precios
Sin contador desde 19 €. Y sin asterisco.
Unlimited here means unlimited: the engine runs in your browser and serving it costs us nothing, so there is no «fair use policy» waiting for you in the small print. Start free with 25 optimizations a month, no card.
Free
0 € /siempre
To see if it helps.
Anyone. No card, no expiry.
- 25 optimizations a month
- All three levels, nothing held back
- Word-by-word diff and breakdown
- Code, URLs and variables protected
- 7-day history
- 3 custom dictionary rules
Basic
7,50 € /mes
90 € al año · ahorras 18 €
0,25 € al día
For everyday use.
Anyone already using it daily who does not need to wire it into anything.
500 a month is about 25 per working day. If you work with prompts, they run out.
- 500 optimizations a month
- 90-day history
- 25 custom dictionary rules
- Export your history to CSV
- Cumulative savings metrics
- Everything in Free
Pro
15,83 € /mes
190 € al año · ahorras 38 €
0,53 € al día
No counter, plus the API.
Anyone working with prompts who wants to automate it.
Ten euros more than Basic and the counter disappears, the API opens up and your history stops expiring.
- Unlimited optimizations
- API to wire it into your own code
- History kept forever
- Unlimited custom dictionary
- Email support
- Everything in Basic
Team
8,33 € /asiento/mes
100 € al año por asiento · ahorras 20 € por asiento
0,28 € al día por persona
One standard for everyone.
A team or agency with several live projects.
Each seat costs a little over half a Pro licence. From three people up.
- From 3 seats, add as many as you need
- Shared dictionaries
- Role-based access control
- Per-project metrics
- A single invoice
- Everything in Pro
Prices exclude VAT, which is added at checkout based on your country. Cancel whenever you want from your account and you keep access until the end of the period you paid for.
Why we can take the counter away
Optimizing you costs us zero. The engine is rules and dictionaries running in your browser, not calls to a model. Try it in airplane mode: it keeps working.
That is why there is no asterisk. Anyone with an LLM behind it pays for your every use and is forced to meter you, even if they write «unlimited» and qualify it in the small print. We do not have that problem.
You pay us for what does cost: storing your history, your rules and your team's work. That is real servers. Optimizing is not.
Enterprise
Self-hosted engine inside your own infrastructure, SSO access, a service level agreement, a data processing agreement and unlimited seats. For when the prompts cannot leave your network.
Frequently asked questions
Tap any of them to open the answer.
How many optimizations does each plan include?
The free plan saves 25 a month and Basic saves 500; Pro and Team have no counter. The limit counts the ones saved to your history and resets on the 1st of each month. If you hit it, the optimizer keeps working and you can copy the result: what stops is the saving.
So what am I paying for?
Four things: losing the monthly counter, an unlimited custom dictionary, history kept forever instead of 7 days, and API access to call the engine from your own code. On the Team plan, dictionaries are shared across the whole team and there is role-based access control.
Can I cancel whenever I want?
Yes, from your account and without writing to anyone. You keep access until the end of the period you already paid for, and when it ends the account returns to the free plan: your rules and your history are not deleted, the free plan limits simply apply again.
I use the free tier of ChatGPT. Is this any use to me?
Yes, and this is where it shows most. You do not pay per token, but you spend them all the same: every pleasantry eats context window and brings forward the point where the conversation gets cut or the model starts forgetting the beginning. Halving the prompt means twice as much fits before you get there.
Does optimizing use up tokens from my account?
No. The engine is rules and dictionaries running in your browser, with no calls to any model. The only thing that leaves your device is the exact token count, and only if you ask for it.
Can it change what my prompt means?
That is the line the engine will not cross. A substitution only ships if the prompt still asks for exactly the same thing without it. Anything that would change the meaning is flagged as a suggestion, never applied automatically, and the word-by-word diff shows you every single cut.
What happens to code inside my prompts?
It is protected. Code blocks, inline code, URLs and template variables are lifted out before the rules run and put back afterwards, untouched. A rule that reformatted your code would break it silently, which is worse than saving nothing.
Do you store my prompts?
Only if you are signed in, and only a 120-character preview so you can recognise the entry in your history. Without an account nothing leaves your browser: the history lives in your device's local storage.