@deepseek-ai/dsh-token-cost
DSH web GUI plugin: token usage (input/output), cache hit/miss and cost statistics per conversation and in aggregate, with auto-switching DeepSeek pricing schemes
6 results
DSH web GUI plugin: token usage (input/output), cache hit/miss and cost statistics per conversation and in aggregate, with auto-switching DeepSeek pricing schemes
Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.
DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.
DSH plugin: keep text-only models (deepseek-v4-flash / deepseek-v4-pro) as the session default, and automatically route requests that carry image content to a configured vision-capable model (deepseek-v4-flash-vision-exp) 鈥?no manual model switching (periscope).
DeepSeek Harness 高峰期模型自动切换插件:高峰前自动切到指定替代模型,高峰后切回官方模型。· Auto-switch to an alternate model before DeepSeek peak hours and back to the official model afterwards. · 本插件由 AI 全权开发,作者无编程经验,请自行测试安全性;安装说明可能含 AI 幻觉。· Developed by AI; test at your own risk; install docs may contain AI hallucinations.
Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.