Overview
Strengths & Best For
CloudGPU rents on-demand GPUs billed per minute, with root SSH access and templates for Ollama, JupyterLab, ComfyUI and LLaMA-Factory. Prices come from CloudGPU's public price feed.
- Per-minute billing — pay only for what you use
- Root SSH access on every instance
- Ready-to-use templates: Ollama, JupyterLab, ComfyUI, LLaMA-Factory
- Wide consumer and data-center GPU selection
- Smaller provider — limited scale vs hyperscalers
- No enterprise SLAs or compliance certifications
- Region information not published per instance
No reviews yet — add yours ↗
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.
- 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
- Per-second billing, no minimum hours, no lock-in
- Interruptible tier: lower cost than on-demand
- SOC 2 certified
- Marketplace model — hardware quality and reliability varies by host
- No enterprise SLAs or uptime guarantees
- Interruptible instances can be reclaimed at any time
Affiliate link — we may earn a commission.
No reviews yet — add yours ↗
Live GPU Pricing
Green = lower price. On-demand hourly rates. Updated every 15 minutes.
Region Coverage
Popular Comparisons
Provider pages
Key differences
CloudGPU
On-demand GPUs billed per minute — RTX 3090 to A100, root SSH, Ollama and ComfyUI templates
Vast.ai
B300, H200, RTX 5090 — 68+ GPU types, per-second billing