Track and optimize LLM token usage costs across Claude, GPT, and Gemini. This MCP server and CLI tool provides real-time cost monitoring with savings recommendations and budget insights.
TokenBurnRate is a monitoring and optimization tool that tracks token consumption and associated costs across multiple large language models including Claude, GPT, and Gemini. It provides real-time visibility into LLM API spending and generates actionable optimization hints to reduce token burn and overall costs.
TokenBurnRate operates as both an MCP (Model Context Protocol) server and a CLI tool. Installation involves cloning the repository from GitHub and configuring API credentials for the LLM providers you want to monitor. The MCP server can be integrated into compatible platforms for seamless token tracking.
Monday.com MCP Server streamlines board management, item operations, and workflow automation for teams. I…
di NotionFlow
Sentry MCP Server provides comprehensive error tracking and performance monitoring, helping developers id…
di AnalyticsPro
Cloudflare MCP Server simplifies Cloudflare management by providing tools for DNS management, Workers dep…
di PricingBot