Loopcut

Pricing

Free with your own model. Simple plans for ours.

Loopcut is open source and works with any OpenAI-compatible endpoint at no cost. Hosted plans add Fast and Pro modes with nothing to set up, metered by model time you can see.

Bring your own key, or run locally

Free, forever. No account.

Paste a key from your provider, or the address of a model on your own machine. The key never leaves your computer, requests go straight to the endpoint you chose, and nothing passes through us.

  • Any OpenAI-compatible API, including local servers
  • Every feature of the agent, no limits from us
  • Pay your provider directly, or nothing at all
  • Set it up in Preferences › Add-ons › Loopcut
  • Download Loopcut

Hosted plans

Fast and Pro, no keys, no setup.

Sign in from the app and start working. Pick the tier that matches how much of your week Loopcut is going to take off your plate.

Free

See what Loopcut does on a real scene.

$0/ month

  • Fast mode
  • Enough to try it on a real scene every week
  • Sign in from the app, no card needed
  • Every feature of the agent, no watermarks or limits
  • Usage shown in the app and your account

Pro

Most popular

For artists who use Loopcut most days.

$20/ month

  • Fast and Pro modes
  • 13× the allowance of Free
  • Pro thinks longer on hard scenes and multi-step jobs
  • Sized for daily use: cleanup, rigs, look dev, exports
  • Every device on your account, cancel any time

Max

For production work, heavy scenes and teams.

$60/ month

  • Everything in Pro
  • 3× the allowance of Pro
  • Room for long sessions and very heavy scenes
  • Built for batch work: variants, turntables, renders
  • First to get new models as we add them

Allowances are model time in a 5-hour session and a 7-day window. Quick Fast edits use little of it; heavy scenes, viewport captures and long Pro turns use more. The app always shows what is left.

Questions

Straight answers.

Anything else? Open an issue and we will answer in public.

What is an allowance?
Each plan gives you an amount of model time in two windows: a 5-hour session and a 7-day week. Model time is the work the model does for you, so a long Pro turn on a heavy scene uses more than a quick Fast rename. The app shows how much of each window is left.
What counts as a turn?
One message to Loopcut with a few tool steps: reading the scene, writing and running the code, checking the viewport. Heavy scenes and viewport captures send more context, so they cost more.
What happens when I run out?
Requests pause until the window resets, and the app tells you when that is. Nothing is deleted and you are never charged extra. If you hit the limit often, the next plan up is the fix.
Do I need a hosted plan at all?
No. Paste a key from any OpenAI-compatible provider, or point Loopcut at a local model, and it is free with no account. Hosted plans exist for people who want zero setup, and they fund the project.
What do you keep from my sessions?
With your own key or a local model, nothing reaches us. On hosted plans the gateway relays your request to the model provider and records token counts, cost and timing for metering. It does not store your prompts or scene data. The provider's own terms cover what they receive.
Can I cancel or change plans?
Any time, from the account page. Downgrades and cancellations take effect at the end of the billing period; upgrades apply straight away.

Not sure yet? Start free.

Download Loopcut, sign in from the app, and see what the busywork looks like when it runs itself.