Connects MCP clients to DeepSeek API, including DeepSeek-R1 reasoning with visible chain-of-thought. Provides four tools: generate, chat, reason, and list models.
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.
Provides coding agents with pre-flight cost estimation by analyzing local logs to forecast token usage and quota impact before expensive work, exposing tools for remaining quota, per-task cost estimates, and attempt affordability.