Platform
About Kael
When to choose Kael, what to expect from it, and how requests are screened.
What to expect
- It is slower than a single call, on purpose. Kael favors correctness over speed, so the first answer token arrives later than with a typical chat model. A stream sends short thinking titles in the meantime. For the quickest replies, use the default thinking level,
low. - You are billed once. Your input and the final answer, nothing else. See Pricing and billing.
- Output is not deterministic. Sampling settings are ignored, so the same request can return different answers.
What Kael is
Kael is a Quancis product, offered through one API. Quancis does not publish how it is built or which components it uses, and Kael will not say. Kael's own weights are not available to download.
Safety screening
Requests and answers can be screened against the acceptable-use section of the Terms of Service. A flagged request can be held for review and the account paused while it is checked. See Data and privacy.
When to use Kael
| Reach for Kael when | Look elsewhere when |
|---|---|
| Correctness matters more than speed. | You need the fastest possible response. |
| The work is code review, debugging, refactoring, or security review. | The work is writing first: fiction or marketing copy. |
| An agent will act on the output. | You need PDFs, video, or other file types today. |
| You already call a chat API and want to change as little as possible. | You need a language other than English. |
| Your work is in English. | You need downloadable or self-hosted weights. |