Skip to content
Pricing

Try it before you exist to us.

Only Pro takes a card. The trial does not charge for seven days and cancels in one click.

Guestno account
$0
2 full sessions, then sign in
Two complete six-stage sessions
All 157 topics, all 17 concept pages
No email, no card, no profile
No practice lab, nothing saved between visits
Freesign in
$0
8 sessions a month
8 sessions a month, no card
Saved threads you can resume
5 practice-lab code reviews a month
Revision cards
Stage 6 grounded in your resume, not generic examples
Pro7-day trial
$9 / month
Unlimited sessions
Unlimited review sessions
Unlimited practice-lab code reviews
Everything in Free
New topics ship to Pro first
Request topics directly

Frequently asked

What counts as a session?

A session is a single 6-stage review run on one topic, started from your dashboard. Continuing or reloading an existing session does not consume a new session credit.

How does the free trial work?

You enter a card when starting your Pro trial. You will not be charged for 7 days. If you cancel before the trial ends, you pay nothing. After 7 days the subscription renews at $9/month until you cancel.

Can I cancel anytime?

Yes. You can cancel from your Stripe customer portal or by emailing hello@liminalml.com. After canceling, you keep Pro access until the end of your current billing period.

Do you offer a promo or student discount?

Occasionally. If you have a promotion code (from a partner site, launch promo, or referral), enter it on the Stripe checkout page. Students and open-source contributors can email hello@liminalml.com.

What happens to my data if I downgrade?

Your profile context, STAR stories, and session history are preserved indefinitely. You'll simply be capped at 8 sessions and 5 practice-lab reviews per month again starting the next billing cycle.

What payment methods are supported?

All major credit and debit cards, plus Apple Pay, Google Pay, and Link, via Stripe Checkout. Stripe never shares your card details with us.

Which model powers LiminalML? Can it be wrong?

LiminalML is built on Claude via the Anthropic API. Like any LLM it can be confidently wrong — sessions are structured so every derivation step is visible and checkable, and anything load-bearing should be verified against a primary source. The six-stage structure, pacing, and saved sessions around the model are what we build.

Is my resume / chat history private?

Your data is stored in our database with row-level security, so other users can never see it. Session content is sent to Anthropic's API to generate responses; per Anthropic's API terms it is not used to train models, and we never train on your data either. You can delete your account and data anytime. See our Privacy Policy for details.

Still have questions? Email us.