Kimi K2.7 Code
Kimi K2.7 Code is a coding-focused model developed by MoonshotAI designed to handle complex programming tasks. It features a large context window and native multimodal capabilities, allowing it to process both text and images for end-to-end development workflows.
Kimi K2.7 Code specs and pricing
- Provider: MoonshotAI
- Released: June 12, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text, images
- Output: text
- Price: $0.56 input / $3.10 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Kimi K2.7 Code is good at
- Analyzing large codebases for bugs or refactoring
- Building applications based on visual design mockups
- Managing complex programming projects with extensive documentation
To-dos to try with Kimi K2.7 Code
- Upload a series of screenshots of a UI design and generate the corresponding frontend code
- Provide a large repository of source files and ask the model to identify architectural bottlenecks
- Paste a long technical specification and ask the model to draft a complete implementation plan with code snippets
FAQ
- What is the primary focus of the Kimi K2.7 Code model? This model is specifically engineered for end-to-end programming tasks and software development workflows.
- Can this model process images? Yes, Kimi K2.7 Code is a native multimodal model that accepts both text and image inputs.
- How much does Kimi K2.7 Code cost? Kimi K2.7 Code costs $0.56 per million input tokens and $3.10 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2 credits ($1 = 100 credits).
- What is the context window of Kimi K2.7 Code? Kimi K2.7 Code can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Kimi K2.7 Code without coding? Yes. In todo.is you pick Kimi K2.7 Code 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.