HZ AIHZ AI
Rent it  ·  Buy it

GPU infrastructure
for AI teams.

Rent GPUs by the second when you need them, or buy the hardware you need.

Per-second billing Hardware you own
NVIDIA A100H100RTX 4090vLLMPyTorchCUDA 12DockerOllamaComfyUIJupytergVisor
NVIDIA A100H100RTX 4090vLLMPyTorchCUDA 12DockerOllamaComfyUIJupytergVisor
Two ways in

Rent the compute, or own the hardware

Some teams just need GPUs for a job and want them gone by morning. Others want racks they control. We do both.

Pay for access

Rent Compute

For teams that need GPUs now and don't want to own anything. Start a node in seconds and only pay for the seconds you use.

  • Serving LLMs and model endpoints
  • Training and fine-tuning runs
  • Batch and data jobs
Own the equipment

Buy Hardware

For teams that would rather own the machines. We find the parts, build the boxes, test them, and ship them to your rack.

  • GPUs and full GPU servers
  • RAM, storage, and networking
  • Complete builds, configured to spec

Nodes online

Jobs completed

Running now

99.9%

Uptime

The platform

Your GPU control plane

See what's online, launch it in a click, and run every endpoint, job, and invoice from one place.

hz-ai.io/marketplace

Marketplace

128 GPUs online across 14 regions

NVIDIA H100 80GB

16 vCPU · 192GB · Frankfurt

$2.89/hrDeploy

NVIDIA A100 80GB

12 vCPU · 128GB · Oregon

$1.89/hrDeploy

RTX 4090 24GB

8 vCPU · 64GB · Singapore

$0.54/hrDeploy
How it works

Three steps to a running GPU

Live marketplace

H100 80GB

Frankfurt

$2.89/hrSelected

A100 80GB

Oregon

$1.89/hr

RTX 4090

Singapore

$0.54/hr
Use cases

What people actually run on it

Fine-tuning, rendering, inference, batch jobs. The heavy stuff, at a fraction of cloud prices.

LLM Inference

Deploy vLLM, Ollama, or TGI endpoints. Serve Llama 3, Mixtral, and Phi on real GPUs.

vLLMOllamaTGILlama 3

Model Fine-Tuning

LoRA or full training runs. Persistent volumes keep your checkpoints safe between sessions.

LoRAPyTorchDeepSpeed

Image Generation

Stable Diffusion, ComfyUI, and more. Serve as an endpoint or batch thousands of images.

SDXLComfyUIFlux

Video & 3D Rendering

Blender, Unreal, or custom pipelines distributed across multiple GPU nodes.

BlenderUnrealOptiX

Data Processing

RAPIDS, GPU Spark, or custom ETL. Process terabytes with GPU acceleration.

RAPIDSSparkDask

Research

Jupyter, PyTorch, experiment tracking. SSH in and work like it's a local machine.

JupyterPyTorchW&B
Live marketplace

Available right now

Buy Hardware

Prefer to own? We sell the hardware too.

GPUs, servers, RAM, storage, networking, or a whole node, built and tested to your spec. We send an itemized quote before anything ships.

GPUs Servers RAM Storage Networking Full builds
Security

Built so tenants can't touch each other

Isolation and zero-trust at every layer, on by default.

gVisor Sandbox

Optional userspace syscall interception — the same isolation model as Google Cloud Run.

Container Isolation

Per-job containers, dropped capabilities, read-only rootfs, enforced PID limits.

Constant-Time Auth

SHA-256 hashed API keys with constant-time validation and instant revocation.

Automatic TLS

Caddy provisions HTTPS automatically. HSTS enforced, mTLS between control planes.

Per-Second Billing

Real provider pricing, 5% platform fee, transparent invoicing with CSV export.

Memory-Safe Agent

Rust agent, zero GC pauses, Docker via library — no shell injection surface.

Rate Limiting

Per-buyer limits and idempotency keys, Redis-backed for sub-millisecond checks.

Full Observability

Prometheus metrics, Grafana dashboards, and alerting rules out of the box.

For GPU owners

Have GPUs? Put them to work.

Install the agent, set your price, and earn whenever a buyer runs a job on your hardware. You keep 95% of every transaction.

  • One-command install on Ubuntu / Debian
  • Set your own price per GPU-hour
  • Auto-detected specs shown to buyers
  • Fiat payouts, transparent earnings
provider setup
$ curl -fsSL https://hz-ai.io/install.sh | bash
✓ Installing HZ AI Agent v0.1.0…
✓ Detected 2× NVIDIA A100 80GB
✓ Agent registered and running

$ hzai-agent --price 1.89
Listing updated · $1.89 / gpu-hr
Waiting for jobs…

↳ Job received · buyer@corp.io
Earned $3.78 (2 GPU-hours)▋
FAQ

Questions, answered

You prepay with credits. When a job runs, compute is billed per second at the provider's GPU-hour rate. Unused credits stay in your account.

Yes. On-demand instances and dedicated reservations give you full SSH access. Your public key is configured in Settings.

Whatever providers list — today that spans consumer cards (RTX 4090, 3090) and data-center GPUs (A100, H100, A10G). The marketplace shows real-time availability.

Each job runs in an isolated container with a read-only root filesystem. Volumes are scoped per buyer and pinned per node, so no other buyer can reach your data.

Register a provider account, run the one-command installer on your Linux machine, set your price, and you're live. The agent auto-detects your GPU specs.

Any public image from Docker Hub, NVIDIA NGC, or GitHub Container Registry. Private-registry support is on the roadmap.

Spin up your first GPU
in under a minute.

Create an account and deploy your first workload in seconds.