kt
KT: Mi:dm K 3.0 Pro
kt/midm-k-3.0-pro
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
kt/midm-k-3.0-pro is a text-to-text model listed on OpenRouter under the name KT: Mi:dm K 3.0 Pro. According to the catalog, it is a Mixture-of-Experts reasoning model from KT with 120B total and 12B active parameters, built on a hybrid architecture combining Mamba, MoE and attention layers. The listing reports a context length of 261,795 tokens and support for tool calling, structured outputs and optional reasoning controls. Evidence here is catalog-only, so real-world performance remains unverified.[1]
Strengths
- Hybrid Mamba, Mixture-of-Experts and attention design with 120B total and 12B active parameters, as described in the OpenRouter catalog.[1]
- Large reported context window of 261,795 tokens, suitable in principle for long-document inputs.[1]
- Catalog lists support for tools, structured outputs, reasoning parameters and common sampling controls such as temperature and top-p.[1]
Limitations
- Only OpenRouter catalog data is available in this source pack; no independent model card, benchmark results or usage reports were supplied, so capabilities are source-reported rather than measured.[1]
- Key fields such as knowledge cutoff and licensing are absent from the catalog entry, and actual quality should be validated on the intended workload before adoption.[1]
Where to use it
- Potentially suitable for long-context text processing tasks such as document analysis, given the large reported context window; verify with your own data.[1]
- A candidate for tool-using or structured-output workflows, since the catalog lists tools and structured_outputs among supported parameters.[1]
- Worth evaluating for reasoning-oriented applications where an optional reasoning mode is desired, as the catalog lists it as available but not mandatory.[1]
Sources
- [1] OpenRouter catalog · KT: Mi:dm K 3.0 ProSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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
- Model ID
- kt/midm-k-3.0-pro
- Creator
- kt
- Added to OpenRouter
- 05.11.2026
- Context length
- 261,795
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.200 / out $0.800
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| KT | 261,795 | $0.200 | $0.800 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.