AI Agent Hub
Back to plugins
dsh-balance-plugin preview

dsh-balance-plugin

Web Tools Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install yxxbc/dsh-balance-plugin

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

Run dsh plugin install yxxbc/dsh-balance-plugin in DeepSeek Harness to install the plugin from https://github.com/yxxbc/dsh-balance-plugin.

About this plugin

For developers who frequently call the DeepSeek API, balance and usage data are often scattered across different pages and hard to track in real time. dsh-balance-plugin provides DeepSeek Harness users with a centralized monitoring panel that makes balance, consumption, and performance status clear at a glance.

The plugin supports parallel multi-account queries across CNY/USD balance pools and can automatically read the local DEEPSEEK_API_KEY, so no manual configuration is needed. When the balance falls below a configurable threshold, the balance bar turns red to warn you, and a direct link to the official top-up page is provided. The usage statistics section faithfully recreates the Miyu WebUI style, including a contribution-graph-style usage calendar, trend bar charts, a model consumption donut chart, and recent call records, while also showing performance metrics such as time to first token, tok/s, and cache hit rate.

Additionally, the plugin offers a third-party plugin management panel and a query_api_quota model tool, allowing you to ask about your balance in natural language. It is suitable for developers, indie hackers, and teams using DeepSeek Harness who want to manage API costs and performance more proactively.

Screenshots

Use Cases

  • Monitor DeepSeek API balance in real time to avoid service interruptions due to insufficient funds.
  • Analyze daily call volume and model consumption to optimize API usage costs.
  • Manage multiple DeepSeek accounts and third-party plugins in one unified view.

Best For

  • Developers who frequently call the DeepSeek API
  • Indie developers or teams concerned with cost and performance
  • DeepSeek Harness users