Track and manage token usage across multiple AI providers (OpenAI, Anthropic, Gemini) with comprehensive cost analysis and session monitoring.
Real-time tracking: Monitor token consumption automatically via API client wrappers or manually, with session progress bars showing used/remaining tokens against configurable budgets
Cost analysis: Calculate costs in USD and KRW with real-time exchange rates, compare pricing between models, and access up-to-date 2025 pricing
User management: Track usage per user with customizable budgets, retrieve individual or overview summaries, and clear user-specific data
Data persistence: Maintain session data across server restarts with automatic historical tracking
MCP integration: Use as a Model Context Protocol server in Claude Desktop for real-time conversation tracking and cost monitoring
Provides automatic token usage tracking and cost calculation for OpenAI API calls, supporting all GPT models including GPT-4, GPT-3.5 Turbo, DALL-E 3, and Whisper with real-time usage monitoring and pricing.
LLM Token Tracker š§®
Token usage tracker for OpenAI, Claude, and Gemini APIs with MCP (Model Context Protocol) support. Pass accurate API costs to your users.
⨠Features
šÆ Simple Integration - One line to wrap your API client
š Automatic Tracking - No manual token counting
š° Accurate Pricing - Up-to-date pricing for all models (2025)
š Multiple Providers - OpenAI, Claude, and Gemini support
š User Management - Track usage per user/session
š Currency Support - USD and KRW
š¤ MCP Server - Use directly in Claude Desktop!
š Intuitive Session Tracking - Real-time usage with progress bars
š¦ Installation
š Quick Start
Option 1: Use as Library
š§ With Real APIs
To use with actual OpenAI/Anthropic APIs:
Option 2: Use as MCP Server
Add to Claude Desktop settings (~/Library/Application Support/Claude/claude_desktop_config.json):
Then in Claude:
"Calculate current session usage" - See current session usage with intuitive format
"Calculate current conversation cost" - Get cost breakdown with input/output tokens
"Track my API usage"
"Compare costs between GPT-4 and Claude"
"Show my total spending today"
Available MCP Tools
get_current_session- š Get current session usage (RECOMMENDED)Returns: Used/Remaining tokens, Input/Output breakdown, Cost, Progress bar
Default user_id:
current-sessionDefault budget: 190,000 tokens
Perfect for real-time conversation tracking!
track_usage- Track token usage for an AI API callParameters: provider, model, input_tokens, output_tokens, user_id
get_usage- Get usage summary for specific user or all userscompare_costs- Compare costs between different modelsclear_usage- Clear usage data for a user
Example MCP Output
š Supported Models & Pricing (Updated 2025)
OpenAI (2025)
Model | Input (per 1K tokens) | Output (per 1K tokens) | Notes |
GPT-5 Series | |||
GPT-5 | $0.00125 | $0.010 | Latest flagship model |
GPT-5 Mini | $0.00025 | $0.0010 | Compact version |
GPT-4.1 Series | |||
GPT-4.1 | $0.0020 | $0.008 | Advanced reasoning |
GPT-4.1 Mini | $0.00015 | $0.0006 | Cost-effective |
GPT-4o Series | |||
GPT-4o | $0.0025 | $0.010 | Multimodal |
GPT-4o Mini | $0.00015 | $0.0006 | Fast & cheap |
o1 Reasoning Series | |||
o1 | $0.015 | $0.060 | Advanced reasoning |
o1 Mini | $0.0011 | $0.0044 | Efficient reasoning |
o1 Pro | $0.015 | $0.060 | Pro reasoning |
Legacy Models | |||
GPT-4 Turbo | $0.01 | $0.03 | |
GPT-4 | $0.03 | $0.06 | |
GPT-3.5 Turbo | $0.0005 | $0.0015 | Most affordable |
Media Models | |||
