Kimi K2 Thinking
Kimi K2 Thinking is an advanced reasoning model developed by Moonshot AI. It utilizes a large-scale Mixture-of-Experts architecture designed to handle complex, long-horizon reasoning tasks and tool-based interactions.
Kimi K2 Thinking specs and pricing
- Provider: MoonshotAI
- Released: November 6, 2025
- Context window: 262K tokens
- Max output: 98K tokens
- Input: text
- Output: text
- Price: $0.60 input / $2.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Kimi K2 Thinking is good at
- Complex multi-step analytical tasks
- Projects requiring deep logical reasoning
- Automated workflows involving external tools
To-dos to try with Kimi K2 Thinking
- Analyze a complex technical problem and break it down into a step-by-step resolution plan.
- Use tool calling to retrieve current data and synthesize it into a structured report.
- Evaluate a logical argument for potential fallacies and provide a detailed critique.
FAQ
- What is the primary focus of the Kimi K2 Thinking model? This model is specifically engineered for agentic, long-horizon reasoning and complex problem-solving.
- Does the model support the use of external tools? Yes, Kimi K2 Thinking is equipped with tool-calling capabilities to perform tasks beyond simple text generation.
- How much does Kimi K2 Thinking cost? Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.03 credits ($1 = 100 credits).
- What is the context window of Kimi K2 Thinking? Kimi K2 Thinking can read up to 262K tokens at once and write up to 98K tokens in one reply.
- Can I use Kimi K2 Thinking without coding? Yes. In todo.is you pick Kimi K2 Thinking as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.