Skip to main content

Boss Plan

Boss is built for heavy coding agents that run continuously: the same curated open-source models as Minion with a much larger included allowance across rolling windows and priority support for $80/month. See all plans on the Pricing page, or compare with Minion for everyday coding.

Usage limits

Boss uses the same 20% / 50% / 100% window shares as Minion with higher limits across every window:
  • 5-hour limit (20%) — Resets at 00:00, 05:00, 10:00, 14:00, and 19:00 UTC.
  • Weekly limit (50%) — Resets every Monday at 14:00 UTC.
  • Monthly limit (100%) — Resets on your monthly billing date.
All limits are per account and shared across your API keys. Accounts also include a burst cap of 50 requests per minute.

Estimated requests per window

Estimates assume a typical coding agent turn of 10,000 input and 100 output tokens (uncached). Active prompt caching meters repeated context at the much lower Cached Read rate, enabling significantly more requests.

Models and token rates

Models on Boss use the exact same catalog token rates as Minion — Boss buys a larger allowance, not different rates. Token prices are per 1M tokens.

Usage beyond your plan limits

When a window limit is reached:
  1. On-demand credits — Add a balance in the dashboard; requests continue automatically at catalog token rates.
  2. Wait for reset — 5-hour windows reset 5 times daily, weekly limits reset Monday 14:00 UTC, and monthly limits reset on your billing date.
Upstream provider errors never count against your allowance.

FAQ

What counts toward my allowance?

Requests that complete or fail because of a client error (4xx) count. Upstream provider errors never count.

Can I switch models mid-month?

Yes. Every included model draws from the same allowance at its catalog token rate.

What happens if I reach 100% of my monthly allowance?

Included plan access pauses until your next billing cycle, or continues on on-demand credits if you have a balance.

Minion or Boss?

If one developer runs an agent day to day, Minion is typically plenty. If agents run in parallel, overnight, or with continuous background workloads, Boss gives you nearly 3x the allowance and priority support.