Moonshot AI's frontier coding model. Use kimi-k3 in AdaL for deep reasoning with 1M context and maximum effort.
Get StartedRun /model and pick Kimi K3 · $3/M input · $15/M output
Key capabilities and pricing
Recommended in AdaL for deep reasoning and complex coding tasks.
Always reasons at max effort — the deepest thinking available.
Process images alongside code.
1M token budget for large projects.
Extended chain-of-thought for the hardest problems.
Premium pricing for frontier capability.
Available in AdaL CLI and Desktop through the model selector
Use the coding environment where AdaL already understands your repo, tools, and task context.
Open the model selector and choose your model from the list.
Ask AdaL to inspect, plan, edit, test, and review with your chosen model powering the agent loop.
Key details about Kimi K3
"Kimi K3 is our frontier model for deep reasoning and complex coding."
Moonshot AI
"Use K3 for the hardest problems — it always reasons at maximum effort."
AdaL
"1M token budget for processing entire repositories."
Context
"50% off launch week in AdaL."
Promotion
Open AdaL CLI or Desktop, run /model, and choose Kimi K3.
Get Started with AdaL