Introducing Kael

Kael is not one model. It is a system, which we call the Composite Intelligence System, or CIS: fine-tuned language models, small language models, retrieval and other specialist models working together behind a single API call. From the outside it behaves like any other chat model. You send a request and you get a response.

What happens in between is the point. Every answer is drafted, checked against what you asked, and refined before it reaches you. For code, that is where bugs and security vulnerabilities get caught, and where we aim to stop them being introduced at all. Kael is built for people who want accuracy more than speed, and it is strongest at coding, security, software engineering, agentic work and math.

There is nothing new to learn to use it. Kael accepts Chat Completions, the Responses API and the Anthropic Messages format. For OpenAI-style requests you change the base URL to https://api.quancis.space/v1, use the model name kael-beta, and keep the rest of your code.

The current beta takes text and images as input and returns text. The context window is 1 million tokens of input with up to 128,000 tokens of output, and the knowledge cutoff is July 2026. Kael is built for English today, and other languages have not been tested. It is a closed model, available through the API and our apps. PDFs, video and other file types are on the way, but they are not in the beta yet.

We have not published benchmark numbers, and we are not publishing ones we ran ourselves. Independent evaluations are in progress, and we plan to share the results on the Kael page once they are in. Until then, the fastest way to judge Kael is to point your existing SDK at it and run your hardest prompts.

Kael is also the system behind Quan Harness, our coding agent, and Quan Chat, our assistant. Same intelligence, three ways in.