Node.js SDK

SovereignEG works with the official OpenAI Node.js SDK for the endpoints it serves. Set baseURL as shown below and use your SovereignEG API key.

Supported: client.chat.completions.create() (streaming included; tool calling on models that support tools), client.embeddings.create(), client.images.generate() on image models, client.decisions.create() on decision models (see Decisions) and client.models.list().
Not available (each returns 404 route_not_found): client.responses, legacy client.completions, Assistants and threads, client.audio, client.files, client.batches, fine-tuning, and image edits and variations. Switch tools that default to the Responses API, such as the OpenAI Agents SDK, to Chat Completions.
Ignored: request fields SovereignEG does not use, such as store, metadata or service_tier, are accepted but have no effect, so stored chat completions are not available.

Installation

npm install openai

Setup

import OpenAI from 'openai';
 
const client = new OpenAI({
  apiKey: 'sk-...',
  baseURL: 'https://backend.sovereigneg.com/v1',
});

Or use environment variables:

export OPENAI_API_KEY=sk-...
export OPENAI_BASE_URL=https://backend.sovereigneg.com/v1

const client = new OpenAI(); // reads from env vars

Chat completions

const response = await client.chat.completions.create({
  model: 'gpt-oss-20b',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello from Node.js!' }
  ],
  temperature: 0.7,
  max_tokens: 256,
});
 
console.log(response.choices[0].message.content);

Streaming

const stream = await client.chat.completions.create({
  model: 'gpt-oss-20b',
  messages: [{ role: 'user', content: 'Write a haiku' }],
  stream: true,
});
 
for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content || '';
  process.stdout.write(content);
}

Next.js API route

// app/api/chat/route.ts
import OpenAI from 'openai';
 
const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  baseURL: 'https://backend.sovereigneg.com/v1',
});
 
export async function POST(req: Request) {
  const { messages } = await req.json();
 
  const stream = await client.chat.completions.create({
    model: 'gpt-oss-20b',
    messages,
    stream: true,
  });
 
  const encoder = new TextEncoder();
  const readable = new ReadableStream({
    async start(controller) {
      for await (const chunk of stream) {
        const content = chunk.choices[0]?.delta?.content || '';
        controller.enqueue(encoder.encode(content));
      }
      controller.close();
    },
  });
 
  return new Response(readable, {
    headers: { 'Content-Type': 'text/plain; charset=utf-8' },
  });
}

Error handling

try {
  const response = await client.chat.completions.create({...});
} catch (error) {
  if (error instanceof OpenAI.AuthenticationError) {
    console.error('Invalid API key');
  } else if (error instanceof OpenAI.RateLimitError) {
    console.error('Rate limited, retry later');
  } else if (error instanceof OpenAI.APIError) {
    console.error(`API error: ${error.message}`);
  }
}

TypeScript support

The OpenAI SDK is fully typed:

import OpenAI from 'openai';
import type { ChatCompletionMessageParam } from 'openai/resources';
 
const messages: ChatCompletionMessageParam[] = [
  { role: 'system', content: 'You are helpful.' },
  { role: 'user', content: 'Hello!' },
];