ai-price-index-mcp
This server provides a read-only interface to the AI Price Index, letting you query current and historical AI model API prices locally — no API keys required.
Look up current prices (
current_price): Get today's input/output price per million tokens for any supported model (e.g.,gpt-4o,claude-opus-4-5,gemini-2.5-pro), along with the source URL.Look up prices on a specific date (
price_on): Retrieve the exact price in effect on any past date (YYYY-MM-DD) — useful for auditing costs or tracking price changes over time.Compare multiple models side-by-side (
compare): Get input/output prices for several models at once, for today or a specific historical date.Calculate cost from token usage (
cost_from_usage): Compute the USD cost from a token rollup (input, output, cache reads/writes) for a given model at a point in time, with built-in cache multipliers.Discover available models (
list_models): List all known model IDs and aliases, optionally filtered by provider (e.g.,anthropic,openai,google).
All results include cite-ready provenance: source_url, last_validated, confidence, and a CC BY 4.0 attribution string. Short/aliased model IDs are supported and resolve to canonical names.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ai-price-index-mcp What was the price of gpt-4 on January 1, 2024?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ai-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-mcpThat command runs the stdio server; an MCP client launches it for you using the config below.
Related MCP server: statlyte
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-mcpTools
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 |
|
| Today's input/output price for a model, with its source. |
|
| The price in effect on that date (the point-in-time lookup). |
|
| Side-by-side input/output prices for several models on one date. |
|
| USD value of a token rollup at a point in time, with cache multipliers. |
|
| 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
Available Tools
5 toolscompareCompare modelsA
Side-by-side input/output prices for several model ids on one date (today by default, or pass date as YYYY-MM-DD). Each row resolves independently; unknown ids are reported per row.
Inputs: models (required), date.
cost_from_usageCost from token usageA
Value a token rollup in USD at a point in time, using the shared cache multipliers (cache read 0.1x input, cache write 1.25x for 5m / 2x for 1h). tokens accepts input, output, cache_read, cache_write_5m, cache_write_1h. Defaults to today if no date is given.
Inputs: model (required), tokens (required), date, provider.
current_priceCurrent priceA
Today's input and output price per million tokens (usd_per_mtok) for a model id, with the first-party source. Accepts short or aliased ids (e.g. "claude-opus-4-8", "gpt-4o", "gemini-2.5-pro"). Pass provider to disambiguate a bare id shared across vendors.
Inputs: model (required), provider.
list_modelsList modelsA
List the model ids known to the dataset, optionally filtered to one provider, each with its provider and aliases. Use this to discover valid ids for the other tools.
Inputs: provider.
price_onPrice on a dateA
The input and output price per million tokens that was IN EFFECT on a given date (YYYY-MM-DD), with the source that proves it. This is the point-in-time lookup: use it to value past usage or to see how a price changed over time. covered=false means the date predates the model's recorded coverage.
Inputs: model (required), date (required), provider.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool serves a distinct purpose: compare for side-by-side price comparison, cost_from_usage for token cost calculation, current_price for today's price, list_models for model discovery, and price_on for historical price lookup. There is no functional overlap.
Names are all lowercase with underscores for multi-word terms (e.g., cost_from_usage, current_price). While not strictly verb-noun (compare is verb-only, price_on is noun-preposition), the pattern is consistent and readable, with no mixing of conventions.
Five tools is well-scoped for an AI pricing index: listing models, current and historical prices, comparison, and cost estimation. Each tool earns its place without unnecessary redundancy or shortage.
The tool set covers the core lifecycle: discovery, current price, historical price, comparison, and cost calculation. A minor gap is the lack of historical cost calculation using past multipliers, but this does not severely impair agent workflows.
Maintenance
Related MCP Connectors
Look up, compare and track AI model API prices from an AI assistant. No sign-in needed.
LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.
Read-only lookups of public AI agent pricing, free plans and source links. No API key.
Dated, sourced AI API prices, model retirements and AI app facts. Read-only, no key needed.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides live LLM pricing data from OpenRouter, enabling agents to search models, get pricing, estimate costs, and compare models.25 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables assistants to access up-to-date LLM pricing, context windows, and model identifiers, with tools to estimate costs, find cheapest models, and check scheduled price changes.61 npmMIT

indextkn MCP serverofficial
AlicenseNot gradedqualityCmaintenanceEnables agents to query live AI model pricing, compare providers, and calculate token workload costs from current published prices.MIT
apipriceindex-mcpofficial
AlicenseAqualityBmaintenanceGives AI agents live, verified LLM API prices from apipriceindex.com, enabling cost estimation, model search, and price lookups with verification metadata.888 PyPIMIT