One thing I keep noticing with AI coding: the session usually gets expensive before it feels broken.

It starts with a few pasted logs, a retry loop, an old file that keeps riding along, or staying on a bigger model after the hard part is already solved. The output still looks fine, but the context is getting heavier every prompt.

Hey everyone! Wanted to share what's new with TokenBar.

We just shipped a major update that adds support for 20+ AI providers including OpenAI, Claude/Anthropic, Gemini, Cursor, GitHub Copilot, OpenRouter, and Vertex AI. You can now see all your AI spending in one glance from your Mac menu bar.