> ## 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.

# Plans & Usage

> Per-plan request limits (5-hour window, weekly cap, burst limit), open-source model access, and on-demand overage.

# Plans & Usage

Every plan includes a **request allowance per usage window** (for example, 20 requests per 5 hours on Free, 800 on Pro), a **weekly request cap** that resets Monday 00:00 UTC, and a **per-minute request cap** per API key (10 per minute on Free, 30 on Pro). Access the latest **open-source LLMs** through a single API. When you need more, on-demand overage kicks in — no hard cutoff.

See live plan details and pricing on the [Pricing page](https://openference.com/pricing).

## Plan limits at a glance

All limits are per account (window and weekly allowances) or per API key (burst limit). Window allowances reset in full on a fixed schedule — your exact reset time is shown in the dashboard under Billing. Weekly caps reset every Monday 00:00 UTC.

### Coding plans

|                               | Free | Lite       | Pro        | Max        |
| ----------------------------- | ---- | ---------- | ---------- | ---------- |
| Price                         | \$0  | \$18.99/mo | \$27.99/mo | \$57.99/mo |
| Requests per 5-hour window    | 20   | 450        | 800        | 1,800      |
| Requests per week             | 350  | 7,500      | 13,000     | 30,000     |
| Burst limit (requests/minute) | 10   | 20         | 30         | 48         |
| On-demand rate discount       | —    | —          | 12%        | 20%        |

### Auto Agent plans

Built for unattended and high-frequency agents, with higher per-minute caps.

|                               | Auto Agent Mini | Auto Agent Lite | Auto Agent Pro | Auto Agent Max |
| ----------------------------- | --------------- | --------------- | -------------- | -------------- |
| Price                         | \$14.99/mo      | \$24.99/mo      | \$54.99/mo     | \$99.99/mo     |
| Requests per 5-hour window    | 200             | 500             | 1,000          | 2,000          |
| Requests per week             | 3,000           | 9,000           | 18,000         | 38,000         |
| Burst limit (requests/minute) | 18              | 28              | 60             | 99             |
| On-demand rate discount       | 5%              | 25%             | 50%            | 50%            |

On-demand overage and credits can extend your window allowance and weekly cap; the per-minute burst limit is a hard cap and is never extended by credits. Prices are shown in USD — local pricing, annual billing, and any current promotions are shown live on the [Pricing page](https://openference.com/pricing), which is authoritative if it differs from this table.

## What's included

Each plan includes:

* A request allowance per usage window (shown on plan cards as requests per 5 hours)
* A weekly request cap (resets Monday 00:00 UTC)
* Access to the curated model catalog, including the latest open-source models (a small number of premium models may be limited to specific plans — see the [Pricing page](https://openference.com/pricing))
* On-demand overage at catalog model rates with your plan's discount
* Optional credit top-ups for predictable costs

Higher tiers include more requests per window, a larger weekly cap, better on-demand rates, and additional features such as usage analytics and priority support.

## Refunds

All subscription and credit purchases are **final and non-refundable**, except where a refund is required by applicable law. We recommend testing the service on the **Free plan** before purchasing a paid subscription. See the [Terms of Service](https://openference.com/terms-of-service) for the full refund policy and the 30-day billing-dispute window.

## What counts as a request?

**One API call to any model = one request.**

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 do not count** against your quota.

## Going over your limit

When you exceed your included requests in the current window or your weekly cap, you can continue using the API:

1. **On-demand usage** — Overage is billed at catalog model rates with your plan's discount applied.
2. **Credit top-ups** — Add a dollar balance in the dashboard for predictable spending.
3. **Upgrade** — Move to a higher tier for a larger allowance.

There is no hard cutoff when credits or on-demand usage are enabled. Your usage window resets on a fixed schedule — your full allowance comes back at each reset, and your exact reset time is shown in the dashboard under Billing. The weekly cap resets every Monday 00:00 UTC.

## Burst protection

To keep the platform responsive for everyone, Openference also applies a **per-minute burst limit** on each API key. This is separate from your per-window request allowance, it is a hard cap (requests beyond it return 429), and it is **not** bypassed by credits — only your per-window allowance can be extended with on-demand credits.

For typical interactive IDE use, you will stay well within the burst limit. For unattended or high-frequency agents, our **Auto Agent plans** offer higher per-minute caps (up to 99 requests per minute) and larger per-window allowances built for automation. If you are hitting the burst limit regularly, upgrade your plan or add credits for on-demand overage.

See [Rate Limits & Fair Usage](/api-reference/rate-limits) for technical details on burst limits and 429 responses.

## Track your usage

View your current usage, remaining allowance, and billing history in the dashboard under **Billing**.