KT: Mi:dm K 3.0 Pro
kt/midm-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.
- Context window
- 261,795
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Inference prices
- Published price : $0.04 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.20 / input_tokens_per_million · openRouter ↗
- Published price : $0.80 / output_tokens_per_million · openRouter ↗