Bring Your Own GPU

Unlimited generations.
Pay nothing per mesh.

One flat $100/mo subscription for unlimited generations — text-to-3D, image-to-3D, mesh repair, validate + export — with no per-mesh metering. Generation runs on AXIS cloud today; the downloadable local worker (BYOGPU) is in preview. The engine itself is self-hostable and air-gapped-friendly.

$100 / month · unlimited generations
Download the worker →

Step 1 · Your hardware

Live capability check

We probe your browser for GPU adapter info. This is a fast first-pass eligibility signal — the real authority is the worker, which inspects nvidia-smi / system_profiler / wmic at registration time.

WebGPU adapter— probing —
Vendor
Architecture
Device
Max buffer size
Estimated tierchecking…

Minimum: 8 GB VRAM · Recommended: 16 GB · Best: 24 GB+ (RTX 4090 / 3090 / A6000). Integrated Intel iris/HD/UHD and AMD Vega 8/10 are not eligible — too little VRAM to run local generation reliably once the BYOGPU worker leaves preview.

Step 2 · Why creators go flat-rate

Stop paying per mesh

What it costsCloud GPU planBYOGPU Unlimited
Monthly base$59 / mo (Studio)
Generations per month~450 included, then $0.13 each
Cost of 1,000 generations~$130 over plan
Cost of 10,000 generations~$1,300 over plan
Waiting roomShared queue at peak
Prompt + IP privacyProcessed on AXIS cloud GPU
Offline useRequires internet

Per-mesh cost on cloud plans is the published list price. Your actual ROI depends on volume — BYOGPU breaks even around 770 generations / mo and is pure savings beyond that. Heavy users save thousands per month.

What you get

Flat-rate unlimited — no per-mesh metering

Unlimited everything

Text→3D, image→3D across 8 asset kinds, parametric avatars, mesh repair, validate + export. No per-action metering. Burn through 10,000 generations a month if you want.

Stdlib-only scaffold

The downloadable worker is pure Python 3.11 stdlib — no requests, no numpy. Today it pairs and heartbeats; local dispatch to your own torch/diffusers is in preview.

Deterministic & signed

Same seed → same mesh. SHA-256 provenance chain. HMAC-signed manifests. The worker package itself is deterministic — same input, byte-identical ZIP.

Auto-pair to your account

One-time 15-minute pairing code. The worker registers, gets a long-lived token, and starts heartbeating. Revoke any worker from the console.

Multi-machine

Pair as many workers as you own — workstation, laptop, that crypto-mining rig you don't use anymore. All managed under one unlimited subscription; local execution arrives when the worker leaves preview.

Cancel anytime

No annual lock-in. No setup fee. Subscribe in November, ship a game in December, cancel in January. Your provenance manifests stay valid forever.

Step 3 · How it works

Four commands to pair your worker.

  1. Activate BYOGPU on your account Subscribe above. Your portal account flips to plan byogpu with unlimited generation rights.
  2. Download the worker package A 5 KB stdlib-only ZIP. Drop it anywhere. It only needs Python 3.11+.

    For local generation (in preview), you install torch, diffusers, and the model weights once — the same dependencies as any local diffusion setup.

  3. Generate a pairing code in the Console One-shot, expires in 15 minutes. POST /portal/api/byogpu/workers/pair returns the code and an exact install command.
  4. Run it python -m axis_foundry_worker pair --code <CODE> --label "Workstation", then python -m axis_foundry_worker run. The worker heartbeats every 30s and shows online in your console. Local job routing is in preview — generation runs on AXIS cloud today.

Step 4 · The download

axis-foundry-worker — stdlib-only scaffold

Filename
Version
Size
SHA-256
Determinismbyte-identical across rebuilds

The download is public so you can inspect it before subscribing. Pairing a worker requires an active subscription.

Step 5 · Questions creators ask

Honest answers

Is the worker really stdlib-only?

The scaffold is. It uses urllib for HTTP, subprocess for GPU detection, zipfile + json. Local generation (in preview) will dispatch to whatever diffusion stack you install (torch + diffusers + a text-to-3D / image-to-3D model) — we don't lock you to one model. Until then, your generations run on AXIS cloud.

What if my GPU is too small?

The hardware probe will flag you ineligible (under 8 GB VRAM or a known underpowered chip). You can still subscribe and run on a different machine, but we won't let an obviously underpowered worker pair — it would just frustrate you with timeouts.

Where does my data go?

Today, generation runs on AXIS cloud, so prompts and images are processed there. When the local worker leaves preview, prompts and images will stay on your machine and the portal will only see worker heartbeats (status + last_seen), job IDs, and the final asset manifest. The engine is also self-hostable and air-gapped-friendly if you need full data isolation now.

Can I cancel?

Yes. From Billing → Switch back to a free or paid token-pack plan. Your existing generations and manifests stay valid forever — the provenance chain doesn't depend on subscription state.

Does this work behind a corporate firewall?

The worker only needs outbound HTTPS to the AXIS API. No inbound ports. Standard corporate egress allows it.

What counts as a "generation"?

Anything that would normally consume tokens — text-to-3D, image-to-3D, parametric, mesh repair, validation+export. On BYOGPU, none of it is metered.

© 2026 X AXIS LLC — a Last Man Up Inc. company · Terms · Privacy · Refunds