Kimi K2.6
Kimi K2.6 is a multimodal model developed by Moonshot AI designed for complex coding tasks and multi-agent orchestration. It supports both text and image inputs and features advanced reasoning and tool-calling capabilities to assist with end-to-end development in languages like Python, Rust, and Go.
Kimi K2.6 specs and pricing
- Provider: MoonshotAI
- Released: April 20, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text, images
- Output: text
- Price: $0.65 input / $3.41 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Kimi K2.6 is good at
- Complex end-to-end coding projects
- Multi-agent system orchestration
- Coding-driven UI/UX generation
To-dos to try with Kimi K2.6
- Analyze this codebase and suggest a refactor for the Python module
- Review these UI design screenshots and generate the corresponding code
- Orchestrate a multi-step workflow to automate data processing in Rust
FAQ
- What types of input can Kimi K2.6 process? The model accepts both text and image inputs.
- What are the primary capabilities of Kimi K2.6? It is designed for long-horizon coding, UI/UX generation, and multi-agent orchestration with built-in reasoning and tool-calling support.
- How much does Kimi K2.6 cost? Kimi K2.6 costs $0.65 per million input tokens and $3.41 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.3 credits ($1 = 100 credits).
- What is the context window of Kimi K2.6? Kimi K2.6 can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Kimi K2.6 without coding? Yes. In todo.is you pick Kimi K2.6 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.