Mi:dm K 3.0 Pro
Mi:dm K 3.0 Pro is a large language model made by KT, added to the catalog on 5 Nov 2026. It has a context window of 261,795 tokens and costs $0.20 per 1M input tokens and $0.80 per 1M output tokens. It accepts text and produces text. Typical uses: reasoning over long text, working with multiple documents and generating structured text.
Price checked ยท source: OpenRouter
What Mi:dm K 3.0 Pro is
KT Mi:dm K 3.0 Pro is a text-in, text-out reasoning model from KT. Its catalog description identifies it as a Mixture-of-Experts model with 120B total parameters and 12B active parameters. It uses a hybrid architecture combining Mamba, MoE and attention layers. The model accepts text and produces text. Its listed capabilities include reasoning, tool support, structured outputs and response-format support; the facts do not specify particular tools or formats.
The model has a context length of 261,795 tokens and a maximum output length of 235,615 tokens. These limits give it room to process long text inputs and return lengthy text responses. That context may suit work involving extended conversations, long reports or multiple text documents supplied together. Its reasoning support makes it relevant to text tasks that call for analysis, while structured-output and response-format support may fit applications that require responses in a defined form. Tool support is also listed, so it can be considered for text workflows that connect model responses with tools. The catalog does not identify specific tools, output schemas or response formats, so those details should be checked for the intended setup. The listed facts do not name particular subject areas, languages or task-level performance, and they do not establish how well the model handles any specific task. Its documented profile is centered on text, long context, reasoning and format-aware response features.
Key features
- Accepts text and produces text
- Context length of 261,795 tokens
- Maximum output length of 235,615 tokens
- Supports reasoning and tools
- Supports structured outputs and response formats
Typical uses
- Reasoning over long text
- Working with multiple documents
- Generating structured text
- Tool-supported text workflows
Mi:dm K 3.0 Pro pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.20 |
| Output, per 1M tokens | $0.80 |
| Cached input read, per 1M tokens | $0.04 |
No price change since it was added on 5 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0003 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0056 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0076 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.031 |
Mi:dm K 3.0 Pro specifications
| Model id | kt/midm-k-3.0-pro |
|---|---|
| Version | midm-k-3.0-pro |
| Context window | 261,795 tokensAbout 196,346 English words |
| Max output | 235,615 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 5 Nov 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Mi:dm K 3.0 Pro yet.