About AI Price Index
AI Price Index is a read-only, local MCP server for developers and agents looking up AI model API prices without API keys. It supports historical date queries and returns source links and validation dates for citing price data.
Key features
- 01Look up current model prices
- 02Retrieve prices for a past date
- 03Compare prices across models
- 04Estimate costs from token usage
- 05List models and aliases
Use cases
- 01Verify a model's price on a specific date
- 02Compare input and output rates across models
- 03Estimate API costs from token usage
MCP support
It provides five read-only tools to MCP clients over stdio, querying a local dataset bundled with its npm dependency. Results include source URLs, validation dates, confidence, and data attribution.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
5Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model id or alias, e.g. "claude-opus-4-8" or "gpt-4o". |
| provider | string | No | Optional provider slug (e.g. "openai", "anthropic") to disambiguate a bare id. |
Details
From the project READMEai-price-index-mcp
RoninForge ai-price-index-mcp is a read-only Model Context Protocol server that answers what an AI model's API price was on a given date, with the first-party source that proves it. It is MIT licensed, runs entirely on your machine, and requires no API keys.
Part of RoninForge.org, an independent open-source workshop that keeps dated, reproducible records of the AI developer tooling economy. It serves the open AI Price Index dataset to any MCP client, including Claude Code and Cursor.
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-indexdependency. 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).
| Tool | Arguments | Returns |
|---|---|---|
current_price | model, provider? | Today's input/output price for a model, with its source. |
price_on | model, date (YYYY-MM-DD), provider? | The price in effect on that date (the point-in-time lookup). |
compare | models[], date? | Side-by-side input/output prices for several models on one date. |
cost_from_usage | model, tokens, date?, provider? | USD value of a token rollup at a point in time, with cache multipliers. |
list_models | provider? | Known model ids (optionally one provider), each with its aliases. |
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 bundled inline. There is no pricing logic, no separate data
layer, and no network call here. The data version a result reports is the dataset release that the
installed ai-price-index pins to. To move to newer prices, update that dependency.
Data license and attribution
The price data is from the AI Price Index and is licensed CC BY 4.0. When you publish anything derived from it, attribute it:
AI Price Index by RoninForge (https://roninforge.org/data/ai-price-index/), CC BY 4.0.
The code of this server is licensed MIT (see LICENSE). Data and tooling licenses are tracked upstream in the ai-price-index repository.
Links
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.