MCP server · Research
API Price Index MCP server
Lets your AI look up live, verified prices for AI models and estimate your monthly bill.
This is a small helper that connects your AI assistant to a live price list for AI models. You can ask what a model costs per million words in and out, or what your monthly usage would run, and you get an answer with a source and a date. It is handy for anyone comparing AI model costs before they commit.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using what it already learned, which goes out of date. An MCP server is a small helper program that gives your AI a new skill or a connection to a service, in this case to the API Price Index. Once it is connected, your AI can look up current model prices and run cost estimates for you on the spot. You just ask in normal words, and the AI uses this helper behind the scenes.
What this MCP server does
You ask your AI something like what 200 million input and 15 million output tokens a month would cost on two different models. Your AI sends that question to this helper, which checks the live index at apipriceindex.com. The index returns the price for each model with the date it was verified, a confidence level, and a link to the source. Your AI then shows you the numbers, ranked cheapest first if you asked for a comparison. If the index is unreachable or a model is not tracked, you get a clear error instead of a made-up number.
What you can do with it
- Look up the input and output price of a specific AI model
- Search for models by name or provider
- Filter models by context window size or whether the weights are open
- Estimate the monthly bill for a workload you describe
- Rank several models from cheapest to most expensive for your usage
- See the verification date and source link behind each price
Try asking your AI
- “What would 200M input and 15M output tokens a month cost on Claude Sonnet versus GPT-4o?”
- “Show me the current price per million tokens for Gemini 1.5 Pro, with the source.”
- “Rank these three models cheapest first for 50M input and 5M output tokens a month.”
- “Which tracked models have at least a 128k context window and open weights?”
What it gives back to you
You get back plain numbers in the chat: price per million tokens for input, output, and cached input where the provider publishes one. For a cost estimate you get a ranked list with the monthly total for each model. Every price comes with a verification date, a confidence level, and a source link so you can check it yourself. If something is missing or the index is down, you get a short error message instead of a guess.
Before you start
What you need
- Python installed on your computer
- The apipriceindex-mcp package installed with pip
- An MCP client such as Claude Desktop or Claude Code
Good to know
It only knows about prices, so it cannot tell you how good a model is and it only has prices for models the index tracks.
Install it with your AI
Add API Price Index 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 API Price Index 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 4,361 MCP servers here for you.
Who it's for
Anyone who compares AI model costs, like product managers, finance folks, or developers picking a model for a project.
