Mi:dm K 3.0 Pro
General purposeKt · Released November 2026
Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
Facts and pricing
- Provider
- Kt
- Context window
- 262K tokens
- Input price
- 2.4 credits / 1M tokens ($0.20 raw)
- Output price
- 9.6 credits / 1M tokens ($0.80 raw)
- Vision (image input)
- No
- Tool calling
- No
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Mi:dm K 3.0 Pro now
What Mi:dm K 3.0 Pro is best for
- Balanced everyday work: writing, questions, brainstorming and summarization
- Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
Model comparisons
- Claude Fable 5.2 vs Claude Fable 5.1
- Claude Opus 5.5 vs Claude Fable 5.2
- GPT-6 Astra vs Claude Fable 5.2
- Claude Opus 5.5 vs Claude Opus 5
Frequently asked questions
- What is Mi:dm K 3.0 Pro?
- Mi:dm K 3.0 Pro is an AI model by Kt. Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
- How much does Mi:dm K 3.0 Pro cost on Zeplik?
- Input tokens cost 2.4 credits per million and output tokens 9.6 credits per million (1 credit = $0.10; the raw provider rates are $0.20 and $0.80 per million). New accounts start with free credits.
- How long can a conversation with Mi:dm K 3.0 Pro be?
- Mi:dm K 3.0 Pro has a 262K-token context window (261,795 tokens), which covers the conversation plus any documents you attach.
- Does Mi:dm K 3.0 Pro support images and tools?
- Mi:dm K 3.0 Pro is text-only and does not support tool calling.
Related models
Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE).
DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from [Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation.
Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following [Pixtral Large 2411](https://openrouter.ai/mistralai/pixtral-large-2411).
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.
GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.
GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.
More you can do with Mi:dm K 3.0 Pro
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Mi:dm K 3.0 Pro or any model you pick.
- 1582 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.