Tally — Claude token counter
Live token counter for Claude. Model-aware messages-left, reset countdowns, and one-click handoff to ChatGPT/Gemini/Grok.
As of June 2026, Tally — Claude token counter has 50,000 users and a 4.54/5 rating from 653 reviews in the Productivity category.
Usersno change0%
50.0K
50,000
Ratingno change0%
4.54
653 reviews
Reviewsno change0%
653
Version
0.3.2
Manifest V3
90-day change · In the last 90 days this extension 1 version update.
History
6 snapshotsTracking since May 29, 2026.
View as table
| Date | Users | Rating | Reviews | Version |
|---|---|---|---|---|
| May 29, 2026 | — | — | — | 0.3.1 |
| Jun 4, 2026 | — | — | — | 0.3.1 |
| Jun 8, 2026 | 10.0K | 4.65 | 48 | 0.3.2 |
| Jun 11, 2026 | 20.0K | 4.53 | 255 | 0.3.2 |
| Jun 16, 2026 | 30.0K | 4.51 | 295 | 0.3.2 |
| Jun 23, 2026 | 40.0K | 4.53 | 468 | 0.3.2 |
| Now | 50.0K | 4.54 | 653 | 0.3.2 |
Changelog
- Jun 4, 2026description
Tally is a quiet meter for Claude. It lives where you work — a thin strip beneath claude.ai's message box that shows your real usage in real time, predicts how many messages you have left, and lets you continue the conversation in ChatGPT, Gemini, or Grok in one click. WHY TALLY Claude's own settings page tells you "Current session: 31%" — but not how many messages 31% buys you, and not what happens when you hit the 5-hour limit. Tally fixes both: • Live inline meter: 31% used · ≈12.4 opus msgs · resets in 1h 22m • Model-aware estimates: Opus burns ~5× faster than Sonnet, ~25× faster than Haiku. The number always matches the model you're actually using. • Cross-LLM handoff: when you're out of Claude headroom, send the conversation — including every HTML file or code artefact Claude built — to ChatGPT/Gemini/Grok. Tally opens the tab and pastes the context automatically. THREE SURFACES, ONE NUMBER 1. Inline bar beneath the chat input on claude.ai 2. Sidebar card on the left nav showing session + weekly windows 3. Toolbar popup with a full breakdown matching claude.ai/settings/usage PRO FEATURES Free: 2 cross-LLM handoffs per day (unlimited copy / download). Pro: $2/mo OR $20 lifetime via Polar.sh — unlimited handoffs, license key, works on every device you sign in from. PRIVACY Tally reads your Claude usage from claude.ai's own API using your existing browser session — no API keys, no new accounts, no servers. All counting happens locally in your browser. The Capsule handoff is short-lived clipboard data only; conversation content is never sent to a Tally server (because there isn't one). BUILT ON THE SHOULDERS OF lugia19/Claude-Usage-Extension Tally builds on top of lugia19's pioneering work (MIT-licensed). The counting engine and API reverse-engineering came from their repo. Tally adds: model-aware messages-left, cross-LLM handoff with artefact preservation, redesigned UI, and Polar.sh-powered Pro tier. NOT AFFILIATED WITH ANTHROPIC.
Tally is a quiet meter for Claude. It lives where you work: a thin strip beneath claude.ai's message box that shows your real usage in real time, predicts how many messages you have left, and lets you continue the conversation in ChatGPT, Gemini, or Grok in one click. WHY TALLY Claude's own settings page tells you "Current session: 31%", but not how many messages 31% buys you, and not what happens when you hit the 5-hour limit. Tally fixes both: • Live inline meter: 31% used, about 12 opus messages, resets in 1h 22m • Model-aware estimates: Opus burns roughly 5x faster than Sonnet and 25x faster than Haiku. The number always matches the model you are actually using. • Cross-LLM handoff: when you run out of Claude headroom, send the conversation to ChatGPT, Gemini, or Grok. Tally opens the tab, pastes your recent turns straight into the box, and automatically attaches the full conversation as a Markdown file so nothing gets truncated, including the files and code Claude built. THREE SURFACES, ONE NUMBER 1. Inline bar beneath the chat input on claude.ai 2. Sidebar card on the left nav showing session and weekly windows 3. Toolbar popup with a full breakdown matching claude.ai/settings/usage PRO FEATURES Free: 2 cross-LLM handoffs per day (unlimited copy and download). Pro: $2/mo or $20 lifetime via Polar.sh. Unlimited handoffs, a license key, and it works on every device you sign in from. PRIVACY Tally reads your Claude usage from claude.ai's own API using your existing browser session. No API keys, no new accounts, no servers. All counting happens locally in your browser. When you hand off a conversation, it stays on your machine: the recent turns are pasted and the Markdown transcript is attached locally, right in your browser. Conversation content is never sent to a Tally server, because there isn't one. NOT AFFILIATED WITH ANTHROPIC.
Permissions & access
- Permissions
- storagealarmstabs
- Host access
- https://claude.ai/*, https://chatgpt.com/*, https://chat.openai.com/*, https://gemini.google.com/*, https://grok.com/*, https://x.ai/*, https://api.polar.sh/*
Screenshots
About
Tally is a quiet meter for Claude. It lives where you work: a thin strip beneath claude.ai's message box that shows your real usage in real time, predicts how many messages you have left, and lets you continue the conversation in ChatGPT, Gemini, or Grok in one click.
WHY TALLY
Claude's own settings page tells you "Current session: 31%", but not how many messages 31% buys you, and not what happens when you hit the 5-hour limit.
Tally fixes both:
• Live inline meter: 31% used, about 12 opus messages, resets in 1h 22m
• Model-aware estimates: Opus burns roughly 5x faster than Sonnet and 25x faster than Haiku. The number always matches the model you are actually using.
• Cross-LLM handoff: when you run out of Claude headroom, send the conversation to ChatGPT, Gemini, or Grok. Tally opens the tab, pastes your recent turns straight into the box, and automatically attaches the full conversation as a Markdown file so nothing gets truncated, including the files and code Claude built.
THREE SURFACES, ONE NUMBER
1. Inline bar beneath the chat input on claude.ai
2. Sidebar card on the left nav showing session and weekly windows
3. Toolbar popup with a full breakdown matching claude.ai/settings/usage
PRO FEATURES
Free: 2 cross-LLM handoffs per day (unlimited copy and download).
Pro: $2/mo or $20 lifetime via Polar.sh. Unlimited handoffs, a license key, and it works on every device you sign in from.
PRIVACY
Tally reads your Claude usage from claude.ai's own API using your existing browser session. No API keys, no new accounts, no servers. All counting happens locally in your browser. When you hand off a conversation, it stays on your machine: the recent turns are pasted and the Markdown transcript is attached locally, right in your browser.
Conversation content is never sent to a Tally server, because there isn't one.
NOT AFFILIATED WITH ANTHROPIC.Technical
- Version
- 0.3.2
- Manifest
- V3
- Size
- 49.84KiB
- Min Chrome
- 88
- Languages
- 1
- Featured
- No
Metadata
- ID
- baicaaiepddopbodaccgfffdimceidbp
- Developer ID
- uf34082caeeb1ec307c10f8c2604e7eca
- Developer Email
- [email protected]
- Created
- May 28, 2026
- Last Updated (Store)
- Jun 2, 2026
- Last Scraped
- Jun 23, 2026
- Website
- —
- Support URL
- —
- Privacy Policy
- https://tally-kohl-pi.vercel.app/privacy
Data sourced from the Chrome Web Store · last verified Jun 23, 2026.