​
Installation

Adaptive works with the official OpenAI SDK - no additional packages needed! 
npm install openai

​
Basic Setup

Simply change the baseURL in your existing OpenAI configuration: 
import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your-adaptive-api-key',
  baseURL: 'https://llmadaptive.uk/api/v1'
});

const completion = await openai.chat.completions.create({
  model: '', // Leave empty for intelligent routing
  messages: [
    { role: 'user', content: 'Hello, world!' }
  ],
});

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

​
Streaming Responses

Adaptive fully supports streaming responses: 
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 || '');
}

​
Advanced Parameters

Adaptive supports all OpenAI parameters plus additional routing controls: 
const completion = await openai.chat.completions.create({
  model: '',
  messages: [{ role: 'user', content: 'Explain quantum computing' }],
  // Standard OpenAI parameters
  temperature: 0.7,
  max_tokens: 1000,
  top_p: 1,
  frequency_penalty: 0,
  presence_penalty: 0,
  
  // Adaptive-specific parameters
  provider_constraint: ['openai', 'anthropic'], // Limit providers
  cost_bias: 0.3, // 0 = cheapest, 1 = best performance
});

​
Function Calling

Function calling works exactly like OpenAI: 
const completion = await openai.chat.completions.create({
  model: '',
  messages: [
    { role: 'user', content: 'What\'s the weather like in Boston?' }
  ],
  tools: [
    {
      type: 'function',
      function: {
        name: 'get_current_weather',
        description: 'Get the current weather in a given location',
        parameters: {
          type: 'object',
          properties: {
            location: {
              type: 'string',
              description: 'The city and state, e.g. San Francisco, CA',
            },
            unit: {
              type: 'string',
              enum: ['celsius', 'fahrenheit'],
            },
          },
          required: ['location'],
        },
      },
    },
  ],
});

​
Vision Models

Vision capabilities work when available in the selected model: 
const completion = await openai.chat.completions.create({
  model: '',
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What\'s in this image?' },
        {
          type: 'image_url',
          image_url: {
            url: 'https://example.com/image.jpg',
          },
        },
      ],
    },
  ],
});

​
Error Handling

Adaptive uses the same error format as OpenAI: 
try {
  const completion = await openai.chat.completions.create({
    model: '',
    messages: [{ role: 'user', content: 'Hello!' }],
  });
} catch (error) {
  if (error instanceof OpenAI.APIError) {
    console.error('API Error:', error.status, error.message);
  } else {
    console.error('Unexpected error:', error);
  }
}

​
Migrating from OpenAI

Migration is simple - just update two lines: 
// Before
const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  // baseURL: 'https://api.openai.com/v1' // default
});

// After
const openai = new OpenAI({
  apiKey: process.env.ADAPTIVE_API_KEY, // New API key
  baseURL: 'https://llmadaptive.uk/api/v1' // New base URL
});

// Everything else stays the same!

​
Response Format

Adaptive returns OpenAI-compatible responses with additional metadata: 
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo",
  "provider": "openai",  // ← Additional field
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}
The provider field tells you which underlying provider was selected for your request.