Lets Claude Desktop, Cursor, Cline, Windsurf, Zed, or any other MCP client estimate token counts and fit a chat history into a model's context budget on demand.
Counts LLM prompt tokens and estimates API costs across OpenAI and Anthropic models directly inside MCP-compatible chat clients. Supports exact tokenization for OpenAI models and fallback approximation for Claude when no API key is present.
Enables token counting, usage tracking, and cost calculation for LLM APIs, with a proxy server mode to automatically intercept and monitor API requests from clients like Cursor and Windsurf.
MCP server for deterministic, zero-dependency context-window math, enabling token estimation, text truncation, and budget reporting without a tokenizer.
Provides intelligent OpenAI API token management with automatic switching between model tiers when usage limits are reached. It enables users to track daily token consumption, estimate costs before making calls, and manage project-specific usage data.