Pay for what you use. Nothing else.
Your company pays per request, based on what the assistant uses. No subscription, no per-seat fee, no commitment.
A token is about three quarters of a word. Code already read in a session is cached. Cache prices per 1M tokens: Cache read $0.10 · Cache write $2.50 · Cache write (1 hour) $4.00.
$1.00 of free credit on every new project, enough to try your first requests before adding a card.
What a request costs
Change some text or a color
≈ $0.04
Add a field to a form
≈ $0.09
Create a new page
≈ $0.23
Estimates: the cost depends on the size of your code and of the change.
Questions you are about to ask
- Is there a free plan?
- No, but every new project starts with $1.00 of credit, enough to try your first requests before adding a card.
- What do I pay for?
- The tokens the assistant uses to read your code and write changes, at the prices listed on the pricing page. A token is a small chunk of text, roughly three quarters of a word: the more code the assistant reads and writes, the more tokens a request uses.
- Who pays: me or my collaborators?
- Whoever has billing access to the project. It has its own balance, topped up by card, and the usage of every member is deducted from it. Usually the company pays for its team. An agency can also give billing access to a client, who then adds their own card: nobody has a subscription.
- What happens when the balance runs out?
- The assistant stops until someone tops the project up. Turn on automatic top-up and the saved card recharges it when it gets low.
- Can I set spending limits?
- Yes. Set a monthly limit for the project and one for each member: the assistant stops when it is reached.
Try it on your own app.
Spend your first $1.00 on real changes.