ProductBenchmarksDevelopers EnterprisePricingDownload ResearchFAQStatus GitHub Trust & Legal 한국어로 보기
Native inference runtime

More models. More GPUs. One runtime.

Install opens soon. Reserve your spot — the launch notice goes out automatically to everyone on the list. Reserving is free and collects no payment.

Veizik is native inference infrastructure for modern generative AI — built to adapt image and video models across GPU generations, memory tiers, and runtime profiles. Measured on real hardware: its own publisher asks for a GPU with 80 GB; veizik ran the same clip at 6.5 GB on one RTX 3090.

Measured on real hardware.

Free when it opens · reserve to get notified Linux and Windows 11 + WSL2 · NVIDIA GPU (per-model VRAM in the table) Runs on your GPU — nothing is uploaded
seed Qwen-Image-2512 Apache-2.0 motion Wan2.2-I2V-A14B Apache-2.0 832×464 · 81f · 40 steps one RTX 3090 delivered 1280×720 · 24 fps C2PA signed · what that means
6
model families on one engine
Linux
+ NVIDIA · Windows WSL2 experimental
0
media or prompts leave your machine
0
per-render charges — you supply the GPU
Verified execution

Support means it actually ran.

Every verified Veizik configuration is tied to measured execution on real hardware — model hash, resolution, frame count, steps and seed all published, with wall time and peak VRAM taken from the run itself.

Video

Wan2.2-I2V-A14B on one RTX 3090 — 6.5 GB peak vs 17.7 GB for the standard fp8 offload path, same clip, same card.

GPU RTX 3090 24GB · 848×480 · 81f · 8-step distilled profile
Peak VRAM 6.5 GB · Drift −8…−11%
Evidence VZK-WAN22-I2V-INT8-3090

Footprint result for the distilled profile. Separate from the 40-step production profile — not an identical-condition comparison.

Image

FLUX.1-dev at 1024², 24 steps, on one RTX 3090 — measured end-to-end, not estimated.

GPU RTX 3090 24GB · 1024² · 24 steps
E2E 49.25 s · Peak VRAM 12.78 GB
4 warm runs · ±0.64s

Memory & Speed

LTX-Video 2B — a 24 GB-class card holding the full run with room to spare, 5 repeated runs, zero spread.

GPU RTX 3090 24GB · 768×448 · 49f · 30 steps
E2E 18.5 s · Peak VRAM 9.55 GB
5 runs · spread 0.00

Every figure ships with the config that produced it and a run manifest you can diff against your own. Explore all benchmarks →

Real renders

Made locally with the Veizik engine

A high-resolution still, turned into a cinematic film with image-to-video — all on one local GPU, nothing leaves the machine.

Wan2.2-I2V · 3 s · click to play

Strawberry splash

C2PA signed
Qwen-Image-2512 (Apache-2.0) → Wan2.2-I2V-A14B · 1280×720 · 24 fps

More renders on the product page →

Compatibility

Model families with a native engine path

These families have a native engine path, each numerically checked at the block/engine level (rel_L2 ~1e-6–1e-7 vs reference — a component check, not an end-to-end render benchmark). A universal fallback path for other models is under development.

Native engine

Step-Video 30B

rel 2.35e-6 · single GPU
Native engine

HunyuanVideo

measurements withheld
⚠ Licence restricted in KR / EU / UK — model licences
Native engine

Wan 2.1

rel 5.53e-7
Native engine

LTX-Video

rel 1.94e-7 · measured
Native engine

CogVideoX

rel 8.43e-7
Native engine

FLUX.1-dev

rel 4.58e-7 · image
planned

Llama / Qwen

LLM · OpenAI-compatible endpoint
Planned

Universal fallback

other models · in development
Test conditions

How every figure on this page is measured

One pinned config per row — model hash, prompt, seed, scheduler, steps, resolution, frame count and power cap all fixed and recorded — so the same command reproduces the same number on the same card. Full method: benchmark-method.md.

Render · 24 GB card, sole tenantWall timeOOM
LTX image-to-video · 1216×704 · 49f · 30 steps33.5 snone
LTX image-to-video · 1216×704 · 73f · 30 steps71.3 snone
LTX text-to-video · 1216×704 · 49f · 30 steps32.2 snone
Warm runs, fixed seed, one card, sole GPU tenant, power cap recorded per run. The remaining model families are measured in the table further up this page; this block is the LTX resolution/frame sweep only.
Engine pathBlock/engine rel_L2
Step-Video 30B2.35e-6block-level
LTX-Video1.94e-7block-level
CogVideoX8.43e-7block-level
Wan 2.15.53e-7block-level
FLUX.1-dev4.58e-7block-level
Numerical equivalence vs the reference implementation at the block/engine level — not an end-to-end generation benchmark.
VRAM budget · measured on a 24 GB cardLTX-Video 2B working set 9.55 GB
9.55 GB 24 GB
LTX-Video 2B at 768×448 · 49f · 30 steps · seed 42 — spread 0.00 across 5 runs. Ran it on your own card? Post the result.
Preview in 3 steps

Install, check your hardware, activate.

1 · Install

curl -fsSL https://veizik.com/install.sh | sh on Linux or Windows WSL2 (git + Python 3.10+). No key needed to install.

2 · Check your hardware

veizik doctor scans this machine and prints the support tier per model family — so you know what runs before you commit.

3 · Activate a free key

veizik login <key> redeems a free key from veizik.com for a signed entitlement. Universal t2v render is experimental today.

Plans

The runtime is the product. Licensing follows capability and deployment scope.

