Mode VC Chart: AI Inference Cost: Output Token Pricing for Flagship LLMs

Name: Mode VC Chart: AI Inference Cost: Output Token Pricing for Flagship LLMs MCP Server
Author: Mode VC Chart: AI Inference Cost: Output Token Pricing for Flagship LLMs

remote

Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..

Getting Started

npx @getmcp/cli add com.modevc/chart-ai-inference-cost-comparison

Requires Node.js 18+. Community-contributed server. Review source before installing.

Claude Desktopguide →Vscodeguide →Cursorguide →Windsurfguide →

Configuration

Config file: ~/Library/Application Support/Claude/claude_desktop_config.json

JSON

{
  "mcpServers": {
    "com.modevc/chart-ai-inference-cost-comparison": {
      "url": "https://modevc.com/api/mcp/chart-ai-inference-cost-comparison",
      "transport": "streamable-http"
    }
  }
}

Claude Desktop MCP documentation (opens in new tab)

AuthorMode VC Chart: AI Inference Cost: Output Token Pricing for Flagship LLMs

Version2.0.2

TransportRemote

modevc.com (opens in new tab)