Install

Kimi K3 as a coding agent in your terminal

Kimi K3 by Moonshot AI, one of 250+ models you can use in Darce, the open source AI coding agent you can undo.

ModelKimi K3
VendorMoonshot AI
Model idmoonshotai/kimi-k3
Context window1.05M tokens
Price per 1M tokens$0.64 input · $13.50 output (OpenRouter)
Can dotool calling · reads images · reasoning
CategoryPopular

Strengths

Moonshot AI's Kimi K3 with a 1M token context. Known for long, agentic tool-using sessions.

OpenRouter's description:

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Use Kimi K3 as a coding agent in your terminal

Start Darce in your project with Kimi K3:

npm install -g darce-cli
darce --model moonshotai/kimi-k3

Already in a session? Type /model moonshotai/kimi-k3, or open the picker with Ctrl+P. Darce then reads your code, edits files and runs commands with Kimi K3; risky commands ask first, and /undo reverses any change, including what shell commands did. No account yet? npx darce-cli lets you try it free. Which plan includes which models is on the pricing page.

Make it your default or a gear

In ~/.darcerc, set it as the starting model or add it to the gears you move between with Shift+↑ / Shift+↓ (see configuration):

{
  "router": { "default": "moonshotai/kimi-k3" },
  "gears": ["qwen/qwen3-coder", "moonshotai/kimi-k3"]
}

Compare it on your own code

Benchmarks rarely match your repository. Race Kimi K3 against two other models on a real task and keep the best diff:

/derby --models moonshotai/kimi-k3,moonshotai/kimi-k2.7-code,moonshotai/kimi-k2.6 fix the failing test

Read more about /derby and /swarm.

Related models

  • Kimi K2.7 Code (Moonshot AI): 262k tokens, $0.67 / $3.35 per 1M tokens
  • Kimi K2.6 (Moonshot AI): 262k tokens, $0.47 / $2.45 per 1M tokens
  • Kimi K2 Thinking (Moonshot AI): 262k tokens, $0.60 / $2.50 per 1M tokens
  • Claude Sonnet 5.5 (Anthropic): 1M tokens, $2.00 / $10.00 per 1M tokens
  • Claude Sonnet 4.5 (Anthropic): 1M tokens, $3.00 / $15.00 per 1M tokens
  • GPT-6.1 Sol (OpenAI): 1.05M tokens, $2.00 / $10.00 per 1M tokens
  • GPT-5.6 Sol (OpenAI): 1.05M tokens, $2.00 / $10.00 per 1M tokens

All models · Getting started · Claude Code alternative

Model data from OpenRouter, refreshed daily. Prices are OpenRouter's list rates and show relative cost; your Darce allowance is used in proportion to them.