Skip to main content

​
Quick Setup

  1. Sign up for an Adaptive API key
  2. Install the OpenAI SDK (if you haven’t already): 
npm install openai
  1. Change two lines in your existing code:
import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your-adaptive-api-key',        // ← Your Adaptive API key
  baseURL: 'https://api.llmadaptive.uk/v1' // ← Only change needed
});

// Everything else works exactly the same
const completion = await openai.chat.completions.create({
  model: '', // Leave empty for intelligent routing
  messages: [{ role: 'user', content: 'Hello!' }]
});
That’s it! Your existing OpenAI code now uses intelligent routing.

​
Key Features

Same API

All OpenAI methods, parameters, and responses work identically

Model Routing

Leave model empty ("") to automatically select the best provider

Streaming

Streaming responses work exactly like OpenAI

Function Calling

Function calling and tools work without changes

​
Streaming Example

const stream = await openai.chat.completions.create({
  model: '',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true,
});

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

​
Response Format

Adaptive returns standard OpenAI responses: 
{
  "id": "chatcmpl-123",
  "choices": [{
    "message": {"content": "Hello! How can I help you?"}
  }],
  "usage": {"total_tokens": 21}
}

​
Error Handling

Handle common errors gracefully: 
try {
  const completion = await openai.chat.completions.create({
    model: '',
    messages: [{ role: 'user', content: 'Hello!' }]
  });
  console.log(completion.choices[0].message.content);
} catch (error) {
  if (error.status === 401) {
    console.error('Invalid API key');
  } else if (error.status === 429) {
    console.error('Rate limit exceeded - try again later');
  } else {
    console.error('API error:', error.message);
  }
}
Common Issues:
  • 401: Check your Adaptive API key
  • 429: Rate limit exceeded - implement retry logic
  • 400: Invalid request parameters

​
Need More Control?

API Reference

See all available parameters and options

Examples

Working code examples and use cases