Kimi K2.5
Kimi K2.5 is a multimodal model developed by Moonshot AI that processes both text and image inputs. It is designed for complex tasks requiring visual coding capabilities and supports autonomous agent workflows.
Kimi K2.5 specs and pricing
- Provider: MoonshotAI
- Released: January 27, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text, images
- Output: text
- Price: $0.50 input / $2.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Kimi K2.5 is good at
- Analyzing and generating code based on visual inputs
- Managing complex, multi-step agentic workflows
- Processing large documents or datasets requiring reasoning
To-dos to try with Kimi K2.5
- Upload a screenshot of a website design and ask the model to generate the corresponding HTML and CSS code.
- Provide a long technical report and ask the model to extract key data points and summarize the findings.
- Assign the model a multi-step research task that requires it to use its tool-calling capabilities to gather information.
FAQ
- What kind of inputs can Kimi K2.5 process? The model is multimodal and can process both text and image files.
- What is the primary focus of this model? Kimi K2.5 specializes in visual coding tasks and operates using a self-directed agent swarm paradigm.
- How much does Kimi K2.5 cost? Kimi K2.5 costs $0.50 per million input tokens and $2.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.75 credits ($1 = 100 credits).
- What is the context window of Kimi K2.5? Kimi K2.5 can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Kimi K2.5 without coding? Yes. In todo.is you pick Kimi K2.5 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.