Kimi K2 0905
Kimi K2 0905 is a large-scale Mixture-of-Experts language model developed by Moonshot AI. Released in September 2025, it supports tool calling and offers a large context window for processing extensive text inputs.
Kimi K2 0905 specs and pricing
- Provider: MoonshotAI
- Released: September 4, 2025
- Context window: 262K tokens
- Max output: 98K tokens
- Input: text
- Output: text
- Price: $0.60 input / $2.50 output per 1M tokens
- Tool calling: yes
What Kimi K2 0905 is good at
- Analyzing long-form text documents
- Complex tasks requiring external tool integration
- Processing large-scale information datasets
To-dos to try with Kimi K2 0905
- Summarize the key arguments from a 200,000-token research report.
- Use the tool-calling capability to search for and synthesize data from multiple web sources.
- Draft a comprehensive project proposal based on a series of long meeting transcripts.
FAQ
- Who developed the Kimi K2 0905 model? The model was developed by Moonshot AI.
- Can this model interact with external tools? Yes, Kimi K2 0905 supports tool calling to assist with complex tasks.
- How much does Kimi K2 0905 cost? Kimi K2 0905 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 0905? Kimi K2 0905 can read up to 262K tokens at once and write up to 98K tokens in one reply.
- Can I use Kimi K2 0905 without coding? Yes. In todo.is you pick Kimi K2 0905 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.