Rental Types

We currently offer three main rental pricing options: On Demand (High Priority), Reserved (High Priority), and Interruptible (Low Priority). On Demand instances have a fixed price set by the host and run for as long as the client wants. Prepaid instances are created from on demand by depositing credits to purchase longer time blocks (months) in advance, in exchange for significant discounts (up to 50%, depending on the provider). Interruptible instances use a bidding system: clients set a bid price for each instance; the host then decides which instances run when to maximize revenue (naturally favoring higher bidders).

In the create interface there is a selector for either "on-demand" or "interruptible". Once the instance is rented, there is currently no way to change the bidding method. In general, on-demand is typical for most tasks where you need reliable access or continous uninterrupted workloads. Using Interruptible instances can reduce costs in half or more for specific use cases where horizontal scalability at low prices is more important than execution guarantee, but requires some extra work to maintain the continuity of work performed.

Renting an instance on-demand means that you have exclusive control over the GPU(s) and have high priority. The instance can be run as long as the host has set the "maximum duration" which appears on the create interface card. Once that time limit has been reached, the host can either renew the contract or stop the instance. Typically this is done to take the machine offline for upgrades or planned maintenance.

For large AI/ML jobs that could take many days or weeks to run, make sure the host has a high reliability score and that the maximum duration is greater than the time estimated for the job. When an on-demand instance is stopped by the user (or host in the case of the contract expiring) the data on the machine is still accessible.

You can deposit credits to get reserved discounts at any time, converting an on demand rental into a pre-paid reserved rental. Any funds deposited are locked into that specific instance. If you later change your mind, you can withdrawal only any fraction of the funds that remain after paying the difference between the on demand and discounted price over the current duration. If the machine fails the implicit or explicit Service Level Agreement and is deverified the full balance can be withdrawn without penalty.

Interruptible instances are unique on Vast in that they use a bidding system for priority. The higher the bid for a given instance, the higher priority that instance has on the machine. Lower priority instances are paused until they become the highest priority, either through a raised bid or the higher bid finishing their job. On-demand instances always have a higher priority than interruptible.

If another user places a higher bid or creates an on demand rental for the same resources then your instance will be stopped. Stopping an instance kills the running processes, so when you are using interruptible instances it's important to save your work to disk. Also we highly recommend having your script periodically save your outputs to cloud storage as well, because once your instance is interrupted it could be a long wait until it resumes.

Once an instance is paused, the data is still available on the machine to be copied, but the instance is otherwise not functional until it regains priority.