Vast.ai
GPU marketplace with competitive pricing
Last reviewed Mar 14, 2026
Vast.ai is a GPU marketplace with live, supply-and-demand pricing across community hosts and Secure Cloud datacenter partners. Instances are provisioned through the console, CLI, Python SDK, or REST API and billed per second.
Available GPUs
Hourly on-demand pricing. Click column headers to sort.
Prices last updated: September 26, 2026
Vast.ai pricing by GPU
Configurations, price rank, and alternatives for one GPU at a time.
Pros & Cons
Advantages
- Significant cost savings with supply-demand pricing
- Flexible pricing with on-demand, interruptible, and reserved options
- Real-time transparent pricing with no hidden fees
- Docker ecosystem for quick software deployment
- SOC 2 Type II certified infrastructure
- Supports various AI and deep learning workloads
- CLI, SDK, and API for automated deployment
- Prebuilt templates and a model library for one-click deployment
- Per-second billing for cost optimization
Limitations
- Primarily focused on Linux-based Docker instances
- Performance may vary across different community providers
- Learning curve for users unfamiliar with marketplace-based pricing
- Limited GUI options compared to traditional cloud providers
Key Features
Real-Time GPU Pricing
Prices set by supply and demand across the platform with no list prices or hidden fees
Three Deployment Options
GPU Cloud for full control, Serverless for zero-ops inference, Clusters for large-scale training
Developer-Focused Tools
CLI, Python SDK, and REST API for programmatic GPU provisioning, installed together via a single package
Agent-Ready Provisioning
API-native workflow intended for AI agents to search, procure, and release compute autonomously
Model Library and Templates
Prebuilt templates for popular open-source models, plus custom templates any GPU can run with one click
Flexible Infrastructure
Scale from $5 to 20,000 GPUs across 40+ data centers without contracts or minimums
Team Accounts
Shared team workspaces with role-based access for managing members and instances
Compute Services
GPU Cloud
On-demand instances across 40+ data centers and 20,000+ GPUs
Serverless
Deploy models as endpoints with autoscaling to zero
Clusters
Dedicated multi-node GPU clusters with InfiniBand networking
Pricing Options
| Option | Details |
|---|---|
| On-Demand | Guaranteed uptime with per-second billing. Best for production workloads. |
| Interruptible | 50%+ cheaper preemptible instances. Best for fault-tolerant batch training. |
| Reserved | Up to 50% off with 1, 3, or 6 month commitments. Guaranteed capacity with volume discounts. |
| Serverless | Endpoint rates billed only for compute time, with no charge while workers are scaled to zero. |
Availability & Support
Regions
40+ data centers with global coverage including community and enterprise providers
Support
24/7 support chat in the console, email support at contact@vast.ai, Discord community, and documentation covering the CLI, SDK, and REST API
Getting Started
- 1
Add credit and get your API key
Start with as little as $5 and grab an API key from the console. No contracts, no sales calls.
- 2
Search GPUs
Filter by model, VRAM, price, and availability via the console or API
- 3
Deploy
Launch instances in seconds. Scale up or down programmatically.
Frequently Asked Questions
What GPU types does Vast.ai offer?
Vast.ai offers various GPU types including GTX 1080 Ti, GTX 1080 Ti, GTX 1080 Ti, GTX 1080 Ti, A100 PCIE, A100 PCIE, A100 PCIE, RTX 4070, RTX 4070, RTX 2060, RTX 2060, RTX 2060, RTX 2060, Tesla T4, GTX 1070, RTX PRO 4000, RTX PRO 4000, RTX PRO 4000, RTX A6000, RTX A6000, RTX A6000, GTX 1650, Quadro RTX 8000, Quadro RTX 8000, A100 SXM, A100 SXM, A100 SXM, GTX 1660 SUPER, GTX 1660 SUPER, GTX 1660 SUPER, GTX 1660 SUPER, RTX 5000 Ada, RTX 5000 Ada, H100 SXM, H100 SXM, H100 SXM, Tesla P40, RTX 2060 SUPER, H200, H200, H200, H200, RTX 5060, RTX 4060, RTX 4060, RTX 4060, H100 NVL, H100 NVL, Quadro RTX 6000, L40, L40, RTX 5080, RTX 5080, RTX 4080 SUPER, RTX 4080 SUPER, Titan RTX, Titan RTX, A10, A10, RTX 4500 Ada, RTX 4500 Ada, RTX 3080, RTX 3080, Quadro P4000, Quadro P4000, GTX 1080, GTX 1080, GTX 1080, GTX 1080, RTX 4080, RTX 4090, RTX 4090, RTX 4090, RTX 4090, RTX 4090, RTX 4090, RTX 4090, RTX 3070, RTX 3070, A40, A40, A40, RTX 3070 Ti, RTX 3070 Ti, RTX 2080 Ti, RTX 2080 Ti, RTX 6000 Ada, RTX 6000 Ada, HGX B300, HGX B300, HGX B300, HGX B300, RTX 4060 Ti, RTX 4060 Ti, RTX PRO 5000, RTX PRO 5000, RTX PRO 5000, RTX PRO 5000, RTX A4000, RTX A4000, RTX A4000, RTX 3080 Ti, RTX 3080 Ti, RTX 5060 Ti, RTX 5060 Ti, RTX 3090 Ti, RTX 5070 Ti, RTX 5070 Ti, Titan Xp, Titan Xp, Titan Xp, L40S, L40S, L40S, L40S, GTX Titan X, GTX Titan X, RTX 5070, RTX 5070, H100 PCIe, RTX 2070, RTX 2070, RTX 4070 Ti, RTX 4070 Ti, RTX 5090, RTX 5090, RTX 5090, RTX 5090, RTX 5090, RTX 5090, B200, B200, B200, B200, GTX 1660 Ti, GTX 1660 Ti, Tesla V100, Tesla V100, Tesla V100, A16, L4, L4, L4, RTX PRO 6000, RTX PRO 6000, RTX PRO 6000, RTX PRO 6000, RTX PRO 6000, RTX 3090, RTX 3090, RTX 3090, RTX 3090, RTX 3060, RTX 3060, RTX 3060, RTX 3060, RTX PRO 4500. Check the pricing table above for current availability and pricing.
How do I get started with Vast.ai?
Add credit and get your API key, Search GPUs, Deploy
What are Vast.ai's main advantages?
Vast.ai's main advantages include: Significant cost savings with supply-demand pricing, Flexible pricing with on-demand, interruptible, and reserved options, Real-time transparent pricing with no hidden fees, Docker ecosystem for quick software deployment, SOC 2 Type II certified infrastructure, Supports various AI and deep learning workloads, CLI, SDK, and API for automated deployment, Prebuilt templates and a model library for one-click deployment, Per-second billing for cost optimization.
What are Vast.ai's limitations?
Vast.ai's main limitations include: Primarily focused on Linux-based Docker instances, Performance may vary across different community providers, Learning curve for users unfamiliar with marketplace-based pricing, Limited GUI options compared to traditional cloud providers.
Compare Providers
Find the best prices for the same GPUs and models from other providers
