Token Speed

opencode-token-speed-plugin

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

Actively maintained

GitHub stars

+1 in 30 days

Monthly installs

14 in 7 days

Composite scoreSCORE

32.7

Multi-signal model

Last commit

4 months ago

2026-04-21

Install and configure

opencode.json

Writes to this project's opencode.json — applies to this repository only.

opencode.json

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

Writes to ~/.config/opencode/opencode.json — applies to every project.

~/.config/opencode/opencode.json

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

opencode loads npm dependencies through its embedded runtime on startup and caches them locally — no manual global install needed.

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