MCP 服务器

ohmytoken

Provides real-time token pricing for AI models, model comparison, cost calculation, and token usage tracking for agents and developers.

README

🪙

<h1 align="center">OhMyToken</h1>

AI Token Price Intelligence for Agents & Developers

<a href="https://www.ohmytoken.com">Website</a> · <a href="https://www.ohmytoken.com/agents.txt">agents.txt</a> · <a href="#mcp-server">MCP Server</a> · <a href="#rest-api">REST API</a> · <a href="#token-tracker">Token Tracker</a>

Real-time token pricing for 23 AI models across 8 providers (Anthropic, OpenAI, Google, DeepSeek, Zhipu, MiniMax, Moonshot, Alibaba). Built for agents — not just humans.

Features

Price Intelligence

Real-time pricing table with sorting, filtering by provider/category/open-source
Token cost calculator — input your usage, see daily/monthly costs across all models
Price evolution timeline — from GPT-4 ($30/MTok) to DeepSeek V3 ($0.3/MTok)

Agent-First Design

MCP Server — 5 tools for price queries, model comparison, smart recommendations
Token Tracker — 5 tools for consumption logging, budget management, efficiency analysis
REST API — 12 endpoints for programmatic access
agents.txt — Machine-readable service description at /agents.txt

Bilingual — Chinese / English with automatic RMB / USD currency conversion

Quick Start

git clone https://github.com/LangGPT/ohmytoken.git
cd ohmytoken
npm install
npm run build
npm run dev        # → http://localhost:18090

MCP Server

Add to your Claude Code settings.json:

{
  "mcpServers": {
    "ohmytoken": {
      "command": "npx",
      "args": ["tsx", "src/mcp/index.ts"]
    }
  }
}

Tools:

Tool	Description
`get_token_price`	Get real-time pricing for any model or provider
`compare_models`	Side-by-side comparison of 2+ models
`recommend_model`	Smart recommendation by task, budget, preferences
`calculate_cost`	Estimate costs for a workload across all models
`get_price_trends`	Historical token price trends since 2023

Token Tracker

Every agent deserves a financial dashboard. Track your token spending like wandb tracks experiments.

{
  "mcpServers": {
    "ohmytoken-tracker": {
      "command": "npx",
      "args": ["tsx", "src/mcp/tracker.ts"]
    }
  }
}

Tools:

Tool	Description
`token_log`	Record token consumption (cost auto-calculated)
`token_usage`	Query spending by period, model, or task
`token_budget`	Set daily/monthly limits with auto-warnings
`token_analyze`	Spending patterns and optimization suggestions
`token_leaderboard`	Multi-agent ranking — who's most efficient?

Data stored in ~/.ohmytoken/ledger.jsonl (append-only, portable).

REST API

Base URL: https://www.ohmytoken.com/api (or http://localhost:18090/api)

# All models
curl /api/models?provider=anthropic

# Cost calculation
curl -X POST /api/calculate \
  -d '{"inputTokens":1000000,"outputTokens":500000,"requestsPerDay":100}'

# Smart recommendation
curl -X POST /api/recommend \
  -d '{"task":"coding","preferOpenSource":true}'

# Log agent token usage
curl -X POST /api/tracker/log \
  -d '{"agent_id":"my-agent","model":"claude-opus-4-6","input_tokens":5000,"output_tokens":1000}'

# Agent leaderboard
curl /api/tracker/leaderboard

Models Covered

Provider	Models	Price Range (Input $/MTok)
Anthropic	Opus 4.6, Sonnet 4.5, Haiku 4.5	$1 — $5
OpenAI	GPT-5.2, GPT-4.1, o3, o4-mini	$0.1 — $2
Google	Gemini 2.5 Pro, 2.5 Flash, 2.0 Flash	$0.1 — $1.25
DeepSeek	V3, R1	$0.3 — $0.7
Zhipu	GLM-5, GLM-5 Code, GLM-4.7	$0.07 — $1.2
MiniMax	M2.1	$0.3
Moonshot	Kimi K2, Kimi K2.5	$0.6
Alibaba	Qwen3-Max, QwQ-Plus	$0.8 — $1.2

Project Structure

ohmytoken/
├── src/
│   ├── client/          # React SPA (bilingual, light theme)
│   │   ├── components/  # PriceTable, Calculator, Timeline, AgentDashboard, ...
│   │   ├── i18n.ts      # zh/en translations, RMB/USD conversion
│   │   └── styles.css   # Light theme with glass morphism
│   ├── server/          # Express API server (port 18090)
│   ├── mcp/
│   │   ├── index.ts     # Price intelligence MCP server
│   │   └── tracker.ts   # Token consumption tracker MCP server
│   └── shared/          # Types, data, tracker storage
├── docs/                # GitHub Pages static build
├── public/              # Static assets (index.html, agents.txt)
└── build.js             # esbuild bundler