DSH-TOKEN-feiyong
Run the following command in DeepSeek Harness:
dsh plugin install singei8/DSH-TOKEN-feiyong
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install singei8/DSH-TOKEN-feiyong in the DeepSeek Harness terminal to install this plugin; the source lives at https://github.com/singei8/DSH-TOKEN-feiyong , then restart DSH to enable it.
About this plugin
Most DSH users have no idea what a single model call costs until the monthly invoice lands. DSH-TOKEN-feiyong intercepts every LLM call, reads the provider-reported TokenUsage, and prices each request across three dimensions: cache-hit input, cache-miss input, and output. It automatically applies the official DeepSeek peak/off-peak schedule, so the question
Use Cases
- See the exact cost of every model call in real time instead of waiting for a monthly bill
- Break down daily and cumulative spending per model when switching between multiple providers
- Monitor 5-hour, weekly, and monthly quota burn on prepaid plans like Volcano Ark Agent
Best For
- Individual developers running dozens or hundreds of DSH turns daily
- Engineering teams that share an API key and need per-member cost breakdown
- AI application developers who switch between models and need per-turn cost visibility
Related Plugins
A network security red-team benchmark plugin for DeepSeek-V4.1/Flash featuring dual-layer kernel injection and zero-tool architecture for controlled model safety assessment.
A security red-team prompt plugin for DeepSeek-V4 that uses code-formal mapping and zero-trigger system prompts to enable unconditional output, intended for authorized testing and research only.
Adds an Auto approval mode on the official workspace-write sandbox, classifying semantic risks, asking when ambiguous, and denying destructive operations.
Undo/rollback system for DSH: config & plugin snapshots, one-click undo/redo/restore, message-level revert, secret masking, safe mode, and offline WebUI/GUI/CLI rescue tools for when DSH won't start.