Quick facts
- Best for
- Track AI coding token usage across agents and IDEs
- Pricing
- Free
- Editor rating
- 4.5 / 5
- Community saves
- 0
About tokscale
tokscale is a developer-focused AI infrastructure tool discovered from its official GitHub repository at https://github.com/junhoyeo/tokscale. It tracks token usage and costs across AI coding agents such as OpenCode, Claude Code, Codex, Gemini, Cursor, AmpCode, Kimi, and related tools. The practical value is simple: it gives builders a focused way to solve a real problem that appears once teams start using AI agents every day. Instead of treating agent workflows as magic, tokscale exposes the underlying state, cost, execution, or safety constraints in a way engineers can inspect and control. That makes it useful for solo builders, AI engineering teams, and platform teams that need repeatable behavior rather than one-off demos. How it works: Tokscale scans local agent usage data, calculates token totals and costs, and presents results through a Rust-powered CLI/TUI, JSON exports, profil
Pros
- Tracks token usage across many AI coding clients
- Provides CLI/TUI reports, JSON exports, profiles, and leaderboards
- Calculates pricing with LiteLLM and OpenRouter data plus local overrides
- Supports detailed input, output, cache, and reasoning token accounting
Cons
Pricing
- • MIT-licensed repository
- • Self-hosted/local usage
- • Review repository for optional hosted features