Two Models. One API.
Kael comes in two models: Kael Beta for most work, and Kael Pro Beta for the hardest problems. You call one endpoint, in the request format you already send.
Quancis builds Kael, in two models, and the products people actually use it through.
Kael comes in two models: Kael Beta for most work, and Kael Pro Beta for the hardest problems. You call one endpoint, in the request format you already send.
Point Harness at a codebase and it reads, plans, edits, and checks its own work before handing anything back. It runs in a real project environment, in whatever stack you already use.
The same Kael as the API and Harness, in a conversation. Built for accuracy over speed, so it thinks before it answers.
Kael is in beta, in two models: Kael Beta and Kael Pro Beta. It is built for accuracy over speed, and it is strongest at coding, security, software engineering, agentic work and math. These are the facts a developer asks for first.
Quancis comes from quán, the Chinese word for the whole. Not a fragment, and not a committee of parts pretending to be one thing. It's how a company works: hundreds of people and tools, and the world sees one name on the door.
Kael is that idea applied to answers: one Kael, in two models, built to be right. The API, Harness, and Chat are three ways of reaching it.
Kael thinks before it answers, and takes longer than most models on purpose.
Kael Beta for most work. Kael Pro Beta, the most thorough, for the hardest problems.
Text and images in, English only, and no benchmark numbers until independent results exist.