kt
KT: Mi:dm K 3.0 Pro
Quality Score
89/100
price + capability + benchmarks
Input Price
$0.20
per 1M tokens · checked 2026-11-12
Output Price
$0.80
per 1M tokens · checked 2026-11-12
Context Window
261,795
tokens
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.
- Model ID
- kt/midm-k-3.0-pro
- Vendor
- kt
- Released
- November 2026
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 235,615 tokens
- Tool Calling
- not supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.20/M input and $0.80/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.14 |
| A month of a busy support chatbot | 5M in / 2M out | $2.60 |
Quick answers
- How much does KT: Mi:dm K 3.0 Pro cost?
- $0.20 per million input tokens and $0.80 per million output tokens.
- What is KT: Mi:dm K 3.0 Pro's context window?
- 261,795 tokens, roughly 392 pages of text in a single request.
- Does KT: Mi:dm K 3.0 Pro support tool calling?
- It supports structured output, a reasoning mode.
- Can KT: Mi:dm K 3.0 Pro process images?
- No, it is text-only on the input side.