Install is free, and inspecting the hardware scan and entitlement client is free. What you buy is a local runtime license: which model families the engine will run, how far you can push resolution and length, commercial use rights, and the advanced execution paths. No cloud credits. You supply the GPU.

Licence unit = 1 key, 1 PC. Rungs differ only by what the engine can do — never by how much you render. Need a second machine? That's a second key (volume discount from 5). Changing hardware is 3 self-service transfers a year.

There is no per-render charge, and there never will be. The engine runs on your GPU and your electricity — we don't pay for your renders, so we don't bill for them.

FREE free
$0
Install free, verify on your own GPU, run the reproducible bench and submit your run-manifest.
  • LTX-Video and Wan 2.2 · up to 1280×720 · 121 frames
  • doctor hardware + per-model support scan
  • Run the fixed-config benchmark & submit results
  • 1 key · 1 PC
  • No watermark. Commercial use permitted — each model keeps its own licence
  • Machine-readable AI provenance marking stays on in every tier and does not restrict your rights. It is not a visible watermark. What this means and why
Start free
FRONTIER
$29 /mo · or $249/yr
Annual works out to just over three months free versus paying monthly. Install free now, upgrade the same key later.
  • + CogVideoX, FLUX · up to 1920×1080 · 241 frames
  • Commercial use of Veizik Runtime included — upstream model terms remain applicable
  • Sell what you render. Running Veizik itself as a shared server, a render fleet or a hosted service is a Business licence — that is about deployment, not about what you earn.
  • Machine-readable AI provenance marking stays on in every tier and does not restrict your rights. It is not a visible watermark. What this means and why
  • Runtime rights only — each model keeps its own licence. FLUX.1-dev is non-commercial. Model licences Benchmarks Third-party notices
  • After 12 months, one version is yours to keep — permanently, even if you stop paying how
  • Stable pinned profiles (not experimental)
  • Frontier Model Adapters & Capsules
  • 1 key · 1 PC · device change 3×/year, self-service
Get Frontier
PRO invited preview
$69 /mo · or $599/yr — preview, not yet billed
Pro is the automation tier. Its three defining capabilities — the automation API, queue & batch execution, and recovery — are not generally available, so it is not for sale. It runs as an invited preview at no charge, and opens for purchase on the day those three ship.
  • The engine’s full model range — see the licence and territory registry for what each model permits where
  • No resolution or frame cap
  • Commercial use of Veizik Runtime included — upstream model terms remain applicable
  • After 12 months, one version is yours to keep — permanently, even if you stop paying how
  • Low-VRAM layer streaming · LoRA / adapters
  • Advanced FP8 / INT8 quantization private preview
  • Queue & batch execution development
  • Recover / TimeMachine / automation API private preview
Join Pro Preview
ENTERPRISE private pilot
Custom · scoped per deployment
Enterprise covers organisational deployment — headless serving, multi-GPU execution and central licence control. Those are not generally available, so Enterprise is run as a scoped pilot with a measured report rather than sold from this page.
  • Everything in Pro — identical model families, no resolution or frame cap
  • Multi-GPU on one machine — every card in the box drives one render
  • Audit log — every render on the node, exportable
  • Dedicated / private Model Adapters
  • Headless serve (no desktop session) development
  • Central license server for a fleet development
Talk to Engineering
Not open yet. We are piloting with individual creators first and will open the node tier once that is steady. Tell us what you need and we will come back to you when it opens.

Every tier writes a machine-readable AI provenance mark (C2PA); it cannot be switched off. No tier watermarks your output — not even the free one. Veizik writes machine-readable AI provenance metadata to supported output formats per the active product policy — that is metadata in the file, not a visible mark on the picture. AI Transparency → AI transparency · Model licences — a paid tier licenses the runtime, not the models.

Twelve paid months earn you one version, permanently. Not a discount and not a trial. Complete a paid year and every version released during it is yours — including the one you were actually running on your last paid day, not a build from twelve months earlier. It keeps working at your tier if you stop paying, and if we stop existing. What exactly you get — including what we owe you if we shut down, the limits we cannot insure against, and the one condition we have not finished building, which is why nothing is issued today.

Running a GPU fleet? by inquiry

We measure whether your current model and quality target can move to a lower-cost accelerator tier — same weights, same output target, reported GPU memory, host memory, throughput and cost per output. Evaluations, design-partner pilots and OEM/embedding agreements are scoped per engagement.

Talk to sales

Frontier billing is live — checkout charges your card today. Pro and Enterprise open for self-serve purchase once their gated capabilities ship; join the preview to get notified. Enterprise and deployment enquiries: sales@veizik.com.

What "commercial output" means: it is your right to use the Veizik runtime commercially. It does not change the licence of the underlying models — those keep their own terms. FLUX.1-dev is published under a non-commercial licence, and HunyuanVideo's licence does not apply in the EU, UK or South Korea. Check every model you plan to bill for on the model licences page before you take paid work.

One installer, every tier — no separate builds. Capabilities are enabled according to your licensed runtime tier; a server-signed entitlement unlocks what your plan includes. The runtime — not the UI — enforces features. Billing by Polar (merchant of record; USD, tax included). Veizik does not ship face swapping, lip-sync, or voice cloning — those capabilities are not in any build. Available globally today, with the EU, EEA and UK opening once regional compliance requirements are in place. Feature states are labelled research / development / private preview / public preview / shipped.

Enterprise

More useful work from the GPU fleet you already operate.

Veizik Enterprise provides workload qualification, runtime deployment, model governance, and production support.

Talk to Engineering

See what your GPU can run.

No payment, no spam. Launch, billing-open, and Preview-build notices only, sent automatically.