# ATOM Pricing Intelligence

ATOM Pricing Intelligence queries live AI model inference rates across multiple providers directly from your coding assistant. Useful for cutting token spend and vetting suppliers.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 4780 installs
- Author: a7om
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/a7om/atom-mcp-server
- Updated: 2026-03-04
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/atom-pricing-intelligence

## What it does

This tool links your assistant to the AIPI benchmark database, covering over 40 inference vendors and 1,600 SKUs. It provides eight functions to filter models by context length, modality, or parameter count, retrieve vendor catalogs, and inspect market-wide price distributions.

The service connects over HTTP via a hosted endpoint, so you do not need local Python or Node runtimes. The free tier works immediately without an API key.

Its `compare_prices` tool orders matching endpoints by ascending cost. That makes spotting cheaper hosted options or caching discounts straightforward before committing infrastructure budgets.

## Requirements
- Remote server: `https://atom-mcp-server--a7om.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http atom-mcp-server https://atom-mcp-server--a7om.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add atom-pricing-intelligence --url https://atom-mcp-server--a7om.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "atom-pricing-intelligence": {
            "url": "https://atom-mcp-server--a7om.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "atom-pricing-intelligence": {
            "type": "http",
            "url": "https://atom-mcp-server--a7om.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http atom-pricing-intelligence https://atom-mcp-server--a7om.run.tools
```

## When to use it
- compare inference costs for open models across hosted providers
- filter available models by context window and modality
- check average price ratios between input and generated tokens
- list inference hosts operating in specific geographic regions

## Example prompts
- Compare pricing for Llama 3.1 70B across all available providers
- Search for vision models supporting context windows above 128k
- List all models and token rates offered by Together AI

## Similar
- [InferCPI](https://affpapa.org/en/nevibecode/mcp/infercpi.md) — MCP server
- [LLM Latency Tracker](https://affpapa.org/en/nevibecode/mcp/llm-latency-tracker.md) — MCP server · ★ 12 repo stars
- [openrouter-pricing-basics](https://affpapa.org/en/nevibecode/skills/openrouter-pricing-basics.md) — skill · 2 installs
- [artificial-analysis-compare](https://affpapa.org/en/nevibecode/skills/artificial-analysis-compare.md) — skill · 1 install
- [azure-pricing](https://affpapa.org/en/nevibecode/skills/azure-pricing.md) — skill · 4700 installs
- [TokenZero](https://affpapa.org/en/nevibecode/mcp/tokenzero.md) — MCP server

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
