ohmytoken
Provides real-time token pricing for AI models, model comparison, cost calculation, and token usage tracking for agents and developers.
README
<p align="center"> <span style="font-size:64px">๐ช</span> </p>
<h1 align="center">OhMyToken</h1>
<p align="center"> <strong>AI Token Price Intelligence for Agents & Developers</strong> </p>
<p align="center"> <a href="https://www.ohmytoken.com">Website</a> ยท <a href="https://www.ohmytoken.com/agents.txt">agents.txt</a> ยท <a href="#mcp-server">MCP Server</a> ยท <a href="#rest-api">REST API</a> ยท <a href="#token-tracker">Token Tracker</a> </p>
<p align="center"> <img src="https://img.shields.io/badge/models-23+-6366F1" alt="Models" /> <img src="https://img.shields.io/badge/providers-8-3B82F6" alt="Providers" /> <img src="https://img.shields.io/badge/MCP_tools-10-10B981" alt="MCP Tools" /> <img src="https://img.shields.io/badge/i18n-zh%20%7C%20en-F59E0B" alt="i18n" /> <img src="https://img.shields.io/badge/license-MIT-gray" alt="License" /> </p>
Real-time token pricing for 23 AI models across 8 providers (Anthropic, OpenAI, Google, DeepSeek, Zhipu, MiniMax, Moonshot, Alibaba). Built for agents โ not just humans.
Features
Price Intelligence
- Real-time pricing table with sorting, filtering by provider/category/open-source
- Token cost calculator โ input your usage, see daily/monthly costs across all models
- Price evolution timeline โ from GPT-4 ($30/MTok) to DeepSeek V3 ($0.3/MTok)
Agent-First Design
- MCP Server โ 5 tools for price queries, model comparison, smart recommendations
- Token Tracker โ 5 tools for consumption logging, budget management, efficiency analysis
- REST API โ 12 endpoints for programmatic access
- agents.txt โ Machine-readable service description at
/agents.txt
Bilingual โ 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 # โ 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 โ 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 โ $5 |
| OpenAI | GPT-5.2, GPT-4.1, o3, o4-mini | $0.1 โ $2 |
| Gemini 2.5 Pro, 2.5 Flash, 2.0 Flash | $0.1 โ $1.25 | |
| DeepSeek | V3, R1 | $0.3 โ $0.7 |
| Zhipu | GLM-5, GLM-5 Code, GLM-4.7 | $0.07 โ $1.2 |
| MiniMax | M2.1 | $0.3 |
| Moonshot | Kimi K2, Kimi K2.5 | $0.6 |
| Alibaba | Qwen3-Max, QwQ-Plus | $0.8 โ $1.2 |
Project Structure
ohmytoken/
โโโ src/
โ โโโ client/ # React SPA (bilingual, light theme)
โ โ โโโ components/ # PriceTable, Calculator, Timeline, AgentDashboard, ...
โ โ โโโ i18n.ts # zh/en translations, RMB/USD conversion
โ โ โโโ styles.css # Light theme with glass morphism
โ โโโ server/ # Express API server (port 18090)
โ โโโ mcp/
โ โ โโโ index.ts # Price intelligence MCP server
โ โ โโโ tracker.ts # Token consumption tracker MCP server
โ โโโ shared/ # Types, data, tracker storage
โโโ docs/ # GitHub Pages static build
โโโ public/ # Static assets (index.html, agents.txt)
โโโ build.js # esbuild bundler
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.