Atom Pricing Intelligence

Name: Atom Pricing Intelligence
Author: A7OM-AI

@A7OM-AI

Repository Homepage

About Atom Pricing Intelligence

ATOM: The Global Price Benchmark for AI Inference. MCP server access to the AIPI index family.

#ai #pricing #inference #mcp #llm #benchmark #fintech #market-data

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "atom-pricing-intelligence": {
      "url": "https://atom-mcp-server-production.up.railway.app/mcp"
    }
  }
}

Tools

Search and filter AI inference models across 40+ vendors and 1,600+ SKUs. Query by modality (Text, Image, Audio, Video, Multimodal), vendor, creator, model family, open-source status, price range, context window, and parameter count. Returns matching models with pricing. Free tier shows count + price range; paid tier shows full details. Examples: - "Find open-source text models under $1/M tokens" → open_source=true, modality="Text", max_price=0.001 - "What multimodal models does Google offer?" → vendor="Google", modality="Multimodal" - "Models with 128K+ context window" → min_context_window=128000

Deep dive on a single AI model: technical specs + pricing across all vendors. Returns model_registry data (context window, parameters, open-source status, training cutoff, model family) plus all SKU pricing across every vendor that offers this model. Examples: - "Tell me everything about GPT-4o" → model_name="GPT-4o" - "Claude Sonnet 4.5 specs and pricing" → model_name="Claude Sonnet 4.5"

Cross-vendor price comparison for a specific model or model family. Shows the same model (or family) priced across different vendors, sorted cheapest first. Essential for cost optimization and vendor selection. Examples: - "Compare Llama 3.1 70B pricing across vendors" → model_name="Llama 3.1 70B" - "Cheapest GPT-4 family output pricing" → model_family="GPT-4", direction="Output" - "Claude pricing comparison" → model_family="Claude"

Full catalog for a specific vendor: all models, modalities, and pricing. Returns vendor metadata (country, region, pricing page URL) plus every model and SKU they offer. Examples: - "What does Together AI sell?" → vendor="Together AI" - "OpenAI's text model pricing" → vendor="OpenAI", modality="Text" - "Amazon Bedrock catalog" → vendor="Amazon Bedrock"

Aggregate AI inference market intelligence. Returns total vendor/model/SKU counts, price distribution (median, mean, quartiles, min/max), and modality breakdown. Optionally filter by modality. Examples: - "AI inference market overview" → (no params) - "Text model pricing statistics" → modality="Text" - "Image generation market stats" → modality="Image"

AIPI (ATOM Inference Price Index) — chained matched-model price benchmarks for AI inference. Returns benchmark prices across index families (Text, Image, Audio, Video, Multimodal, Composite) with input, cached, and output pricing per period. These are market-wide benchmarks, not individual vendor prices. Use them to understand where the market is and how it's moving. Fully public — available to all tiers. Examples: - "What's the current benchmark for text inference?" → index_category="Text" - "Show me all AIPI indexes" → (no params) - "AIPI-TXT-GLB history" → index_code="AIPI-TXT-GLB"

ATOM Inference Price Index (AIPI) market-level KPIs. Returns 6 key performance indicators derived from 1,600+ SKUs: - Output Premium: how much more output tokens cost vs input - Caching Savings: average discount for cached input pricing - Open Source Advantage: price difference between open-source and proprietary - Context Cost Curve: price multiplier for larger context windows - Caching Availability: % of models offering cached pricing - Size Spread: price ratio between largest and smallest models These KPIs are available to all tiers — they demonstrate ATOM's market intelligence.

List all 41 AI inference vendors tracked by ATOM. Returns vendor name, country, region, and pricing page URL. Optionally filter by region or country. Examples: - "List all vendors" → (no params) - "European AI vendors" → region="Europe" - "Chinese AI vendors" → country="China"

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.

Comments

More Other MCP servers

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K