> ## Documentation Index
> Fetch the complete documentation index at: https://docs.dodopayments.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM Blueprint

> Lacak penggunaan token LLM dengan mudah untuk penagihan berbasis penggunaan dengan pengambilan otomatis ke Dodo Payments. Bekerja dengan AI SDK, OpenAI, Anthropic, OpenRouter, Groq, dan Google Gemini.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="#quick-start">
    Mulai dalam 2 menit dengan pelacakan token otomatis.
  </Card>

  <Card title="API Reference - Events Ingestion" icon="code" href="/api-reference/usage-events/ingest-events">
    Dokumentasi API lengkap untuk memasukkan event penggunaan.
  </Card>

  <Card title="API Reference - Meters" icon="gauge" href="/api-reference/meters/create-meter">
    Pelajari cara membuat dan mengkonfigurasi meter untuk penagihan.
  </Card>

  <Card title="Usage-Based Billing Guide" icon="arrow-trend-up" href="/developer-resources/usage-based-billing-guide">
    Panduan komprehensif untuk penagihan berbasis penggunaan dengan meter.
  </Card>
</CardGroup>

<Info>
  Sangat cocok untuk aplikasi SaaS, chatbot AI, alat pembuatan konten, dan aplikasi bertenaga LLM apa pun yang memerlukan penagihan berbasis penggunaan.
</Info>

## Quick Start

Mulai dengan pelacakan token LLM otomatis hanya dalam 2 menit:

<Steps>
  <Step title="Install the SDK">
    Pasang Dodo Payments Ingestion Blueprints:

    ```bash theme={null}
    npm install @dodopayments/ingestion-blueprints
    ```
  </Step>

  <Step title="Get Your API Keys">
    Anda memerlukan dua kunci API:

    * **Dodo Payments API Key**: Dapatkan dari [Dodo Payments Dashboard](https://app.dodopayments.com/developer/api-keys)
    * **LLM Provider API Key**: Dari AI SDK, OpenAI, Anthropic, Groq, dll.

    <Tip>
      Simpan kunci API Anda dengan aman di variabel lingkungan. Jangan pernah commit ke kontrol versi.
    </Tip>
  </Step>

  <Step title="Create a Meter in Dodo Payments">
    Sebelum melacak penggunaan, buat meter di dashboard Dodo Payments Anda:

    1. **Masuk** ke [Dodo Payments Dashboard](https://app.dodopayments.com/)
    2. **Navigasi ke** Products → Meters
    3. **Klik** "Create Meter"
    4. **Konfigurasikan meter Anda**:
       * **Meter Name**: Pilih nama deskriptif (misalnya, "LLM Token Usage")
       * **Event Name**: Atur identifier event unik (misalnya, `llm.chat_completion`)
       * **Aggregation Type**: Pilih `sum` untuk menjumlahkan jumlah token
       * **Over Property**: Pilih apa yang akan dilacak:
         * `inputTokens` - Lacak token input/prompt
         * `outputTokens` - Lacak token output/completion (termasuk token penalaran bila berlaku)
         * `totalTokens` - Lacak gabungan token input + output

    <Info>
      Nama **Event** yang Anda tetapkan di sini harus cocok persis dengan yang Anda kirim ke SDK (peka huruf).
    </Info>

    Untuk petunjuk mendetail, lihat [Usage-Based Billing Guide](/developer-resources/usage-based-billing-guide).
  </Step>

  <Step title="Track Token Usage">
    Bungkus klien LLM Anda dan mulailah melacak secara otomatis:

    <CodeGroup>
      ```javascript AI SDK theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import { generateText } from 'ai';
      import { google } from '@ai-sdk/google';

      const llmTracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'aisdk.usage',
      });

      const client = llmTracker.wrap({
        client: { generateText },
        customerId: 'customer_123'
      });

      const response = await client.generateText({
        model: google('gemini-2.0-flash'),
        prompt: 'Hello!',
        maxOutputTokens: 500
      });

      console.log('Usage:', response.usage);
      ```

      ```javascript OpenRouter theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import OpenAI from 'openai';

      const openrouter = new OpenAI({
        baseURL: 'https://openrouter.ai/api/v1',
        apiKey: process.env.OPENROUTER_API_KEY
      });

      const llmTracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'openrouter.usage'
      });

      const client = llmTracker.wrap({
        client: openrouter,
        customerId: 'customer_123'
      });

      const response = await client.chat.completions.create({
        model: 'qwen/qwen3-max',
        messages: [{ role: 'user', content: 'Hello!' }],
        max_tokens: 500
      });

      console.log('Response:', response.choices[0].message.content);
      console.log('Usage:', response.usage);
      ```

