Atom Pricing Intelligence
@A7OM-AI
ATOM: The Global Price Benchmark for AI Inference. MCP server access to the AIPI index family.
Overview
What is Atom Pricing Intelligence?
Atom Pricing Intelligence is an MCP server that lets any MCP‑compatible AI agent (e.g., Claude, GPT, Cursor) query live AI inference pricing data programmatically. Built on financial index methodology comparable to S&P Dow Jones, MSCI, and Bloomberg, it delivers the ATOM Inference Price Index (AIPI) — the first independent benchmark for the AI inference market. It is designed for developers, analysts, and infrastructure buyers who need transparent, deterministic pricing intelligence.
How to use Atom Pricing Intelligence?
Connect via remote URL to Claude.ai or Claude Desktop (no install required), or use local stdio for Cursor, Windsurf, and similar clients. For the free tier no API key is needed; the Pro tier requires a subscription from a7om.com/mcp. You can also deploy your own instance on Railway using the provided environment variables.
Key features of Atom Pricing Intelligence
- Free tier: vendors, KPIs, model intelligence, AIPI index benchmarks
- Tiered tools: search, compare, vendor catalog, model detail
- AIPI index family across modality, channel, tier, and special
- Weekly updated chained matched‑model methodology
- Transparent methodology and deterministic indexing
- Works with any MCP‑compatible AI agent
Use cases of Atom Pricing Intelligence
- Ask “What’s the cheapest way to run GPT‑4o?” and get a data‑backed answer.
- Compare pricing for a model family across all tracked vendors.
- Find open‑source text models under a price per million tokens.
- Get a market overview of AI inference pricing including medians and distributions.
- Understand how much cheaper open‑source inference is vs. proprietary models.
FAQ from Atom Pricing Intelligence
What does Atom Pricing Intelligence do that alternatives don’t?
It is the first independent benchmark for the AI inference market, built on financial index methodology, providing transparent and deterministic pricing intelligence across the global vendor landscape.
What dependencies or runtime requirements does it have?
The server is built with TypeScript/Node.js, MCP SDK, Supabase, Express, and Zod. For local deployment, you need Node.js and a Supabase project with the provided environment variables.
Where does the data live?
The pricing data is stored in a Supabase (PostgreSQL) database and accessed via REST API. The hosted server is available at a Railway URL; local deployments connect to the same Supabase instance.
What transports and authentication are supported?
Transport can be either stdio (default) or http. The free tier requires no authentication; the Pro tier uses comma‑separated API keys set via the ATOM_API_KEYS environment variable.
Is there a limit on the free tier?
The free tier provides full access to vendors, KPIs, model intelligence, and AIPI indexes, but only aggregated market stats, model counts and price ranges, specs‑only model detail, and summary vendor catalogs. Pro tier unlocks vendor‑level breakdowns, full granular SKU data, and per‑vendor pricing.