Loading MCP servers…
Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
This server publishes no hosted endpoint. Run one of its packages locally.
@comparedge/llm-cost-mcp · npm 1.0.0 · stdio
claude mcp add --transport stdio comparedge-llm-cost -- npx -y @comparedge/llm-cost-mcp@1.0.0