      ```javascript OpenAI theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import OpenAI from 'openai';

      // 1. Create your LLM client (normal way)
      const openai = new OpenAI({ 
        apiKey: process.env.OPENAI_API_KEY 
      });

      // 2. Create tracker ONCE at startup
      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode', // Use 'live_mode' for production
        eventName: 'llm.chat_completion' // Match your meter's event name
      });

      // 3. Wrap & use - automatic tracking!
      const client = tracker.wrap({ 
        client: openai, 
        customerId: 'customer_123' 
      });

      // Every API call is now automatically tracked
      const response = await client.chat.completions.create({
        model: 'gpt-4',
        messages: [{ role: 'user', content: 'Hello!' }]
      });

      // ✨ Usage automatically sent to Dodo Payments!
      console.log('Tokens used:', response.usage);
      ```

      ```javascript Anthropic theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import Anthropic from '@anthropic-ai/sdk';

      const anthropic = new Anthropic({ 
        apiKey: process.env.ANTHROPIC_API_KEY 
      });

      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'anthropic.usage'
      });

      const client = tracker.wrap({ 
        client: anthropic, 
        customerId: 'customer_123' 
      });

      const response = await client.messages.create({
        model: 'claude-sonnet-4-0',
        max_tokens: 1024,
        messages: [{ role: 'user', content: 'Hello Claude!' }]
      });

      console.log('Tokens used:', response.usage);
      ```

      ```javascript Groq theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import Groq from 'groq-sdk';

      const groq = new Groq({ 
        apiKey: process.env.GROQ_API_KEY 
      });

      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'groq.usage'
      });

      const client = tracker.wrap({ 
        client: groq, 
        customerId: 'customer_123' 
      });

      const response = await client.chat.completions.create({
        model: 'llama-3.1-8b-instant',
        messages: [{ role: 'user', content: 'Hello!' }]
      });

      console.log('Tokens:', response.usage);
      ```

      ```javascript Google Gemini theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import { GoogleGenAI } from '@google/genai';

      const googleGenai = new GoogleGenAI({
        apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY
      });

      const llmTracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'gemini.usage'
      });

      const client = llmTracker.wrap({
        client: googleGenai,
        customerId: 'customer_123'
      });

      const response = await client.models.generateContent({
        model: 'gemini-2.5-flash',
        contents: 'Why is the sky blue?'
      });

      console.log('Response:', response.text);
      console.log('Usage:', response.usageMetadata);
      ```
    </CodeGroup>

    <Check>
      Itu saja! Setiap panggilan API sekarang secara otomatis melacak penggunaan token dan mengirim event ke Dodo Payments untuk penagihan.
    </Check>
  </Step>
</Steps>

***

## Konfigurasi

### Konfigurasi Pelacak

Buat pelacak sekali saat aplikasi dimulai dengan parameter yang diperlukan ini:

<ParamField path="apiKey" type="string" required>
  Kunci API Dodo Payments Anda. Dapatkan dari [API Keys page](https://app.dodopayments.com/developer/api-keys).

  ```javascript theme={null}
  apiKey: process.env.DODO_PAYMENTS_API_KEY
  ```
</ParamField>

<ParamField path="environment" type="string" required>
  Mode lingkungan untuk tracker.

