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

# Reserved Getting Started

> Reserve GPU capacity in a few steps, self-serve through the app

Reserving capacity works just like launching an On-Demand instance, using the same app and the same flow. Choose a fixed reservation term, pay up front, and lock in the capacity at a discounted rate.

## Reserve an instance

**1. Log in to your Hyperbolic account**

Log in to Hyperbolic and select **GPUs** from the navigation. Browse the GPU capacity currently available in the platform.

Don't see the capacity you need? [Contact Sales](mailto:sales@hyperbolic.ai) for additional capacity.

**2. Choose your GPUs**

Select the GPU type you want and select the GPU Count. Your rental plan options appear below. Longer reservation terms have lower rates.

**3. Select a reservation term**

Select **Reserved term** to choose how long to reserve. A calendar opens below the plan cards. Select a quick pick, such as **1 Week** or **2 Weeks**, or pick the day your reservation ends, up to 30 days out. The summary shows your rate, total, and savings. **Next** stays disabled until you pick an end day. For reservations longer than 30 days, [contact sales](mailto:sales@hyperbolic.ai).

![Rental plan step with Reserved term selected, showing the end-date calendar, 1 Week, 2 Weeks, and 1 Month quick picks with discounts, and a summary with the rate, total, and savings](https://mintcdn.com/hyperboliclabs/Men_QByCSX-khpfv/images/reserve-terms.png?fit=max\&auto=format\&n=Men_QByCSX-khpfv\&q=85\&s=7b239feab218dacdfbd2f4b5beb1ca6e)

Review the rate and reservation details, then continue to the SSH key step.

Reserved instances are paid up front, so your balance must cover the full reservation cost.

**4. Select an SSH key**

Select a saved SSH key, or paste a new public key to save it and attach it to the instance. Then complete the instance configuration. See [SSH Keys](https://hyperbolic.ai/docs/general/account-management.md#ssh-keys) to manage your saved keys.

When you're ready, click **Start Building** to create your reserved instance.

**5. Run your workload**

Your reservation begins when the instance is ready and runs for the full reservation term. Before it ends you can extend it from the instance's details page. When the term ends, **Reservation Protection**, which is on by default at launch unless you turn it off, keeps the instance running at the on-demand rate. If you turned it off, the instance is terminated when the reservation ends — save any data you need to persistent storage first. See [Reserved Overview](https://hyperbolic.ai/docs/reserved/overview.md#what-happens-at-the-end-of-the-term).

## Reserve with the API

1. Get the discount for your length with `GET /v2/on-demand/reserve-options`. Pass `termPeriodDays`, any whole number of days from 1 to 30, and the discount comes back as `requestedOption.discountPercentage`.
2. Create the rental with `POST /v2/on-demand/rentals`. Set `termType` to `reserved`, and send your `termPeriodDays` and the `discountPercentage` from step 1.

```bash theme={null}
curl "https://api.hyperbolic.ai/v2/on-demand/reserve-options?termPeriodDays=10" \
  -H "Authorization: Bearer $HYPERBOLIC_API_KEY"

curl -X POST "https://api.hyperbolic.ai/v2/on-demand/rentals" \
  -H "Authorization: Bearer $HYPERBOLIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "rentalType": "virtual-machine",
    "gpuType": "h100",
    "gpuCount": 1,
    "termType": "reserved",
    "termPeriodDays": 10,
    "discountPercentage": 5
  }'
```

Replace `5` with the `discountPercentage` you got in step 1. If it doesn't match the current discount for that length, the request is rejected with a 400. Get the discount again and retry. Lengths over 30 days are also rejected with a 400. The full term is prepaid from your credits. See [Get a list of reserve options](https://hyperbolic.ai/docs/api-reference/rentals/get-a-list-of-reserve-options.md) and [Create a rental](https://hyperbolic.ai/docs/api-reference/rentals/create-a-rental.md).

> [!NOTE]
>
> Have a large or long-term commitment? You can also work with our team directly. [Contact sales](mailto:sales@hyperbolic.ai) to discuss volume pricing and terms.

Need dedicated, single-tenant infrastructure custom-built for your team instead? See [Private Cloud](https://hyperbolic.ai/docs/private-cloud/overview.md).


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