MCP server · Analytics
LLM Prices MCP server
by romanshumy
Lets your AI look up live token prices for 220 AI models and find the cheapest one for a job.
This is a small helper that connects your AI assistant to a live price list for AI models. The list covers 220 models from 36 companies, like OpenAI, Anthropic, Google and Mistral, and it is checked against the providers' own pricing pages every day. It is handy if you are comparing AI costs or need to pick a cheaper model for a task.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. It cannot see today's prices anywhere. An MCP server is a small helper program that gives your AI a new skill or a connection to a service. This one connects your AI to a live pricing database at modelpricewatch.com, so when you ask about model costs, your AI can look them up and answer with current numbers instead of guessing.
What this MCP server does
You ask your AI a question about AI model prices, for example which model is cheapest for a long document. Your AI passes that question to this helper. The helper talks to the modelpricewatch.com pricing data and finds the matching models and prices. Your AI then reads the results back to you in the chat. You get numbers, comparisons and answers without opening a spreadsheet or a website.
Click to zoomWhat you can do with it
- Look up the input and output price per million tokens for a model
- Compare prices across several models side by side
- Find the cheapest model that fits a budget or a task
- Check the context window and modality of a model
- See the LLM Price Index, one number for the blended cost of frontier models
- Browse price history for a model over time
- Read recent price changes and new model launches
Try asking your AI
- “What is the cheapest model for summarizing long documents right now?”
- “Compare the input and output prices of GPT-4o, Claude Sonnet and Gemini Pro.”
- “What is the current LLM Price Index?”
- “Show me recent price changes for DeepSeek models.”
What it gives back to you
You get answers in plain chat text: prices per million tokens, short comparisons, the name of the cheapest model, or the current index number. Some answers come as small tables or lists of models with their prices. If you ask about history, you get a timeline of dated price points. Everything is read-only, so nothing in your own files or accounts is changed.
Before you start
What you need
- An AI app that supports MCP servers, such as Claude Desktop or Cursor
- Node.js 18 or newer if you run the npx version locally
- Internet access to reach modelpricewatch.com
Good to know
Prices change often, so treat the numbers as a helpful snapshot and check the provider's official page before you make a spending decision.
Install it with your AI
Add LLM Prices MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check LLM Prices MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Anyone who compares AI model costs, like product managers, finance teams, developers choosing a model, and writers budgeting their AI spend.