  * `test_mode` - Gunakan untuk pengembangan dan pengujian
  * `live_mode` - Gunakan untuk produksi

  ```javascript theme={null}
  environment: 'test_mode' // or 'live_mode'
  ```

  <Warning>
    Selalu gunakan `test_mode` selama pengembangan agar tidak memengaruhi metrik produksi.
  </Warning>
</ParamField>

<ParamField path="eventName" type="string" required>
  Nama event yang memicu meter Anda. Harus cocok persis dengan yang Anda konfigurasi di meter Dodo Payments (peka huruf).

  ```javascript theme={null}
  eventName: 'llm.chat_completion'
  ```

  <Info>
    Nama event ini menghubungkan penggunaan yang dilacak ke meter yang tepat untuk perhitungan penagihan.
  </Info>
</ParamField>

### Konfigurasi Pembungkus

Saat membungkus klien LLM Anda, berikan parameter ini:

<ParamField path="client" type="object" required>
  Instansi klien LLM Anda (OpenAI, Anthropic, Groq, dll.).

  ```javascript theme={null}
  client: openai
  ```
</ParamField>

<ParamField path="customerId" type="string" required>
  Pengidentifikasi pelanggan unik untuk penagihan. Ini harus cocok dengan ID pelanggan Anda di Dodo Payments.

  ```javascript theme={null}
  customerId: 'customer_123'
  ```

  <Tip>
    Gunakan ID pengguna atau ID pelanggan aplikasi Anda untuk memastikan penagihan akurat per pelanggan.
  </Tip>
</ParamField>

<ParamField path="metadata" type="object">
  Data tambahan opsional untuk dilampirkan ke event pelacakan. Berguna untuk penyaringan dan analisis.

  ```javascript theme={null}
  metadata: {
    feature: 'chat',
    userTier: 'premium',
    sessionId: 'session_123',
    modelVersion: 'gpt-4'
  }
  ```
</ParamField>

### Contoh Konfigurasi Lengkap

<CodeGroup>
  ```javascript Full Configuration theme={null}
  import { createLLMTracker } from "@dodopayments/ingestion-blueprints";
  import { generateText } from "ai";
  import { google } from "@ai-sdk/google";
  import "dotenv/config";

  async function aiSdkExample() {
    console.log("🤖 AI SDK Simple Usage Example\n");

    try {
      // 1. Create tracker
      const llmTracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY!,
        environment: "test_mode",
        eventName: "your_meter_event_name",
      });

      // 2. Wrap the ai-sdk methods
      const client = llmTracker.wrap({
        client: { generateText },
        customerId: "customer_123",
        metadata: {
          provider: "ai-sdk",
        },
      });

      // 3. Use the wrapped function
      const response = await client.generateText({
        model: google("gemini-2.5-flash"),
        prompt: "Hello, I am a cool guy! Tell me a fun fact.",
        maxOutputTokens: 500,
      });

      console.log(response);
      console.log(response.usage);
      console.log("✅ Automatically tracked for customer\n");
    } catch (error) {
      console.error(error);
    }
  }

  aiSdkExample().catch(console.error);
  ```
</CodeGroup>

<Info>
  **Pelacakan Otomatis:** SDK secara otomatis melacak penggunaan token di latar belakang tanpa memodifikasi respons. Kode Anda tetap bersih dan identik dengan menggunakan SDK penyedia asli.
</Info>

***

## Penyedia yang Didukung

LLM Blueprint bekerja dengan lancar dengan semua penyedia dan agregator LLM utama:

<AccordionGroup>
  <Accordion title="AI SDK (Vercel)" icon="code">
    Lacak penggunaan dengan Vercel AI SDK untuk dukungan LLM universal.

    <CodeGroup>
      ```javascript AI SDK Integration theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import { generateText } from 'ai';
      import { google } from '@ai-sdk/google';

      const llmTracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'aisdk.usage',
      });

      const client = llmTracker.wrap({
        client: { generateText },
        customerId: 'customer_123',
        metadata: {
          model: 'gemini-2.0-flash',
          feature: 'chat'
        }
      });

      const response = await client.generateText({
        model: google('gemini-2.0-flash'),
        prompt: 'Explain neural networks',
        maxOutputTokens: 500
      });

      console.log('Usage:', response.usage);
      ```
    </CodeGroup>

    **Metrik yang Dilacak:**

    * `inputTokens` → `inputTokens`
    * `outputTokens` + `reasoningTokens` → `outputTokens`
    * `totalTokens` → `totalTokens`
    * Nama model

    <Note>
      Saat menggunakan model yang dapat melakukan penalaran melalui AI SDK (seperti Gemini 2.5 Flash milik Google dengan thinking mode), token penalaran secara otomatis termasuk dalam `outputTokens` untuk penagihan yang akurat.
    </Note>
  </Accordion>

  <Accordion title="OpenRouter" icon="route">
    Lacak penggunaan token di lebih dari 200 model melalui API terpadu OpenRouter.

