Skip to main content

​
Plans & Usage

Every account starts on the Free plan, which is on-demand only. Minion and Boss add reliable access to a curated set of open-source coding models for one simple monthly price — Minion for everyday coding, Boss for heavy agents that never sleep. Minion and Boss work like any other plan in your dashboard: subscribe, create an API key, and point your coding tool at Openference. They’re built for coding tools and autonomous agents (Cursor, Claude Code, Codex, OpenCode, Cline, Pi, and more). See live plan details and availability on the Pricing page. Deep dives: Minion plan · Boss plan.

​
Free plan

Free has no subscription and no included usage. Create an account, create an API key, add credits, and every request is billed per token at the model’s standard catalog rate. With no credit balance, requests return 402 Payment Required until you add credits. You can move to Minion or Boss at any time for included usage, and return to Free by cancelling a subscription.

​
How it works

  1. Subscribe to Minion or Boss and add your billing details.
  2. Create an API key in the dashboard.
  3. Connect your coding tool and pick any included model — switch models at any time, and each call simply counts toward your included usage.
The model list may change as we test and add new models. See the model catalog for the current list.

​
Usage limits

Usage is metered across three rolling windows allocating your plan’s monthly budget ($60/month** on Minion, **$160/month on Boss):
  • 5-hour limit (20%) — Resets at fixed times daily (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. Track your usage in real time from your dashboard.

​
How usage is counted

Requests are metered at each model’s standard catalog token rates. Repeated context during prompt caching is metered at the lower Cached Read rate, enabling significantly more requests per window.

​
Model token rates

​
What counts toward your allowance?

A request counts toward your allowance when the final status recorded is:
  • success
  • client_error (4xx from client or bad request)
Upstream provider errors and capacity-unavailable situations never count against your allowance.

​
Going over your limit

When you reach your 5-hour, weekly, or monthly plan allowance, you can continue using the API without interruption:
  1. On-demand credits — Add a USD credit balance in the dashboard; overage is billed automatically at catalog token rates.
  2. Wait for the window reset — The 5-hour windows reset at fixed times daily (00:00, 05:00, 10:00, 14:00 and 19:00 UTC), the weekly limit resets every Monday at 14:00 UTC, and the monthly limit resets on your monthly billing date.

​
Refunds

All subscription and credit purchases are final and non-refundable, except where a refund is required by applicable law. You can start with on-demand credits first to confirm the service fits your needs before subscribing. See the Terms of Service for the full refund policy and the 30-day billing-dispute window.

​
Burst protection

To keep the platform responsive for everyone, Openference applies a per-minute burst limit on each account (all of your API keys share one burst budget). This is separate from your 5-hour, weekly, and monthly allowances, it is a hard cap (requests beyond it return 429), and it is not bypassed by credits. See Rate Limits & Fair Usage for details on burst limits and 429 responses.

​
Legacy plans (Promo, Free, Lite, Pro, Pro+, Max, Max+, Auto Agent, Coding)

The legacy request-count and earlier tiers (Promo, Free, Lite, Pro, Pro+, Max, Max+, Auto Agent, and Coding) are retired and no longer offered for new purchases, renewals, or extensions. Existing subscribers on a legacy plan keep their plan and limits until the end of their current billing period, after which the subscription ends automatically. For legacy plan limits and per-model request ratios, see Model Request Ratios (Legacy).

​
Plans for teams

Need a plan for a whole team? Teams gives every member their own seat, allowance and API keys, with shared billing, roles and admin controls.

​
Track your usage

View your current 5-hour, weekly, and monthly allowance percentages, the token rates for each included model, credit balance, and billing history in the dashboard under Billing and Usage.