Performance Optimizations

npm install costlens

import CostLens from 'costlens';

const costlens = new CostLens({
  apiKey: 'your-api-key',
  smartRouting: true,     // 💰 Auto-route to cheaper models
  enableCache: true,      // 💰 Cache repeated requests
  autoOptimize: true,     // 💰 Optimize prompts automatically
  costLimit: 0.10,        // 💰 Max $0.10 per request
});

// Instead of individual requests:
for (const request of requests) {
  await costlens.trackOpenAI(request.params, request.result, request.latency);
}

// Use batch processing for 3-5x better performance:
await costlens.trackBatch([
  { provider: 'openai', model: 'gpt-4', tokens: 150, latency: 1200 },
  { provider: 'anthropic', model: 'claude-3', tokens: 200, latency: 1000 },
  { provider: 'openai', model: 'gpt-3.5-turbo', tokens: 100, latency: 800 }
]);

// Check your savings and performance
const analytics = costlens.getCostAnalytics();
console.log('Cache Hit Rate:', analytics.cacheHitRate * 100 + '%');
console.log('Total Savings: $' + analytics.totalSavings);
console.log('Average Latency:', analytics.averageLatency + 'ms');
console.log('Error Rate:', analytics.errorRate * 100 + '%');

// Calculate potential savings
const savings = await costlens.calculateSavings('gpt-4', messages);
console.log('Potential Savings: ' + savings.savingsPercentage + '%');
console.log('Recommended Model: ' + savings.recommendedModel);

// Before: Slow and expensive
const responses = [];
for (const query of customerQueries) {
  const response = await openai.chat.completions.create({
    model: 'gpt-4', // Always expensive
    messages: [{ role: 'user', content: query.question }]
  });
  responses.push(response);
}
// Result: 10 requests = 10 API calls = $0.50 = 5 seconds

// After: Fast and cheap with optimizations
const costlens = new CostLens({
  apiKey: 'your-api-key',
  smartRouting: true,    // Auto-route to cheaper models
  enableCache: true,     // Cache repeated requests
  autoOptimize: true,    // Optimize prompts
});

const tracked = costlens.wrapOpenAI(openai);
const responses = [];

// Process in batches for 3-5x better performance
const batchSize = 5;
for (let i = 0; i < customerQueries.length; i += batchSize) {
  const batch = customerQueries.slice(i, i + batchSize);
  
  // Process batch
  const batchPromises = batch.map(async (query) => {
    const response = await tracked.chat.completions.create({
      model: 'gpt-4', // Automatically routes to GPT-3.5-turbo for simple tasks
      messages: [{ role: 'user', content: query.question }]
    });
    return response;
  });
  
  const batchResults = await Promise.all(batchPromises);
  responses.push(...batchResults);
}

// Result: 10 requests = 2 batches = $0.10 = 1 second (3-5x faster, significantly cheaper)

// Check your savings
const analytics = costlens.getCostAnalytics();
console.log(`Saved $${analytics.totalSavings} with ${analytics.cacheHitRate * 100}% cache hit rate`);