Vast.ai

Vast.ai GPU pricing overview

Vast.ai is a marketplace GPU cloud provider headquartered in San Francisco, CA. Vast.ai is a GPU marketplace where prices are set by supply and demand across 40+ data centers. 68+ GPU types spanning Blackwell, Hopper, Ada Lovelace, Ampere, Turing, Volta, Pascal — from B300 and H200 down to RTX 3090. Three pricing tiers: On-Demand (higher availability), Interruptible (lower cost, interruptible), Reserved (committed pricing). Per-second billing, no lock-in. SOC 2 certified. Check the live table for current rates. Billing is Per-second on-demand, Interruptible, Reserved with a minimum commitment of None. Available regions include US, EU, APAC, Various (40+ data centers). GPU instances can be provisioned on-demand, making Vast.ai suitable for both short-duration experiments and sustained production workloads.

Vast.ai vs other GPU providers

Vast.ai competes with providers including Lambda Labs, CoreWeave, RunPod, Paperspace, Vast.ai, and the major hyperscalers (AWS, Google Cloud, Azure) for GPU compute workloads spanning LLM training, fine-tuning, and inference serving. Key differentiators include: B300, H200, H100 — competitive frontier pricing on marketplace rates; RTX 5090, RTX 4090 — consumer GPU inference at marketplace rates; 68+ GPU types from RTX 3060 to B300 — wide selection. Use the side-by-side comparison tool above to see Vast.ai pricing against any other provider across shared GPU models. For a broader market view, the live GPU prices table shows all 4 Vast.ai listings alongside 91+ providers in a single sortable view.

Best use cases for Vast.ai

Vast.ai is best suited for: Budget AI training and fine-tuning, Batch inference on consumer GPUs, Teams needing maximum GPU variety, Researchers avoiding waitlists and quotas. Support tiers range from Community → Enterprise, making it viable for both individual researchers and enterprise teams with SLA requirements. There are currently 4 active GPU listings on Vast.ai, covering L4, RTX 3090, RTX 3080, RTX 4090. H100 SXM5 instances with NVLink interconnect are commonly used for large-scale training workloads. A100 40GB and RTX 4090 instances are frequently used for fine-tuning and inference of smaller models.

Vast.ai billing model and cost structure

Vast.ai uses Per-second on-demand, Interruptible, Reserved pricing. Spot (interruptible) instances are available from $0.04/hr — interruptible instances are typically lower-cost than on-demand, suitable for fault-tolerant training jobs with checkpointing. Reserved instance pricing may be available for predictable long-running workloads — check the provider's pricing page for current committed-use rates. Always compare the effective hourly rate including egress, storage, and networking costs when evaluating total cost of ownership across providers.

Choosing the right GPU on Vast.ai

GPU selection depends on model size, precision, and whether your workload is compute-bound or memory-bandwidth-bound. For LLM training above 30B parameters, H100 80GB SXM5 instances with NVLink are the standard choice — high HBM3 bandwidth and FP16 throughput make them well-suited for large transformer workloads. For inference of 7B–13B models in FP16 or BF16, A100 40GB is a common choice on many providers. RTX 4090 instances are widely used for fine-tuning, prototyping, and quantized inference (INT4/INT8) of models up to 70B. Read the H100 vs A100 guide or the GPU benchmarks for ML guide for a full breakdown.

How Vast.ai pricing data is collected

Prices shown are sourced from Vast.ai's public pricing API or pricing page and refreshed every 15 minutes. On-demand rates reflect the current list price for a single GPU instance in the cheapest available region. Spot prices, where available, reflect interruptible instance rates at the time of the last snapshot. All prices are in USD per hour. Daily snapshots are kept in our history archive and visualised in the GPU price history charts — useful for identifying seasonal pricing patterns and evaluating whether current rates are above or below the 30-day average.

Evaluating managed LLM inference APIs as an alternative to self-hosted GPU compute? Compare live LLM token prices across OpenAI, Anthropic, Google, Groq, and many other providers. The cheapest GPU cloud guide covers the break-even analysis between self-hosted and managed inference at different request volumes.