Context Previewer for Claude

Live token count, context-window fill %, and $ cost preview for the claude.ai composer — before you hit send.

Know when to start a new chat, before you hit send. Context Previewer adds a small bar above the claude.ai prompt box that estimates how much of your rolling 5-hour usage window you'll have used once your current message sends. It updates live as you type. - Projected 5-hour usage: includes the message you're drafting, so you can see the impact of a long paste before sending it - New-chat recommendation: green "plenty of room", amber "getting up there", red "start a new chat" - Reset countdown: shows when your oldest logged usage drops out of the 5-hour window WHY Long conversations get more expensive with every message, because the whole conversation is processed again each turn. A single oversized prompt can use a large share of your 5-hour limit. Context Previewer flags this before you send, so you can start a fresh chat instead of running out mid-task. SETUP Anthropic doesn't publish a token budget for the 5-hour window, so you set one in settings. Choose your plan (Free, Pro, Max 5x or Max 20x) for a rough starting point, then adjust it as you see how it tracks your real usage. Treat the percentage as an estimate, not an official figure. Optional Exact Mode: add your own Anthropic API key to use Anthropic's official token-counting endpoint instead of the built-in estimate. PRIVACY - No account, no sign-up, no backend, no analytics, no tracking - Your usage log and settings are stored only in your browser - The only network request the extension ever makes is to api.anthropic.com, and only if you turn on Exact Mode and provide your own API key Open source: github.com/irfanmno/claude-context-previewer Context Previewer is an independent project and is not affiliated with, endorsed by, or sponsored by Anthropic. "Claude" is a trademark of Anthropic.