> ## Documentation Index
> Fetch the complete documentation index at: https://vastai-80aa3a82-ltxv2-serverless.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Instance Types

> Understand Vast.ai instance types - On-demand, Reserved, and Interruptible. Learn how each type works, their differences, and when to use each.

<script
  type="application/ld+json"
  dangerouslySetInnerHTML={{
__html: JSON.stringify({
"@context": "https://schema.org",
"@type": "TechArticle",
"headline": "Vast.ai Instance Types",
"description": "Understanding Vast.ai's three instance types: On-demand (high priority, fixed pricing, guaranteed resources), Reserved (high priority with pre-payment discounts up to 50%), and Interruptible (low priority, lowest cost with bidding system), including key considerations and use case recommendations.",
"author": {
  "@type": "Organization",
  "name": "Vast.ai"
},
"articleSection": "Instances Documentation",
"keywords": ["instance types", "on-demand", "reserved", "interruptible", "pricing", "priority", "GPU rental", "vast.ai"]
})
}}
/>

Vast.ai offers three instance types with different priority levels and pricing models to match your workload requirements and budget.

## Overview

<CardGroup cols={3}>
  <Card title="On-demand" icon="shield-check">
    **High Priority**
    Fixed pricing, guaranteed resources
  </Card>

  <Card title="Reserved" icon="piggy-bank">
    **High Priority**
    Discounted rates with pre-payment
  </Card>

  <Card title="Interruptible" icon="shuffle">
    **Low Priority**
    Lowest cost, may be paused
  </Card>
</CardGroup>

In the create interface, you'll see a selector for "on-demand" or "interruptible". Once an instance is rented, you cannot change its type. However, you can convert on-demand instances to reserved for discounts.

## On-demand Instances

**Best for**: Production workloads, continuous training, time-sensitive tasks

On-demand instances provide:

* **Exclusive GPU control** with high priority
* **Guaranteed resources** for the contract duration
* **Fixed pricing** set by the host
* **Maximum duration** shown on offer cards
* **Data persistence** even when stopped

### Key Considerations

* Check the maximum duration before renting (shown on offer cards)
* For long-running jobs (days/weeks), verify host reliability scores
* When contracts expire, hosts may renew or stop the instance
* Data remains accessible when instances are stopped

<Warning>
  **Expired Instance Deletion**: Expired instances may be deleted 48 hours after expiration. Retrieve your data before then. Expired instances cannot restart while expired.
</Warning>

## Reserved Instances

**Best for**: Long-term projects, predictable workloads, cost optimization

Reserved instances are on-demand instances with pre-paid discounts:

* **Up to 50% discount** based on commitment length
* **Same high priority** as on-demand
* **Convert anytime** from existing on-demand instances
* **Credits locked** to the specific instance
* **Partial refunds** available if cancelled early

To create a reserved instance, first rent on-demand, then convert using the discount badge on your instance card.

<Info>
  For detailed instructions on creating and managing reserved instances, see [Reserved Instances](/documentation/instances/choosing/reserved-instances).
</Info>

## Interruptible Instances

**Best for**: Batch processing, fault-tolerant workloads, development/testing

Interruptible instances use a bidding system:

* **Lowest cost** (often 50%+ cheaper than on-demand)
* **Bidding priority** - higher bids get priority
* **May be paused** if outbid or if on-demand requested
* **Data preserved** when paused but instance not functional
* **Resume automatically** when priority returns

### Working with Interruptible Instances

<Warning>
  When using interruptible instances:

  * **Save work frequently** to disk
  * **Use cloud storage** for important outputs
  * **Implement checkpointing** in your code
  * **Expect interruptions** and plan accordingly
</Warning>

Priority rules:

1. On-demand instances always have highest priority
2. Among interruptible instances, highest bid wins
3. Paused instances resume when they regain priority

## Choosing the Right Type

| Use Case              | Recommended Type | Why                                    |
| --------------------- | ---------------- | -------------------------------------- |
| Production inference  | On-demand        | Need guaranteed availability           |
| Multi-day training    | Reserved         | Long-term discount with reliability    |
| Hyperparameter search | Interruptible    | Can handle interruptions, cost matters |
| Data preprocessing    | Interruptible    | Can resume where left off              |
| Time-critical jobs    | On-demand        | Cannot afford interruptions            |
| Development/testing   | Interruptible    | Short sessions, cost-sensitive         |
| Steady workloads      | Reserved         | Predictable usage, want discounts      |

## Quick Reference

### Switching Between Types

* **On-demand → Reserved**: ✅ Yes, anytime via discount badge
* **On-demand → Interruptible**: ❌ No, must create new instance
* **Interruptible → On-demand**: ❌ No, must create new instance
* **Reserved → On-demand**: ⚠️ Lose remaining discount

### Priority Levels

1. **On-demand/Reserved**: High priority, never interrupted
2. **Interruptible (high bid)**: Runs when resources available
3. **Interruptible (low bid)**: Paused until higher bids complete

## Next Steps

* **Compare costs**: Check current [Pricing](/documentation/instances/pricing)
* **Get discounts**: Learn about [Reserved Instances](/documentation/instances/choosing/reserved-instances)
* **Start renting**: [Finding & Renting](/documentation/instances/choosing/find-and-rent)