Numbers a builder cares about: the monthly bill to clear captchas, whether the free Gemini key is enough, and the machine you'd need to pull 3,000 products a day over Tor. Cost figures are live from the leaderboard (real bench tokens × real OpenRouter prices).
The solver only runs when a captcha appears, and captchas are rare (measured ~0.8% of exits). So the monthly cost = $/1k-solves × captcha-rate × scrapes. We show a band: 0.8% measured → 16.5% worst-case (the early small-sample pilot, kept as a pessimistic bound).
| model / combo | solved | $/1k solves | $/mo @ 0.8% | $/mo @ 16.5% |
|---|---|---|---|---|
| loading… |
Assumes 3,000 scrapes/day, every day (×30). $/mo = $/1k-solves × rate × 90 (90 = 3k/day ÷ 1k × 30 days). A ~ on a price means the unit price is an estimate, not a model we run in production.
Short answer: not on its own. Two separate things get called "Gemini":
Google's free tier — what GEMINI_API_KEY uses. Serves only gemini-2.5-flash (~500/day) and 2.5-flash-lite (~1,000/day).
Problem 1: those models are weak on this puzzle — 32% / 30% solved vs 90%+ for the paid Gemini-3 tier.
Problem 2: the daily quota (~500–1,500 solves) sits right at our captcha volume, so a busy day exhausts it and the scraper stalls.
The strong models — gemini-3-flash, 3.1-flash-lite, qwen3-vl-32b — only exist on the paid tier, billed through OpenRouter. That's what every combo on the board uses.
But "paid" here is cents/month (section 1). So the honest setup is: free key as a first try, paid OpenRouter as the fallback when the puzzle is hard or the quota's gone — which is exactly what production runs.
We did not ship two separate builds — one solver picks the provider per call. The free key is tried first where it's viable; OpenRouter catches the rest for a few cents.
Throughput is measured at ~600 product fetches/hour per arm (555–731 across the study + shootout). An "arm" = one headed Chrome + its own Tor exit. You scale by adding arms — mostly for exit diversity (more distinct IPs in rotation), not because Tor is slow.
| parallel arms | throughput | time for 3,000 | RAM (Chrome+Tor) | CPU |
|---|---|---|---|---|
| 1 | ~600/hr | ~5 h | ~0.45 GB | ~1 core |
| 3 | ~1,800/hr | ~1.7 h | ~1.3 GB | ~2–3 cores |
| 6 | ~3,600/hr | ~50 min | ~2.6 GB | ~4–6 cores |
| 9 | ~5,400/hr | ~33 min | ~3.9 GB | ~6–9 cores |