llm-cost

Name: llm-cost
Author: comparedge

@comparedge

リポジトリホームページドキュメント

llm-cost について

MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge

#llm #pricing #tokens #cost-estimation #api-pricing #ai-models

基本情報

カテゴリ

データと分析

ライセンス

MIT

ランタイム

node

公開者

comparedge

投稿者

KMT Dev

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "llm-cost": {
      "command": "npx",
      "args": [
        "-y",
        "@comparedge/llm-cost-mcp@latest"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is llm-cost?

llm-cost is a zero-dependency MCP server that gives assistants current per-million-token pricing for 69 LLM models across 17 providers and does cost arithmetic locally: per call, per batch, per month. Rates are verified and date-stamped, so estimates stop relying on stale training data.

How to use llm-cost?

Add npx -y @comparedge/llm-cost-mcp@latest to your MCP client config (Claude Desktop, Cursor, VS Code). Restart the client and six tools appear. No API key, no account.

Key features of llm-cost

Dollar estimates for a single call or thousands of identical calls.
Same-call comparison across up to 6 models, cheapest first.
Monthly budget projection from daily volume.
Cheapest-model ranking with a context-window floor.
Batch API and cached-input discounts where the provider offers them.
Fuzzy model resolution: claude-opus-4-8, Opus 4.8 and anthropic/opus land on the same model.

Use cases of llm-cost

"Price Claude Opus 4.8 on a 25k-token prompt with a 1k answer, run 5,000 times."
"Compare that call on Opus, Sonnet, GPT and Gemini."
"What does 10,000 support-bot conversations a day cost per month?"
"Cheapest model with at least 200k context?"

「データと分析」の他のコンテンツ

🎓 Semantic Scholar MCP Server

JackKuo666

🔍 This project implements a Model Context Protocol (MCP) server for interacting with the Semantic Scholar API. It provides tools for searching papers, retrieving paper and author details, and fetching citations and references.