Vast.ai
GPU marketplace with competitive pricing
Last reviewed Mar 14, 2026
Vast.ai is a GPU marketplace with live, transparent pricing across thousands of community and datacenter hosts. Deploy high-performance GPU instances in seconds with transparent supply-and-demand pricing.
Available GPUs
Hourly on-demand pricing. Click column headers to sort.
Prices last updated: May 12, 2026
GPU Model↑ | Memory↑ | GPUs | Price / hr↑ | Updated↑ | Source |
|---|---|---|---|---|---|
| A10 | 24GB | 1× | $0.15/hr | 5/8/2026 | |
| A100 PCIE | 40GB | 1× | $0.48/hr | 5/12/2026 | |
| A100 SXM | 80GB | 1× | $0.47/hr | 5/11/2026 | |
| A40 | 48GB | 1×2× | $0.41/hr | 5/12/2026 | |
| L4 | 24GB | 1×2× | $0.13/hr | 5/12/2026 | |
| L40 | 40GB | 1× | $0.58/hr | 5/12/2026 | |
| L40S | 48GB | 1× | $0.56/hr | 5/12/2026 | |
| RTX 3070 | 8GB | 1×2×4× | $0.07/hr | 5/12/2026 | |
| RTX 3070 Ti | 8GB | 1× | $0.06/hr | 4/30/2026 | |
| RTX 3080 | 10GB | 1×2×4× | $0.12/hr | 5/12/2026 | |
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 certified infrastructure
- Supports various AI and deep learning workloads
- CLI, SDK, and API for automated 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
Flexible Infrastructure
Scale from $5 to 20,000 GPUs across 40+ data centers without contracts or minimums
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. |
Availability & Support
Regions
40+ data centers with global coverage including community and enterprise providers
Support
24/7 expert support, comprehensive documentation, Discord community, CLI and SDK tools
Getting Started
- 1
Add Credit
Start with as little as $5. No contracts, no minimums.
- 2
Search GPUs
Filter by model, VRAM, price, and availability across the platform
- 3
Deploy
Launch instances in seconds. Scale up or down anytime.
Compare Providers
Find the best prices for the same GPUs from other providers
