PRICING SNAPSHOT 2026-07-10CLAUDE OPUS 4.5 $5.00/$25.00 MTOKCLAUDE SONNET 4.5 $3.00/$15.00 MTOKCLAUDE HAIKU 4.5 $1.00/$5.00 MTOKGPT-5 $1.25/$10.00 MTOKGPT-5 MINI $0.25/$2.00 MTOKGEMINI 3 PRO $2.00/$12.00 MTOKGEMINI 2.5 FLASH $0.30/$2.50 MTOKDEEPSEEK V3.2 $0.28/$0.42 MTOK
▮▮▮TOKENBURN_INDEX

TBX / BURNMETER v1

How much are you burning?

Paste anything you feed an AI. We estimate the tokens, price it across eight models, score the waste, and hand you a leaner version. Everything runs in your browser.

INPUTNOTHING LEAVES YOUR BROWSER
HOW THE ESTIMATE WORKS
  • — Tokens are estimated heuristically (~4 chars/token for prose, ~3.3 for code). Typical accuracy: ±15%. Real tokenizers vary by model.
  • — Output tokens are assumed from your usage type (e.g. an agent run assumes 6x output per input token). The assumption is always shown.
  • — Pricing is a manual snapshot of public list prices (2026-07-10). Cached-input discounts are not applied.
  • — The leaner version is heuristic compression: it strips filler, ceremony and duplicates. Review it before use.
WHAT THE BURN SCORE MEASURES
  • — Verbosity (35%): social ritual and filler. The model doesn't need “please”. It bills for it anyway.
  • — Redundancy (30%): repeated phrases. Saying it twice doesn't make it truer.
  • — Bloat (20%): size versus a reasonable baseline for your usage type.
  • — Ritual (15%): decorative markdown, separators, ASCII ceremony.
  • Agent runs get a 1.3x multiplier. Agents amplify everything, including your mistakes.