Skip to main content

​
Minion Plan

Minion is built for everyday coding: access to curated open-source models for $20/month across three rolling usage windows. Point your coding tool (Cursor, Claude Code, Codex, OpenCode, Cline, Pi, and more) at Openference and start building. See all plans on the Pricing page, or compare with Boss for higher-throughput agent workloads.

​
Usage limits

Usage is tracked across three rolling windows:
  • 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

Every model below is included on Minion — switch at any time. 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.