DALL-E 3 | $0.040 per image | - | Image generation |
Whisper | $0.006 per minute | - | Speech-to-text |
Anthropic (2025)
Model | Input (per 1K tokens) | Output (per 1K tokens) | Notes |
Claude 4 Series | |||
Claude Opus 4.1 | $0.015 | $0.075 | Most powerful |
Claude Opus 4 | $0.015 | $0.075 | Flagship model |
Claude Sonnet 4.5 | $0.003 | $0.015 | Best for coding |
Claude Sonnet 4 | $0.003 | $0.015 | Balanced |
Claude 3 Series | |||
Claude 3.5 Sonnet | $0.003 | $0.015 | |
Claude 3.5 Haiku | $0.00025 | $0.00125 | Fastest |
Claude 3 Opus | $0.015 | $0.075 | |
Claude 3 Sonnet | $0.003 | $0.015 | |
Claude 3 Haiku | $0.00025 | $0.00125 | Most affordable |
Google Gemini (2025)
Model | Input (per 1K tokens) | Output (per 1K tokens) | Notes |
Gemini 2.0 Series | |||
Gemini 2.0 Flash (Exp) | Free | Free | Experimental preview |
Gemini 2.0 Flash Thinking | Free | Free | Reasoning preview |
Gemini 1.5 Series | |||
Gemini 1.5 Pro | $0.00125 | $0.005 | Most capable |
Gemini 1.5 Flash | $0.000075 | $0.0003 | Fast & efficient |
Gemini 1.5 Flash-8B | $0.0000375 | $0.00015 | Ultra-fast |
Gemini 1.0 Series | |||
Gemini 1.0 Pro | $0.0005 | $0.0015 | Legacy model |
Gemini 1.0 Pro Vision | $0.00025 | $0.0005 | Multimodal |
Gemini Ultra | $0.002 | $0.006 | Premium tier |
Note: Prices shown are per 1,000 tokens. Batch API offers 50% discount. Prompt caching can reduce costs by up to 90%.
šÆ Examples
Run the example:
Check examples/basic-usage.js for detailed usage patterns.
š API Reference
new TokenTracker(config)
config.currency: 'USD' or 'KRW' (default: 'USD')config.webhookUrl: Optional webhook for usage notifications
tracker.wrap(client)
Wrap an OpenAI or Anthropic client for automatic tracking.
tracker.forUser(userId)
Create a user-specific tracker instance.
tracker.startTracking(userId?, sessionId?)
Start manual tracking session. Returns tracking ID.
tracker.endTracking(trackingId, usage)
End tracking and record usage.
tracker.getUserUsage(userId)
Get total usage for a user.
tracker.getAllUsersUsage()
Get usage summary for all users.
š Development
š License
MIT
š¤ Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
š Issues
For bugs and feature requests, please create an issue.
š¦ What's New in v2.4.0
š Gemini API Support - Full integration with Google's Gemini models
š Gemini 2.0 Support - Free preview models included
š Enhanced Pricing - Up-to-date Gemini 1.5 and 2.0 pricing
š§ Auto-detection - Automatic Gemini client wrapping
š° Cost Comparison - Compare Gemini with OpenAI and Claude
š¦ What's New in v2.3.0
š± Real-time exchange rates - Automatic USD to KRW conversion
š Uses exchangerate-api.com for accurate rates
š¾ 24-hour caching to minimize API calls
š New
get_exchange_ratetool to check current ratesš Background auto-updates with fallback support
What's New in v2.2.0
šļø File-based persistence - Session data survives server restarts
š¾ Automatic saving to
~/.llm-token-tracker/sessions.jsonš Works for both npm and local installations
š Historical data tracking across sessions
šÆ Zero configuration required - just works!
What's New in v2.1.0
š Added
get_current_sessiontool for intuitive session trackingš Real-time progress bars and visual indicators
š° Enhanced cost breakdown with input/output token separation
šØ Improved formatting with thousands separators
š§ Better default user_id handling (
current-session)
Built with ā¤ļø for developers who need transparent AI API billing.
Token usage tracker for OpenAI and Claude APIs with MCP (Model Context Protocol) support.