Track Every LLM Token in Node.js with all-llm-token-tracker

A developer built all-llm-token-tracker, an npm package that tracks input and output tokens for LLM API calls in Node.js. The tool supports manual recording, auto-wrapping of OpenAI and Anthropic calls, multiple storage backends (memory, file, MongoDB), and query/summarize features. It is designed to be lightweight with zero required dependencies.

node javascript openai llm Alternates: typescript, npm, webdev Use a dashboard screenshot or a simple banner with: "Track input/output LLM tokens in Node.js" If you build with OpenAI, Anthropic, or any LLM API, you've probably wondered: How many tokens did that request actually use? Token usage drives cost , performance , and scaling . But in many Node.js apps, response.usage gets logged once and forgotten. I built all-llm-token-tracker — a small npm package that tracks npm: https://www.npmjs.com/package/all-llm-token-tracker https://www.npmjs.com/package/all-llm-token-tracker GitHub: https://github.com/rkanumetta/all-llm-token-tracker https://github.com/rkanumetta/all-llm-token-tracker Most integrations look like this: js const response = await openai.chat.completions.create { ... } ; console.log response.usage ; // logged, rarely stored That works for debugging — not for production. You usually need: Many existing tools bundle pricing engines, MCP servers, or heavy infra. Sometimes you just want clean token tracking . all-llm-token-tracker does one job well: | Feature | Supported | |---|---| | Manual token recording | ✅ | | Auto-wrap LLM calls | ✅ | | OpenAI extractor | ✅ | | Anthropic extractor | ✅ | | Memory storage | ✅ | | File JSON storage | ✅ | | MongoDB storage | ✅ | | Query & summarize | ✅ | | Browser dashboard | ✅ | | Zero required deps | ✅ | Requirements: Node.js 18+ License: MIT npm install all-llm-token-tracker MongoDB storage optional : npm install all-llm-token-tracker mongodb js import { createTracker } from 'all-llm-token-tracker'; const tracker = createTracker { storage: 'memory' } ; const record = await tracker.record { provider: 'openai', model: 'gpt-4o-mini', inputTokens: 120, outputTokens: 45, metadata: { userId: 'user-123' }, } ; console.log record.totalTokens ; // 165 Each record gets a UUID, timestamp, and optional metadata. Wrap your existing function — usage is recorded automatically: js import { createTracker, extractOpenAiUsage, } from 'all-llm-token-tracker'; import OpenAI from 'openai'; const tracker = createTracker { storage: 'file', file: { filePath: './.llm-usage/usage.json' }, } ; const openai = new OpenAI ; const { result, record } = await tracker.track = openai.chat.completions.create { model: 'gpt-4o-mini', messages: { role: 'user', content: 'Hello ' } , } , { provider: 'openai', model: 'gpt-4o-mini', extractUsage: extractOpenAiUsage, metadata: { feature: 'chat' }, } ; console.log result.choices 0 .message.content ; console.log record.inputTokens, record.outputTokens ; What happens: { result, record } backNo changes to your core LLM logic — just a wrapper. js import { extractAnthropicUsage } from 'all-llm-token-tracker'; await tracker.track = anthropic.messages.create { model: 'claude-3-5-sonnet-20241022', max tokens: 1024, messages: { role: 'user', content: 'Hello ' } , } , { provider: 'anthropic', model: 'claude-3-5-sonnet-20241022', extractUsage: extractAnthropicUsage, } ; js const tracker = createTracker { storage: 'memory' } ; js const tracker = createTracker { storage: 'file', file: { filePath: './.llm-usage/usage.json' }, } ; js const tracker = createTracker { storage: 'mongodb', mongodb: { uri: process.env.MONGODB URI, database: 'my app', collection: 'llm token usage', }, } ; // on shutdown await tracker.close ; js const calls = await tracker.getCalls { provider: 'openai', from: '2026-07-01', limit: 100, } ; const summary = await tracker.getSummary ; / { totalCalls: 42, totalInputTokens: 12500, totalOutputTokens: 3200, totalTokens: 15700, averageInputTokens: 297.6, averageOutputTokens: 76.2, averageTotalTokens: 373.8 } / const byModel = await tracker.getSummaryByModel ; const byProvider = await tracker.getSummaryByProvider ; Every call is stored like this: { "id": "uuid", "provider": "openai", "model": "gpt-4o-mini", "inputTokens": 120, "outputTokens": 45, "totalTokens": 165, "timestamp": "2026-07-10T06:00:00.000Z", "durationMs": 842, "metadata": { "userId": "user-123" } } js import { createUsageExtractor } from 'all-llm-token-tracker'; const extractMyProvider = createUsageExtractor response = { inputTokens: response.tokens.in, outputTokens: response.tokens.out, } ; Or plug in your own storage Postgres, Redis, etc. : js import { createTracker, type StorageAdapter, type LlmCallRecord } from 'all-llm-token-tracker'; class PostgresStorage implements StorageAdapter { async save record: LlmCallRecord { / ... / } async find query { / ... / } async count query { / ... / } } const tracker = createTracker { storage: new PostgresStorage } ; The repo includes a simple dashboard to visualize input vs output tokens: git clone https://github.com/rkanumetta/all-llm-token-tracker.git cd all-llm-token-tracker npm install npm run example npm run dashboard You'll see: npm install all-llm-token-tracker Links: If you find it useful, star the repo ⭐ and open an issue if you want support for another provider Gemini, Mistral, etc. . LLM token tracking doesn't need to be complicated. Wrap your API calls, store consistent records, query when you need insights. Track input. Track output. Store it. Query it. Done. What storage backend do you use for LLM observability — file, MongoDB, or something else? Drop a comment below. node , javascript , openai , llm Paste this as the first line under the title if DEV shows a preview/subtitle field: A lightweight Node.js npm package to track input/output tokens for OpenAI, Anthropic, and custom LLM providers — with memory, file, and MongoDB storage plus a browser dashboard.