    <CodeGroup>
      ```javascript OpenRouter Integration theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import OpenAI from 'openai';

      // OpenRouter uses OpenAI-compatible API
      const openrouter = new OpenAI({
        baseURL: 'https://openrouter.ai/api/v1',
        apiKey: process.env.OPENROUTER_API_KEY
      });

      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'openrouter.usage'
      });

      const client = tracker.wrap({ 
        client: openrouter, 
        customerId: 'user_123',
        metadata: { provider: 'openrouter' }
      });

      const response = await client.chat.completions.create({
        model: 'qwen/qwen3-max',
        messages: [{ role: 'user', content: 'What is machine learning?' }],
        max_tokens: 500
      });

      console.log('Response:', response.choices[0].message.content);
      console.log('Usage:', response.usage);
      ```
    </CodeGroup>

    **Metrik yang Dilacak:**

    * `prompt_tokens` → `inputTokens`
    * `completion_tokens` → `outputTokens`
    * `total_tokens` → `totalTokens`
    * Nama model

    <Tip>
      OpenRouter menyediakan akses ke model dari OpenAI, Anthropic, Google, Meta, dan banyak penyedia lainnya melalui satu API.
    </Tip>
  </Accordion>

  <Accordion title="OpenAI" icon="robot">
    Lacak penggunaan token dari model GPT OpenAI secara otomatis.

    <CodeGroup>
      ```javascript OpenAI Integration theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import OpenAI from 'openai';

      const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'openai.usage'
      });

      const client = tracker.wrap({ 
        client: openai, 
        customerId: 'user_123' 
      });

      // All OpenAI methods work automatically
      const response = await client.chat.completions.create({
        model: 'gpt-4',
        messages: [{ role: 'user', content: 'Explain quantum computing' }]
      });

      console.log('Total tokens:', response.usage.total_tokens);
      ```
    </CodeGroup>

    **Metrik yang Dilacak:**

    * `prompt_tokens` → `inputTokens`
    * `completion_tokens` → `outputTokens`
    * `total_tokens` → `totalTokens`
    * Nama model
  </Accordion>

  <Accordion title="Anthropic Claude" icon="robot">
    Lacak penggunaan token dari model Claude milik Anthropic.

    <CodeGroup>
      ```javascript Anthropic Integration theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import Anthropic from '@anthropic-ai/sdk';

      const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });

      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'anthropic.usage'
      });

      const client = tracker.wrap({ 
        client: anthropic, 
        customerId: 'user_123' 
      });

      const response = await client.messages.create({
        model: 'claude-sonnet-4-0',
        max_tokens: 1024,
        messages: [{ role: 'user', content: 'Explain machine learning' }]
      });

      console.log('Input tokens:', response.usage.input_tokens);
      console.log('Output tokens:', response.usage.output_tokens);
      ```
    </CodeGroup>

    **Metrik yang Dilacak:**

    * `input_tokens` → `inputTokens`
    * `output_tokens` → `outputTokens`
    * Kalkulasi `totalTokens`
    * Nama model
  </Accordion>

  <Accordion title="Groq" icon="gauge-high">
    Lacak inferensi LLM super cepat dengan Groq.

    <CodeGroup>
      ```javascript Groq Integration theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import Groq from 'groq-sdk';

      const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'groq.usage'
      });

      const client = tracker.wrap({ 
        client: groq, 
        customerId: 'user_123' 
      });

      const response = await client.chat.completions.create({
        model: 'llama-3.1-8b-instant',
        messages: [{ role: 'user', content: 'What is AI?' }]
      });

      console.log('Tokens:', response.usage);
      ```
    </CodeGroup>

    **Metrik yang Dilacak:**

    * `prompt_tokens` → `inputTokens`
    * `completion_tokens` → `outputTokens`
    * `total_tokens` → `totalTokens`
    * Nama model
  </Accordion>

  <Accordion title="Google Gemini" icon="sparkles">
    Lacak penggunaan token dari model Gemini Google melalui Google GenAI SDK.

