Kimi K2 Thinking as a coding agent in your terminal
Kimi K2 Thinking by Moonshot AI, one of 250+ models you can use in Darce, the open source AI coding agent you can undo.
| Model | Kimi K2 Thinking |
|---|---|
| Vendor | Moonshot AI |
| Model id | moonshotai/kimi-k2-thinking |
| Context window | 262k tokens |
| Price per 1M tokens | $0.60 input · $2.50 output (OpenRouter) |
| Can do | tool calling · reasoning |
| Category | Reasoning |
Strengths
Kimi K2 with extended thinking for harder reasoning steps.
OpenRouter's description:
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Use Kimi K2 Thinking as a coding agent in your terminal
Start Darce in your project with Kimi K2 Thinking:
npm install -g darce-cli
darce --model moonshotai/kimi-k2-thinkingAlready in a session? Type /model moonshotai/kimi-k2-thinking, or open the picker with Ctrl+P. Darce then reads your code, edits files and runs commands with Kimi K2 Thinking; 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-k2-thinking" },
"gears": ["qwen/qwen3-coder", "moonshotai/kimi-k2-thinking"]
}Compare it on your own code
Benchmarks rarely match your repository. Race Kimi K2 Thinking against two other models on a real task and keep the best diff:
/derby --models moonshotai/kimi-k2-thinking,moonshotai/kimi-k3,moonshotai/kimi-k2.7-code fix the failing testRead more about /derby and /swarm.
Related models
- Kimi K3 (Moonshot AI): 1.05M tokens, $0.64 / $13.50 per 1M tokens
- 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
- Claude Opus 5.5 (Anthropic): 1M tokens, $4.00 / $20.00 per 1M tokens
- Claude Fable 5.1 (Anthropic): 1M tokens, $10.00 / $50.00 per 1M tokens
- Claude Opus 5 (Anthropic): 1M tokens, $5.00 / $25.00 per 1M tokens
- GPT-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.