open source · MIT★ star it on GitHubfound a bug, or want an agent supported?open an issuebuilt in the open, receipts included
skip to content
tokenchitv0.7.0 · MIT

@manishreddy123

✓ github verified

First activity 2026-02-25. synced 4h ago. Figures are self-reported by the tokenchit CLI from local agent logs.

tokens
6.64B
equiv. cost
$3,935
streak
16d
active days
35

Activity · last 12 months

6.64B tokens across 35 active dayslessmore

Agents

  • codex3.90B58.7%
  • claude-code2.74B41.3%

Models lifetime

Models used, with tokens and equivalent cost
modeltokensequiv. cost
gpt-5.6-sol2.75B$1,550.72
claude-opus-52.17B$1,659.47
gpt-5.3-codex989M
claude-fable-5370M$515.14
codex-auto-review148M
claude-opus-4-8135M$167.79
claude-sonnet-546.4M$22.81
claude-fable-5-118.2M$19.00
gpt-5.6-luna15.9M$0.57

The card

@manishreddy123TOKENS6.64BEQUIV. COST$3,935STREAK16dcodex 59%claude-code 41%TOKENCHIT.APPSYNCED 4H AGO
markdown
[![tokenchit — @manishreddy123 AI coding agent usage](https://tokenchit.app/api/card/manishreddy123.svg)](https://tokenchit.app/u/manishreddy123)

This renders live from the endpoint. To commit the file instead — no request to us at all — run tokenchit sync and add the SVG to your repo.

Equiv. cost is not what they paid. It is what these tokens would cost at list API rates; most agent usage runs under a subscription where no per-token charge happens. Models with no public price are counted in the token total and left out of the cost.

Who is burning the most?

Ranked by tokens, from developers who chose to publish. The two windows disagree on purpose — one rewards the last month, the other the whole history.

Last 30 days

All time

Top 8 of each. A means the GitHub identity was proved; everything else is self-reported.

See the full board →