Cost per task
- Low
- $2
- Likely
- $8
- High
- $25
- Basis
- Cursor guidance ($60-100/mo for daily Agent users); alldonesites window ($262 per 5h when saturated, so at most about $52/h)
- Uncertainty
- ±5-10x (effort level and number of parallel agents)
- Unit
- API-$ equivalent
Share of a Claude plan's weekly capacity
One “agentic coding, 1 hour, one interactive agent” as a share of each Claude plan's weekly capacity, computed by calc.js (task cost ÷ weekly capacity).
| Plan | Weekly capacity | Low | Likely | High |
|---|---|---|---|---|
| Claude Pro | $66 inferred | 3.03% | 12.12% | 37.88% |
| Claude Max 5x | $550 inferred | 0.36% | 1.45% | 4.55% |
| Claude Max 20x | $1,099 measured | 0.18% | 0.73% | 2.27% |
Ranges were drafted at an Opus-class list price of about $5 per M input and $25 per M output tokens (Sonnet about 0.6x, Haiku about 0.2x). Re-checked 20 Oct 2026: Claude Opus 5.5 lists at $4 / $20 per M (claude.com/pricing), about 20% lower, so the high ends are conservative for Opus 5.5. On GitHub Copilot plans the calculator rescales every row to the chosen model's per-token rate published by GitHub (see methodology).