ai-price-index-mcp

AI model prices for when quality matters - first-party-sourced, dated, point-in-time, and human-verified.

A read-only, zero-key Model Context Protocol server that lets a coding agent (Claude Code, Cursor, and any other MCP client) query the open AI Price Index: dated, first-party-sourced AI model API prices.

Most pricing tools tell an agent what a model costs today. This one also answers what a model cost on a given date, and returns the first-party source URL plus the date that price was last validated, so the agent can cite the number. That point-in-time lookup is the differentiator.

• Zero keys, zero prompts, zero network at runtime. The dated dataset is bundled inline inside the ai-price-index dependency. The server reads it locally and adds nothing to your traffic.
• Read-only. It only looks prices up. It cannot write, configure, or call out.
• Cite-ready. Every result carries source_url, last_validated, confidence, and the CC BY 4.0 attribution string.

Install

Requires Node.js 18 or newer. No build step, no API key.

npx -y ai-price-index-mcp

That command runs the stdio server; an MCP client launches it for you using the config below.

Client configuration

Drop this into your MCP client config. The server speaks stdio.

Claude Code (~/.claude.json or a project .mcp.json), and Cursor (~/.cursor/mcp.json), use the same mcpServers shape:

{
  "mcpServers": {
    "ai-price-index": {
      "command": "npx",
      "args": ["-y", "ai-price-index-mcp"]
    }
  }
}

Or, with Claude Code's CLI:

claude mcp add ai-price-index -- npx -y ai-price-index-mcp

Tools

All tools return structured JSON as text content. Prices are usd_per_mtok (USD per million tokens). Model ids resolve through the dataset's aliases, so short ids work (e.g. claude-opus-4-5 resolves to claude-opus-4-5-20251101).

tokens for cost_from_usage accepts input, output, cache_read, cache_write_5m, cache_write_1h (all optional, missing counts as 0). Cache read is 0.1x input, cache write is 1.25x (5 minute) or 2x (1 hour).

Pass provider (for example openai, anthropic, google) to disambiguate a bare id that exists under more than one vendor.

Example result

price_on with { "model": "gpt-4", "date": "2024-01-01" }:

{
  "query": "gpt-4",
  "provider": "openai",
  "model": "gpt-4",
  "date": "2024-01-01",
  "covered": true,
  "input": {
    "usd_per_mtok": 30,
    "unit": "usd_per_mtok",
    "effective_from": "2023-03-14",
    "effective_to": null,
    "last_validated": "2023-04-15",
    "confidence": "archived",
    "source_url": "https://web.archive.org/web/20230415223802/https://openai.com/pricing"
  },
  "output": { "usd_per_mtok": 60, "...": "..." },
  "provenance": {
    "dataset": "AI Price Index by RoninForge",
    "data_version": "2026-06-17",
    "license": "CC-BY-4.0",
    "attribution": "AI Price Index by RoninForge (https://roninforge.org/data/ai-price-index/), CC BY 4.0",
    "source": "https://roninforge.org/data/ai-price-index/"
  }
}

How it works

This server is a thin wrapper over the ai-price-index npm library, which ships the dated dataset bund

... View full README on GitHub