GPU Catalog Pricing Templates Regions Docs

Log in Launch GPU

Cloud GPUs by the minute

Product

GPU catalog
Templates
Regions
Pricing
VRAM calculator
Model GPU requirements
Solutions
Comparisons
Guides

GPU rental

Rent a graphics card
GPU server
Cloud GPU
Hourly GPU rental
GPU VPS
GPU for AI
Rent RTX 4090
Rent RTX 5090
Rent RTX 3090
Rent A100
Rent H100
Rent L40S

AI apps

All templates
ComfyUI
Open WebUI + Ollama
Stable Diffusion Forge
vLLM
Whisper
Run AI models privately
Stable Diffusion: install guide
FLUX: which GPU you need
Ollama: install and API
A server for AI

Company

Business
About
Docs
MCP for AI agents
Support
Telegram channel
GitHub

Legal

Public offer
Privacy policy
Personal data consent
Acceptable use
3D model credits

Protection and listings

DDoS protectionStormWall
Verified profileSaaSHub
Listed onDevHunt
Review us onTrustpilot

Prices are in dollars per hour, billed by the minute · © 2026 gpu.nzPayment: SBP and cryptoServices are provided by Transtrade LLC (OsOO «Transtrade»), registration No. 310961-3301-ООО, INN 9909710251, address: 66 Kalyk Akiev St., Leninsky District, Bishkek, Kyrgyz Republic

Rent graphics cards and GPU servers: every option · gpu.nz

HomeGPU rental

GPU rental: graphics cards, servers and cloud

A graphics card for an hour or a GPU server for a month, a cloud GPU for AI or a VPS with CUDA — it is the same server with an NVIDIA card, billed per minute. Pick the page that matches your job.

Browse all GPUs

Rent a graphics card online, billed by the minuteRent an NVIDIA graphics card on a server: RTX 3090, 4090, 5090, A100, H100. Starts in minutes, billed per minute from your balance, with SSH and ready AI apps.
GPU server rental: 1 to 8 GPUs, billed by the minuteRent a GPU server with 1 to 8 whole NVIDIA GPUs, root over SSH and a country of your choice. Starts in 2–5 minutes, billed per minute from your balance.
Cloud GPU rental: an NVIDIA graphics card by the minute, no purchaseA cloud GPU without buying a card: rent an RTX, A100 or H100 for the minutes you need. Work from a browser or over SSH, top up with cryptocurrency or through SBP.
Hourly and per-minute GPU rental: how billing worksHourly and per-minute GPU rental: a price per hour, charged by the minute from your balance. What you pay for while a server runs, is stopped or deleted, and how to save.
GPU VPS rental: a Linux server with a graphics card and root over SSHGPU VPS rental: a Linux server with root over SSH and a whole NVIDIA card. How it differs from a regular VPS, how to set it up and what it costs, billed per minute.
Rent a GPU for AI: LLMs, images, video and trainingRent a GPU for AI: run an LLM, Stable Diffusion, ComfyUI or LoRA training on an NVIDIA card. Ready templates, per-minute billing from your balance, SSH access.

What to run on a rented GPU

Run LLMs on a rented GPU: Llama, Qwen, DeepSeek, MistralRun Llama, Qwen, DeepSeek and Mistral on a rented GPU: Ollama with a chat UI or vLLM with an API. Which card you need, what an hour costs, and how to start.
Stable Diffusion and FLUX on a rented GPU: Forge and SDXL onlineStable Diffusion, SDXL and FLUX on a rented GPU with the Forge template. How much memory you need, what a minute of generation costs, and how to avoid paying for idle time.
ComfyUI online on your own server: FLUX, Wan and HunyuanVideoComfyUI on a rented GPU with a ready template: FLUX, SDXL, Wan and HunyuanVideo, workflows and an API. Which card to choose and what it costs.
Fine-tuning and LoRA training on a rented GPULLM fine-tuning and LoRA training on a rented GPU: how much memory a 7B model needs, QLoRA, Kohya for SDXL and FLUX. Time and cost estimates.
JupyterLab with a GPU for rent: PyTorch, CUDA and data scienceJupyterLab with CUDA and PyTorch on a rented GPU, billed per minute. Experiments, notebooks and data prep without buying a GPU.
GPU rendering on a rented server: Blender Cycles and 3D by the minuteRendering in Blender Cycles on a rented CUDA GPU. When renting beats buying, how to start a render over SSH, and what an hour costs.
Video generation on a rented GPU: Wan and HunyuanVideo in ComfyUIWan and HunyuanVideo video generation on a rented GPU through ComfyUI. How much memory short clips and 14B models need, and what an hour costs.