​
Basic Chat Implementation

This example shows how to implement a basic chat application using Adaptive’s API as a drop-in replacement for OpenAI.

​
Quick Setup

Replace your OpenAI base URL with Adaptive’s endpoint: 
import openai

client = openai.OpenAI(
    base_url="https://www.llmadaptive.uk/api/v1",
    api_key="your-adaptive-api-key"
)

# Basic chat completion
response = client.chat.completions.create(
    model="gpt-3.5-turbo",  # Adaptive will optimize routing
    messages=[
        {"role": "user", "content": "Hello! How can you help me today?"}
    ]
)

print(response.choices[0].message.content)

​
JavaScript/Node.js Example

import OpenAI from 'openai';

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

async function basicChat() {
  const completion = await client.chat.completions.create({
    model: 'gpt-3.5-turbo',
    messages: [
      { role: 'user', content: 'What are the benefits of using Adaptive?' }
    ],
  });

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

basicChat();

​
cURL Example

curl https://www.llmadaptive.uk/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-adaptive-api-key" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [
      {"role": "user", "content": "Tell me about cost optimization"}
    ]
  }'

​
Cost Comparison

Traditional OpenAI Direct:
  • GPT-3.5-turbo: $3.00 per 1M input tokens
  • Total cost for 10K messages: ~$30
With Adaptive Smart Routing:
  • Optimized routing: $0.10 per 1M input tokens
  • Total cost for 10K messages: ~$1
  • Savings: 97%

​
Key Features

  • Drop-in Replacement: Use your existing OpenAI SDK
  • Automatic Optimization: Adaptive selects the best model for each request
  • Cost Savings: Typically 60-97% cost reduction
  • Same Quality: Intelligent routing maintains response quality
  • No Code Changes: Just update the base URL and API key

​
Error Handling

try:
    response = client.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": "Hello"}]
    )
    print(response.choices[0].message.content)
except openai.APIError as e:
    print(f"API error occurred: {e}")
except openai.RateLimitError as e:
    print(f"Rate limit exceeded: {e}")

​
Next Steps