AI Agent Hub
Back to plugins
dsh-usage-monitor preview

dsh-usage-monitor

Web Tools Updated 2026.09.13

Run the following command in DeepSeek Harness:

dsh plugin install liyiersan/dsh-usage-monitor

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install liyiersan/dsh-usage-monitor inside DeepSeek Harness to install; full source code is available at https://github.com/liyiersan/dsh-usage-monitor.

About this plugin

Running DeepSeek API sessions inside DeepSeek Harness often raises the same anxieties: how much did this turn really cost, what is left on the account, and am I quietly paying double during peak hours? dsh-usage-monitor folds DeepSeek's official balance endpoint, per-turn incremental pricing, cross-session cumulative usage, and peak/off-peak rates directly into the DSH Web UI. Click the Usage tab for a full breakdown, or glance at the dock bar above the input field for an always-visible balance, current model rate, and pricing window—without leaving the page.

Per-session cost is computed incrementally: each stage is priced by the model actually in use and the time slot in effect, so switching models mid-conversation never causes the total to jump. Token usage and spend are bucketed per model, making it easy to compare Flash versus V4-Pro at a glance. The dock bar reports in the background continuously, so the ledger keeps accumulating even when the panel is closed. The built-in pure-function pricing engine distinguishes cached reads, uncached input, and output tokens, matching DeepSeek's official billing semantics and automatically applying the correct peak or off-peak rate.

If you develop or debug with the DeepSeek API in DSH daily and want precise per-turn cost visibility, model economics comparison, or simply a safeguard against silently burning budget during peak hours, this is the lightest-weight solution available. It stores no API keys, sends no telemetry, and keeps the local ledger confined to your DSH directory—privacy stays entirely in your hands.

Screenshots

Use Cases

  • Check per-turn API cost and account balance inline during DSH conversations without leaving the page
  • Compare actual token usage and spend for Flash vs V4-Pro across peak and off-peak windows
  • Track cumulative usage through the persistent dock bar during debugging to avoid unexpected peak-hour overspend

Best For

  • Engineers who call the DeepSeek API daily for development or debugging
  • Indie developers or small teams that need precise control over AI inference budgets
  • Users running multiple models in DSH who want an at-a-glance cost comparison