Token Speed

opencode-token-speed-plugin

OpenCode TUI plugin that displays real-time LLM output token speed (tok/s)

维护活跃

GitHub 星标

近 30 天 +1

月装机量

近 7 天 14

综合评分SCORE

32.7

生态多维模型

快速安装与配置

opencode.json

写入当前项目的 opencode.json，只对这个仓库生效。

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["opencode-token-speed-plugin@1.0.4"]
}

写入 ~/.config/opencode/opencode.json，对所有项目生效。

~/.config/opencode/opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["opencode-token-speed-plugin@1.0.4"]
}

opencode 启动时会通过内嵌运行时自动加载 npm 依赖并缓存至本地目录，无需手动在全局环境执行安装。

README.md

A OpenCode TUI plugin that displays real-time LLM output token speed (tok/s) in the session prompt area.

Real-time speed display — Shows output token speed during streaming using a 2-second sliding window.
Persistent display — When streaming ends, the last measured speed is kept visible.
Non-intrusive — Uses the session_prompt_right slot (append mode), so it doesn't replace any built-in UI.

Add the plugin to your tui.json (not opencode.json):

{
  "plugin": ["opencode-token-speed-plugin"]
}

That's it. OpenCode will automatically install the plugin on next run.

Note: This is a TUI plugin, so it must be configured in ~/.config/opencode/tui.json, not opencode.json.

Listens to message.part.delta events to count characters as they stream in.
Estimates tokens using the chars / 4 heuristic within a 2-second sliding window.
Displays ▲ XX.X tok/s to the right of the session prompt.

MIT