Skip to main content

​
Get Your Nordlys API Key

Sign up here to create an account and generate your API key.

​
Overview

The Vercel AI SDK works seamlessly with Nordlys through two methods:
  • Nordlys SDK (Recommended): Use the native @nordlys-llm/nordlys-ai-provider package.
  • OpenAI-Compatible Client: Use Nordlys via @ai-sdk/openai with a custom base URL.

​
Method 1: Nordlys SDK

​
Installation

npm install ai @nordlys-llm/nordlys-ai-provider

​
Basic Setup

import { nordlys } from "@nordlys-llm/nordlys-ai-provider";

// Use default configuration
const model = nordlys();

​
Method 2: OpenAI-Compatible Client

​
Installation

npm install ai @ai-sdk/openai

​
Configuration

import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

const nordlysOpenAI = openai({
  apiKey: process.env.NORDLYS_API_KEY,
  baseURL: 'https://api.nordlyslabs.com/v1',
});

const { text } = await generateText({
  model: nordlysOpenAI('nordlys/hypernova'),
  prompt: 'Explain quantum computing simply',
});

​
Text Generation

import { generateText } from 'ai';
import { nordlys } from '@nordlys-llm/nordlys-ai-provider';

const { text } = await generateText({
  model: nordlys(),
  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
});

​
Streaming

import { streamText } from 'ai';
import { nordlys } from '@nordlys-llm/nordlys-ai-provider';

const { textStream } = await streamText({
  model: nordlys(),
  prompt: 'Explain machine learning step by step',
});

for await (const delta of textStream) {
  process.stdout.write(delta);
}

​
React Chat Component

import { useChat } from 'ai/react';

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit } = useChat({
    api: '/api/chat', // Your API route using Nordlys
  });

  return (
    <div>
      {messages.map(m => (
        <div key={m.id}>
          <strong>{m.role}: </strong>
          {m.content}
        </div>
      ))}
      
      <form onSubmit={handleSubmit}>
        <input
          value={input}
          placeholder="Say something..."
          onChange={handleInputChange}
        />
        <button type="submit">Send</button>
      </form>
    </div>
  );
}

​
Configuration

Nordlys keeps advanced tuning internal. Use a Nordlys model ID and focus on your product logic.

​
Tool/Function Calling

import { generateText, tool } from 'ai';
import { z } from 'zod';
import { nordlys } from '@nordlys-llm/nordlys-ai-provider';

const { text } = await generateText({
  model: nordlys(),
  prompt: "What's the weather in New York?",
  tools: {
    getWeather: tool({
      description: 'Get weather for a location',
      parameters: z.object({
        location: z.string(),
      }),
      execute: async ({ location }) => {
        return `Weather in ${location} is sunny and 72°F`;
      },
    }),
  },
});

​
Environment Variables

Environment Setup
# .env.local
NORDLYS_API_KEY=your-nordlys-api-key

​
Error Handling

Nordlys retries transient errors automatically. For comprehensive error handling patterns, see the Error Handling Guide. 
import { useChat } from 'ai/react';

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit, error, reload } = useChat({
    api: '/api/chat',
    onError: (error) => {
      console.error('Nordlys chat error:', error);
    },
  });

  return (
    <div>
      {/* Your chat UI */}
      {error && (
        <div className="error">
          {error.message}
          <button onClick={() => reload()}>Retry</button>
        </div>
      )}
    </div>
  );
}

​
What You Get

Mixture of Models Activation

The right specialists activate per prompt

Built-in Streaming

Real-time response streaming with React components

Cost Optimization

Significant cost savings through lab‑tuned models

Response Metadata

Inspect latency and quality signals per request

​
Next Steps

More Examples

See complete working examples

API Reference

Explore all available options and parameters