The Orchestrator › Models › KT
KT: Mi:dm K 3.0 Pro
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.
Specifications
| Provider | KT |
| Model ID | kt/midm-k-3.0-pro |
| Context window | 262K tokens (261,795) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter |
| Released | 2026-11-05 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | kt/midm-k-3.0-pro | $0.2 | $0.8 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.2 | $0.8 | 262K |
Capabilities
Agentic tool useStructured outputs256K+ context windowControllable reasoning
Supported parameters
frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p