#token-tracking

DeepSeek Pilot — Vision + Token Tracking

konstantyn-ganenkov

DeepSeek V4 Pro & Flash in GitHub Copilot Chat. Vision proxy for image attachments, KV-cache-aware context-window indicator, persistent reasoning cache, live session cost and platform balance in the status bar, a thinking-effort selector per model variant, and one-click wiring as Copilot's utility/u

AIFlowBridge - 100+ AI models via OpenRouter, plus DeepSeek V4, MiniMax M3 & MiMo in Copilot Chat

laurentOngaro

100+ AI models through one free local gateway. OpenRouter (GPT-5.6, Claude Opus 4.8, Gemini 3.5 Flash, Llama 4 Maverick, MiniMax M3, DeepSeek V4 Pro, Qwen 3.7 Max) reaches GitHub Copilot Chat, Kilo Code, Continue, Open WebUI, and JetBrains AI Assistant through a unified OpenAI-compatible endpoint at