SDK Reference

const costlens = new CostLens({
  apiKey: process.env.COSTLENS_API_KEY,
  routingPolicy: (requestedModel, messages) => {
    // Route complex queries to better models
    const complexity = messages.reduce((acc, msg) => acc + msg.content.length, 0);
    
    if (complexity > 1000) {
      return 'gpt-5.4'; // Use premium model for complex tasks
    }
    
    if (requestedModel === 'gpt-5.4' && complexity < 100) {
      return 'gpt-5.4-mini'; // Downgrade simple tasks
    }
    
    return requestedModel; // Keep original choice
  }
});

const costlens = new CostLens({
  apiKey: process.env.COSTLENS_API_KEY,
  qualityValidator: (responseText, messagesJson) => {
    const messages = JSON.parse(messagesJson);
    
    // Score based on response completeness
    let score = 3; // baseline
    
    if (responseText.length > 200) score += 1;
    if (responseText.includes('```')) score += 1; // code examples
    if (messages.some(m => m.content.includes('?')) && 
        responseText.includes('?')) score -= 1; // answered with question
    
    return Math.max(1, Math.min(5, score)); // clamp 1-5
  }
});

// Track user session
const sessionId = 'session_' + userId;
const requestId = 'req_' + Date.now();

const costlens = new CostLens({
  apiKey: process.env.COSTLENS_API_KEY,
  requestId: requestId,
  correlationId: sessionId
});

const tracked = costlens.wrapOpenAI(openai);

// All requests will be tagged with these IDs
await tracked.chat.completions.create({
  model: 'gpt-5.4-mini',
  messages: [{ role: 'user', content: 'Hello' }]
});

// Get analytics using SDK method
const analytics = costlens.getCostAnalytics();
console.log('Cache Hit Rate:', analytics.cacheHitRate * 100 + '%');
console.log('Total Savings: $' + analytics.totalSavings);

const costlens = new CostLens({
  apiKey: process.env.COSTLENS_API_KEY,
  enableCache: true, // Enable Redis caching
});

const tracked = costlens.wrapOpenAI(openai);

// First call - cache miss, costs $0.05
await tracked.chat.completions.create({
  model: 'gpt-5.4',
  messages: [{ role: 'user', content: 'What is 2+2?' }],
});

// Second call - cache hit, costs $0.00!
await tracked.chat.completions.create({
  model: 'gpt-5.4',
  messages: [{ role: 'user', content: 'What is 2+2?' }],
});

// SDK checks quality status before routing
const tracked = costlens.wrapOpenAI(openai);

// If quality is good: GPT-5.4 → GPT-5.4-mini (saves money)
// If quality dropped: Uses GPT-5.4 (protects quality)
await tracked.chat.completions.create({
  model: 'gpt-5.4',
  messages: [{ role: 'user', content: 'Complex task...' }],
});

// Note: Quality feedback is handled automatically by the SDK
// The SDK tracks routing decisions and learns from them internally

const costlens = new CostLens({
  apiKey: process.env.COSTLENS_API_KEY,
  autoOptimize: true, // Enable AI compression
});

const tracked = costlens.wrapOpenAI(openai);

// Original: 200 tokens
// Optimized: 100 tokens (50% reduction)
// Savings: $0.009 per request
await tracked.chat.completions.create({
  model: 'gpt-5.4',
  messages: [{
    role: 'user',
    content: 'Please kindly help me understand what the weather will be like tomorrow in San Francisco, California, USA'
  }],
});
// Compressed to: "Weather forecast for San Francisco tomorrow?"

// Calculate potential savings using SDK method
const savings = await costlens.calculateSavings('gpt-5.4', messages);

console.log(`Current Cost: $${savings.currentCost}`);
console.log(`Optimized Cost: $${savings.optimizedCost}`);
console.log(`Savings: $${savings.savings} (${savings.savingsPercentage.toFixed(1)}%)`);
console.log(`Recommended Model: ${savings.recommendedModel}`);

// Example output:
// Current Cost: $0.15
// Optimized Cost: $0.03
// Savings: $0.12 (80.0%)
// Recommended Model: gpt-5.4-mini