Moonshot AI · Kimi K3
Kimi K3
Frontier intelligence, best-in-class frontend.
What it is
Kimi K3 is a natively multimodal 2.8-trillion-parameter model with a one-million-token context, built for long-horizon coding, knowledge work and deep reasoning.
Its reputation is front-end taste: layout, motion and detail that read as designed rather than assembled. For Skills that ship a page, that is the difference between a template and a piece of work.
Profiles describe the model, not a guarantee: the Skill folder is what makes the work repeatable, and the agent's settings decide what the model can reach.
What it's best at
The work this engine is built for, and where it earns its place in a run.
Front-end craft
Interfaces with a sense of type, spacing and motion, not just working markup.
Long-horizon coding
Carries a build across many files and many steps without flattening the design.
Multimodal input
Reads screenshots and references alongside the brief.
Deep reasoning
Researches and plans before it writes, which shows on open-ended briefs.
A good first run
Three web Skills to try on Kimi K3 — each one a folder of instructions the model can pick up straight away.
Other models
The rest of the engine room.
Anthropic · Claude 5.5
Opus 5.5
Anthropic's newest frontier model, built to carry long, multi-step work from one prompt to a finished result.
- Context
- 1M tokens
- Best at
- Agentic coding
OpenAI · GPT-6
GPT-6 Astra
OpenAI's frontier model for end-to-end agentic work, reasoning across a task rather than a single turn.
- Context
- ≈1M tokens
- Best at
- End-to-end work
Anthropic · Claude Fable 5.1
Fable 5.1
Anthropic's top model for demanding reasoning and long-horizon agentic work, with adaptive thinking.
- Context
- 1M tokens
- Best at
- Demanding reasoning
Ready to extend your agent?
Connect once, then install any Skill from our studio straight from your agent.