall.function.arguments);
}

Responses API

This example requires the Model ID to support Responses. Regular chat models may not work. If client.responses doesn't exist, upgrade the openai package first, or call directly following Responses API curl examples.

const response = await client.responses.create({
  model: "responses-model-id",
  input: "Introduce CoreRouter in three sentences.",
});

console.log(response.output_text);

Embeddings

const result = await client.embeddings.create({
  model: "embedding-model-id",
  input: ["First text segment", "Second text segment"],
});

console.log(result.data[0].embedding.length);

Using .env

COREROUTER_API_KEY=sk-xxxxxxxxxxxxxxxx
COREROUTER_BASE_URL=https://api.corerouter.cloud/v1
COREROUTER_MODEL=claude-sonnet-4-5

import "dotenv/config";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.COREROUTER_API_KEY,
  baseURL: process.env.COREROUTER_BASE_URL,
});

const completion = await client.chat.completions.create({
  model: process.env.COREROUTER_MODEL ?? "claude-sonnet-4-5",
  messages: [{ role: "user", content: "Hello" }],
});

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

Add .env to .gitignore; don't commit API Keys to repositories.

Common Issues

• COREROUTER_API_KEY is empty: Confirm the program starts from the same terminal, or the deployment platform has environment variables configured.
• Returns model not found: Confirm model is the Model ID from the console.
• Regular conversation works but tool calling fails: Switch to a model that supports Tool Calling.