KT: Mi:dm K 3.0 Pro
kt/midm-k-3.0-pro
Try Mi:dm K 3.0 Pro for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "kt/midm-k-3.0-pro"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "kt/midm-k-3.0-pro"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Mi:dm K 3.0 Pro is a reasoning language model from KT, the South Korean telecom company, and the newest model in its Mi:dm K family. It is a Mixture-of-Experts model with 120B total parameters and 12B active per token, using a hybrid of Mamba, MoE, and attention layers.
KT says it tuned the model for Korean-language data and enterprise work, and reports that it generates Korean text about 30% faster than NVIDIA's Nemotron 3 Super. KT has not published benchmark scores for it.
The model takes text in and returns text, with a context window of about 262K tokens and adjustable reasoning depth. It fits developers building Korean-language assistants, document summarization and Q&A, or long-context analysis who want a low per-token price.
Context Window 262K
tokens
Max Output 236K
tokens
Input Cost $0.2
per million tokens
Output Cost $0.8
per million tokens
Input text
modalities
Tool Use No
Release Date Nov 5, 2026
Try Mi:dm K 3.0 Pro for free
Try Mi:dm K 3.0 Pro instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Mi:dm K 3.0 Pro by KT through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Mi:dm K 3.0 Pro is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Mi:dm K 3.0 Pro is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.2 |
| Output | $0.8 |
Mi:dm K 3.0 Pro was created by KT and released on Nov 5, 2026.
Mi:dm K 3.0 Pro supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Mi:dm K 3.0 Pro can generate up to 236K tokens in a single response.
Mi:dm K 3.0 Pro accepts the following input types: text. It produces: text.
No, Mi:dm K 3.0 Pro does not currently support tool use (function calling).
Yes — the Mi:dm K 3.0 Pro API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Mi:dm K 3.0 Pro to your app for free
Developers can integrate Mi:dm K 3.0 Pro for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.