Node.js - Automatic Tracking
Automatic tracking uses wrapper classes that handle token counting and tracking for you.
📖 Real-World Scenario
You're building a chatbot and making dozens of OpenAI API calls. Manually extracting usage data and calling sendUsage() for each one is tedious and error-prone. You just want the tracking to happen automatically.
💡 Solution
Use Paygent's automatic wrappers. Just wrap your API client and add 3 tracking parameters:
1
2import { PaygentClient, PaygentOpenAI } from '@paygent_org/paygent-sdk-node';
3import OpenAI from 'openai';
4
5// Initialize Paygent client
6const paygentClient = PaygentClient.newClient(process.env.PAYGENT_API_KEY);
7
8// Initialize OpenAI client
9const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
10
11// Create PaygentOpenAI wrapper for automatic tracking
12const paygentOpenai = new PaygentOpenAI(openai, paygentClient);
13
14// Make OpenAI call with automatic tracking
15// Just add 3 tracking parameters to your normal OpenAI call!
16const response = await paygentOpenai.chat.completions.create({
17 indicator: 'message-sent',
18 external_agent_id: 'chatbot-agent',
19 external_customer_id: 'customer-123',
20
21 model: 'gpt-4o',
22 messages: [{ role: 'user', content: 'Hello!' }]
23});
24
25
26// Usage automatically tracked! No manual code needed!✅ Result
Zero manual tracking code. Every OpenAI call is automatically tracked with accurate token counts and costs. 60% less code!
Pro-Tip: Auto-Onboarding
Before your first AI call, use createOrGetCustomer with your user's ID. This allows Paygent to automatically handle data isolation and billing attribution for new users.
Manual vs Automatic
| Feature | Manual Tracking | Automatic Tracking |
|---|---|---|
| Code Lines | ~40 lines | ~15 lines |
| Token Counting | Manual extraction | Automatic |
| Error Risk | Can forget to track | Impossible to miss |
| Maintenance | High | Low |
| Recommended | For custom use cases | ✓ For most users |
Was this page helpful?
Need help? Contact us at support@withpaygent.com