Tokoscope — LLM Token Optimizer

Audit, compress, and monitor LLM token usage directly in VS Code.

Tokoscope sits in your editor and gives you instant token visibility as you write prompts, system instructions, or LLM-powered code. See token counts, estimated costs, and waste scores without leaving VS Code.

Features

Status bar token counter Live token count and estimated cost for the current file or selected text — always visible at the bottom of the editor.

One-command analysis Run Tokoscope: Analyze Current File or Tokoscope: Analyze Selected Text from the Command Palette to get:

Token count
Estimated cost across all supported models
Waste score (0–100)
Specific suggestions to reduce tokens

Right-click menu Right-click any selection to run Tokoscope analysis directly from the context menu.

Auto-analyze on save Optionally enable auto-analysis on every file save.

Setup

Install the extension
Open Command Palette (Cmd+Shift+P / Ctrl+Shift+P)
Run Tokoscope: Set API Key
Enter your key from app.tokoscope.com/settings

No Tokoscope account yet? Get started free — no credit card required.

Commands

Command	Description
`Tokoscope: Analyze Current File`	Analyze the full file
`Tokoscope: Analyze Selected Text`	Analyze selected text
`Tokoscope: Set API Key`	Save your Tokoscope API key
`Tokoscope: Open Dashboard`	Open app.tokoscope.com/dashboard

Settings

Setting	Default	Description
`tokoscope.apiKey`	—	Your Tokoscope API key
`tokoscope.model`	`gpt-4o`	Default model for cost estimates
`tokoscope.showStatusBar`	`true`	Show token count in status bar
`tokoscope.autoAnalyze`	`false`	Auto-analyze on file save

Supported models

OpenAI: gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-3.5-turbo Anthropic: claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5 Gemini: gemini-2.5-flash, gemini-2.5-pro, gemini-1.5-flash

Tokoscope — LLM Token Optimizer

tokoscope

Tokoscope — LLM Token Optimizer

Features

Setup

Commands

Settings

Supported models

Links