ATOM Pricing Intelligence — Claude Code MCP server: model price checks
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.
no license 4,780 installs updated 2026-03-04
claude mcp add --transport http atom-mcp-server https://atom-mcp-server--a7om.run.toolsWhat ATOM Pricing Intelligence 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.
What it helps with
- 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 for the agent
- 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
How to install ATOM Pricing Intelligence
Platform CLI: remote server
claude mcp add --transport http atom-mcp-server https://atom-mcp-server--a7om.run.toolsPlatform CLI: remote server
codex mcp add atom-pricing-intelligence --url https://atom-mcp-server--a7om.run.toolsConfig file
{
"mcpServers": {
"atom-pricing-intelligence": {
"url": "https://atom-mcp-server--a7om.run.tools"
}
}
}Config file
{
"servers": {
"atom-pricing-intelligence": {
"type": "http",
"url": "https://atom-mcp-server--a7om.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http atom-pricing-intelligence https://atom-mcp-server--a7om.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about ATOM Pricing Intelligence
How to install ATOM Pricing Intelligence in Claude Code?
Run claude mcp add --transport http atom-pricing-intelligence https://atom-mcp-server--a7om.run.tools in your terminal.
Do I need an API key to query inference prices?
No, the server includes a free tier that operates without any API token.
What information does get_model_detail provide?
It returns hardware context limits, parameter size, cutoff dates, and cross-vendor token prices for the requested model.