    <CodeGroup>
      ```javascript Google Gemini Integration theme={null}
      import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
      import { GoogleGenAI } from '@google/genai';

      const googleGenai = new GoogleGenAI({ 
        apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY 
      });

      const tracker = createLLMTracker({
        apiKey: process.env.DODO_PAYMENTS_API_KEY,
        environment: 'test_mode',
        eventName: 'gemini.usage'
      });

      const client = tracker.wrap({ 
        client: googleGenai, 
        customerId: 'user_123' 
      });

      const response = await client.models.generateContent({
        model: 'gemini-2.5-flash',
        contents: 'Explain quantum computing'
      });

      console.log('Response:', response.text);
      console.log('Usage:', response.usageMetadata);
      ```
    </CodeGroup>

    **Metrik yang Dilacak:**

    * `promptTokenCount` → `inputTokens`
    * `candidatesTokenCount` + `thoughtsTokenCount` → `outputTokens`
    * `totalTokenCount` → `totalTokens`
    * Versi model

    <Note>
      **Gemini Thinking Mode:** Saat menggunakan model Gemini dengan kemampuan berpikir/menalar (seperti Gemini 2.5 Pro), SDK secara otomatis memasukkan `thoughtsTokenCount` (token penalaran) ke dalam `outputTokens` agar mencerminkan biaya komputasi penuh secara akurat.
    </Note>
  </Accordion>
</AccordionGroup>

***

## Penggunaan Lanjutan

### Beberapa Penyedia

Lacak penggunaan di berbagai penyedia LLM dengan pelacak terpisah:

<CodeGroup>
  ```javascript Multiple Provider Setup theme={null}
  import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
  import OpenAI from 'openai';
  import Groq from 'groq-sdk';
  import Anthropic from '@anthropic-ai/sdk';
  import { GoogleGenAI } from '@google/genai';

  // Create separate trackers for different providers
  const openaiTracker = createLLMTracker({
    apiKey: process.env.DODO_PAYMENTS_API_KEY,
    environment: 'live_mode',
    eventName: 'openai.usage'
  });

  const groqTracker = createLLMTracker({
    apiKey: process.env.DODO_PAYMENTS_API_KEY,
    environment: 'live_mode',
    eventName: 'groq.usage'
  });

  const anthropicTracker = createLLMTracker({
    apiKey: process.env.DODO_PAYMENTS_API_KEY,
    environment: 'live_mode',
    eventName: 'anthropic.usage'
  });

  const geminiTracker = createLLMTracker({
    apiKey: process.env.DODO_PAYMENTS_API_KEY,
    environment: 'live_mode',
    eventName: 'gemini.usage'
  });

  const openrouterTracker = createLLMTracker({
    apiKey: process.env.DODO_PAYMENTS_API_KEY,
    environment: 'live_mode',
    eventName: 'openrouter.usage'
  });

  // Initialize clients
  const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
  const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });
  const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });
  const googleGenai = new GoogleGenAI({ apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY });
  const openrouter = new OpenAI({ 
    baseURL: 'https://openrouter.ai/api/v1',
    apiKey: process.env.OPENROUTER_API_KEY 
  });

  // Wrap clients
  const trackedOpenAI = openaiTracker.wrap({ client: openai, customerId: 'user_123' });
  const trackedGroq = groqTracker.wrap({ client: groq, customerId: 'user_123' });
  const trackedAnthropic = anthropicTracker.wrap({ client: anthropic, customerId: 'user_123' });
  const trackedGemini = geminiTracker.wrap({ client: googleGenai, customerId: 'user_123' });
  const trackedOpenRouter = openrouterTracker.wrap({ client: openrouter, customerId: 'user_123' });

  // Use whichever provider you need
  const response = await trackedOpenAI.chat.completions.create({...});
  // or
  const geminiResponse = await trackedGemini.models.generateContent({...});
  // or
  const openrouterResponse = await trackedOpenRouter.chat.completions.create({...});
  ```
</CodeGroup>

