Mi:dm K 3.0 Pro
Mi:dm K 3.0 Pro is a reasoning model developed by KT that utilizes a hybrid architecture combining Mamba, Mixture-of-Experts, and attention layers. It is designed to handle complex text-based tasks with a large context window and a focus on logical processing.
Mi:dm K 3.0 Pro specs and pricing
- Provider: KT
- Released: November 5, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text
- Output: text
- Price: $0.20 input / $0.80 output per 1M tokens
- Reasoning: yes
What Mi:dm K 3.0 Pro is good at
- Complex logical reasoning tasks
- Processing long-form text documents
- Applications requiring high-capacity text analysis
To-dos to try with Mi:dm K 3.0 Pro
- Analyze a long technical report and explain the logical inconsistencies in the findings.
- Draft a structured argument for a research paper based on a provided set of premises.
- Break down a complex multi-step problem into a logical sequence of operations.
FAQ
- What is the underlying architecture of Mi:dm K 3.0 Pro? It is a Mixture-of-Experts model that uses a hybrid architecture incorporating Mamba, MoE, and attention layers.
- Can this model process images or other media? No, Mi:dm K 3.0 Pro is designed specifically for text input and text output.
- How much does Mi:dm K 3.0 Pro cost? Mi:dm K 3.0 Pro costs $0.20 per million input tokens and $0.80 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.67 credits ($1 = 100 credits).
- What is the context window of Mi:dm K 3.0 Pro? Mi:dm K 3.0 Pro can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Mi:dm K 3.0 Pro without coding? Yes. In todo.is you pick Mi:dm K 3.0 Pro 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.