
Facts from Vast.ai’s own pricing and docs pages, September 2026 — 50 read from a quoted sentence on the page we archived.
Vast.ai rents GPUs from $0.10 per GPU-hour on demand, bills per second. The minimum to start is $5 minimum to start. Vast.ai does not publish an uptime SLA.
| On-Demand | Interruptible | Reserved | |
|---|---|---|---|
| From | Market-set; H100 from $0.90/hr | Often 50%+ below on-demand | Up to 50% off on-demand |
| Minimum term | None; $5 to get started | None | 1, 3 or 6 months |
| Billing | Per second | Per second | Prepaid for the term |
| Uptime SLA | Guaranteed uptime, no interruptions | None — preemptible | Guaranteed capacity |
| Tenancy | Isolated instance on a host's machine | Same machines; may be paused when outbid | Guaranteed capacity |
| Provisioning | ~60 seconds | ~60 seconds | Convert a running on-demand instance |
| Payment | Prepaid credits | Prepaid credits | Prepaid credits |
As of September 2026, the lowest published on-demand rate is $0.10 per GPU-hour for the NVIDIA RTX 5060 8GB. Vast.ai publishes an on-demand rate for 17 GPU models. Billing is per second.
Vast.ai does not publish an uptime commitment on its own site.
Vast.ai states its minimum as $5 minimum to start.
Vast.ai states its egress terms as priced per byte by each host.
Vast.ai states that signup is self-serve. On approval and identity checks it states: card and email verification.
Vast.ai states: spent credits final; unspent balance refundable at discretion.
Vast.ai lists 40+ data centres worldwide.
The contracting entity is Vast.ai Inc. (Delaware).
Reviewed September 2026, from Vast.ai’s own site. 50 facts, each quoted from the page it was read on.