⚡Under $0.50/hr🧠VRAM Estimator⚖Compare GPUs🎁Free LLM APIs🎯Model Index
Cloud GPUper-second Live

Vast.ai — Peer-to-Peer GPU Marketplace

Workload Suitability Matrix: Multi-Node Training: Marketplace model aggregates idle consumer and enterprise GPUs; pricing determined by supply and demand; reliability varies by host with uptime rangin...

Cloud GPU Pricing

GPUVRAMInterconnectSpotOn-DemandMonthlyDeploy
RTX 409024GB GDDR6XPCIe 4.0 (64 GB/s)$0.34$0.34$208Deploy →
L40S48GB GDDR6PCIe 4.0 (64 GB/s)$0.69$0.69$422Deploy →
H100 SXM580GB HBM3NVLink 4.0 (900 GB/s)$1.89$1.89$1,157Deploy →
H200141GB HBM3eNVLink 4.0 (900 GB/s)$2.79$2.79$1,707Deploy →
B200192GB HBM3eNVLink 5.0 (1.8 TB/s)$3.99$3.99$2,442Deploy →

Competitor Comparison

PROVIDERMIN PRICE / HRAVG TOKEN RATEFREE TIERBILLINGKEY ADVANTAGE
Vast.ai$0.34—No free tier; lowest hourly ra...per-second★ You are here
RunPod$0.39—No free GPU tier; 20% off firs...per-secondCommunity & Secure GPU Cloud

Technical Nuances & Editorial Analysis

Workload Suitability Matrix: Multi-Node Training: Marketplace model aggregates idle consumer and enterprise GPUs; pricing determined by supply and demand; reliability varies by host with uptime ranging from partial to 99.9%. Spot Inference Prototyping: Lowest hourly rates across H100, H200, B200, and RTX 4090; community tier carries preemption risk; ideal for batch inference, fine-tuning, and experimentation. Persistent Production API: Users must verify GPU health and uptime history before committing to long-running workloads; CLI deployment and custom container images supported for vLLM, Ollama.

Billing Granularity

per-second

How charges are calculated

Hidden Costs

Variable reliability; some instances may be preempted by host

Watch out for these fees

Free Tier

No free tier; lowest hourly rates available

Credit requirements and caps

Best Use Case

Best for flexible GPU workloads

Ideal workload profile

Frequently Asked Questions

What is the cheapest instance/model on Vast.ai?▾
The lowest spot rate on Vast.ai is $0.34/hr for RTX 4090.
Does Vast.ai offer a free tier without a credit card?▾
No free tier; lowest hourly rates available
How does Vast.ai compare to its cheaper alternatives?▾
Compared to competitors like RunPod, Vast.ai offers peer-to-peer gpu marketplace with per-second billing. Rates range from $1.94 to $3.99 per hour depending on GPU model.
Data Freshness: Verified via Official Provider APIs & Documentation | Refreshed WeeklyPricing sourced from Vast.ai official documentation and public APIs.Methodology →

Cost Analysis & Deployment Guides

What should I do next?