I like Claude Code a lot, but one thing still feels weirdly opaque to me: token burn while you are deep in a session.
When I am iterating fast, the bill usually shows up after the fact. By then I already made the expensive choices. Long context, repeated retries, and bouncing between models can get surprisingly costly before you really notice it.
Code Meter features:
• Real-time usage gauge in the menu bar with color-coded status
• Per-model breakdowns for Opus and Sonnet
• Burn rate analysis - see if you’re pacing well or burning too fast
• Projected exhaustion warnings (“you’ll hit the limit in ~15 minutes”)
• Smart notifications at 50%, 75%, 90%, and 100% usage
• Desktop widgets (small & medium) for at-a-glance monitoring
• Usage history charts (Now, 6H, 1D, 1W)
• Minimax AI Token Plan support (via API key)
Code Meter - Claude Usage Monitor macOSBetter monitoring for Claude Code and Minimax rate limitsApr 2026