<Tip>
  Gunakan nama event berbeda untuk penyedia yang berbeda agar penggunaan terlacak secara terpisah di meter Anda.
</Tip>

### Integrasi API Express.js

Contoh lengkap mengintegrasikan pelacakan LLM ke dalam API Express.js:

<CodeGroup>
  ```javascript Express.js Server theme={null}
  import express from 'express';
  import { createLLMTracker } from '@dodopayments/ingestion-blueprints';
  import OpenAI from 'openai';

  const app = express();
  app.use(express.json());

  // Initialize OpenAI client
  const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

  // Create tracker once at startup
  const tracker = createLLMTracker({
    apiKey: process.env.DODO_PAYMENTS_API_KEY,
    environment: process.env.NODE_ENV === 'production' ? 'live_mode' : 'test_mode',
    eventName: 'api.chat_completion'
  });

  // Chat endpoint with automatic tracking
  app.post('/api/chat', async (req, res) => {
    try {
      const { message, userId } = req.body;
      
      // Validate input
      if (!message || !userId) {
        return res.status(400).json({ error: 'Missing message or userId' });
      }
      
      // Wrap client for this specific user
      const trackedClient = tracker.wrap({
        client: openai,
        customerId: userId,
        metadata: { 
          endpoint: '/api/chat',
          timestamp: new Date().toISOString()
        }
      });
      
      // Make LLM request - automatically tracked
      const response = await trackedClient.chat.completions.create({
        model: 'gpt-4',
        messages: [{ role: 'user', content: message }],
        temperature: 0.7
      });
      
      const completion = response.choices[0].message.content;
      
      res.json({ 
        message: completion,
        usage: response.usage
      });
    } catch (error) {
      console.error('Chat error:', error);
      res.status(500).json({ error: 'Internal server error' });
    }
  });

  app.listen(3000, () => {
    console.log('Server running on port 3000');
  });
  ```
</CodeGroup>

***

## Apa yang Dilacak

Setiap panggilan API LLM secara otomatis mengirimkan peristiwa penggunaan ke Dodo Payments dengan struktur berikut:

<CodeGroup>
  ```json Event Structure theme={null}
  {
    "event_id": "llm_1673123456_abc123",
    "customer_id": "customer_123",
    "event_name": "llm.chat_completion",
    "timestamp": "2024-01-08T10:30:00Z",
    "metadata": {
      "inputTokens": 10,
      "outputTokens": 25,
      "totalTokens": 35,
      "model": "gpt-4",
    }
  }
  ```
</CodeGroup>

### Bidang Peristiwa

<ParamField path="event_id" type="string">
  Pengidentifikasi unik untuk event ini. Dibuat otomatis oleh SDK.

  Format: `llm_[timestamp]_[random]`
</ParamField>

<ParamField path="customer_id" type="string">
  ID pelanggan yang Anda berikan saat membungkus klien. Digunakan untuk penagihan.
</ParamField>

<ParamField path="event_name" type="string">
  Nama event yang memicu meter Anda. Sesuai dengan konfigurasi tracker Anda.
</ParamField>

<ParamField path="timestamp" type="string">
  Timestamp ISO 8601 ketika event terjadi.
</ParamField>

<ParamField path="metadata" type="object">
  Penggunaan token dan data pelacakan tambahan:

  * `inputTokens` - Jumlah token input/prompt yang digunakan
  * `outputTokens` - Jumlah token output/completion yang digunakan (termasuk token penalaran bila berlaku)
  * `totalTokens` - Total token (input + output)
  * `model` - Model LLM yang digunakan (misalnya, "gpt-4")
  * `provider` - Penyedia LLM (jika disertakan dalam metadata wrapper)
  * Metadata khusus apa pun yang Anda berikan saat membungkus klien

  <Note>
    **Token Penalaran:** Untuk model dengan kemampuan penalaran, `outputTokens` secara otomatis mencakup token completion dan token penalaran.
  </Note>
</ParamField>

<Info>
  Meter Dodo Payments Anda menggunakan bidang `metadata` (terutama `inputTokens`, `outputTokens` atau `totalTokens`) untuk menghitung penggunaan dan penagihan.
</Info>

***