> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openference.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Minion Plan

> Minion at $20/month: curated open-source coding models, 5-hour / weekly / monthly usage windows, and estimated requests per model.

# 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](https://openference.com/pricing), or compare with [Boss](https://docs.openference.com/billing/boss.md) 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.

| Model | Requests / 5 hours | Requests / week | Requests / month |
| - | - | - | - |
| `Kimi K3` | 380 | 950 | 1,900 |
| `GLM-5.3` | 830 | 2,080 | 4,160 |
| `DeepSeek-V4-Pro-0813` | 880 | 2,210 | 4,410 |
| `DeepSeek-V4-Flash-0731` | 2,650 | 6,620 | 13,240 |
| `DeepSeek-V4.1-Flash` | 3,850 | 9,620 | 19,230 |
| `DeepSeek-V4.1-Flash-1017` | 3,850 | 9,620 | 19,230 |
| `GLM-5.3-Flash` | 7,740 | 19,350 | 38,710 |
| `GLM-4.7-Flash` | 18,750 | 46,880 | 93,750 |
| `Agnes-3.0-Flash` | 23,300 | 58,250 | 116,500 |
| `Auto` | — | — | — |
| `Gemma 4 26B` | Unlimited | Unlimited | Unlimited |
| `GPT-OSS-120B` | Unlimited | Unlimited | Unlimited |
| `Llama 3.2 3B` | Unlimited | Unlimited | Unlimited |
| `MiniMax M3` | Unlimited | Unlimited | Unlimited |
| `Nemotron-3-120B` | Unlimited | Unlimited | Unlimited |
| `Qwen3.8 27b` | Unlimited | Unlimited | Unlimited |

## Models and token rates

Every model below is included on Minion — switch at any time. Token prices are per 1M tokens.

| Model | Input (/ 1M tokens) | Output (/ 1M tokens) | Cached Read (/ 1M tokens) |
| - | - | - | - |
| `Kimi K3` | \$3.00 | \$15.00 | \$0.30 |
| `GLM-5.3` | \$1.40 | \$4.40 | \$0.26 |
| `DeepSeek-V4-Pro-0813` | \$1.32 | \$3.96 | \$0.132 |
| `Qwen3.8 27b` | \$0.45 | \$3.20 | — |
| `DeepSeek-V4-Flash-0731` | \$0.44 | \$1.32 | \$0.044 |
| `DeepSeek-V4.1-Flash` | \$0.30 | \$1.20 | \$0.006 |
| `DeepSeek-V4.1-Flash-1017` | \$0.30 | \$1.20 | \$0.006 |
| `GLM-5.3-Flash` | \$0.15 | \$0.50 | \$0.03 |
| `GLM-4.7-Flash` | \$0.06 | \$0.40 | — |
| `Agnes-3.0-Flash` | \$0.05 | \$0.15 | \$0.005 |
| `Auto` | \$0.3675 | \$1.00 | — |
| `Gemma 4 26B` | \$0.10 | \$0.30 | — |
| `GPT-OSS-120B` | \$0.35 | \$0.75 | — |
| `Llama 3.2 3B` | \$0.051 | \$0.335 | — |
| `MiniMax M3` | \$0.30 | \$1.20 | \$0.06 |
| `Nemotron-3-120B` | \$0.50 | \$1.50 | — |

## 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.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.