UltraGPT
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.
Intelligence overview
261.8K tok
Context window
235.6K tok
Max output
What KT: Mi:dm K 3.0 Pro can do.
Reasoning
Extended reasoning
Works through problems step by step before answering, trading latency for accuracy on harder tasks.
Development
Structured output
Returns responses constrained to a JSON schema, ready to parse without cleanup.
Streaming
Streams tokens as they're generated instead of waiting on the full response.
Pay for what you use.
Every model in UltraGPT runs behind one flat subscription — this is the underlying per-token cost the catalog tracks.
$0.2 / 1M tok
$0.8 / 1M tok
Built for serious work.
Build
Generate and refactor code, with the ability to return structured, parseable output.
Think
Works through multi-step problems with extended reasoning before it answers.
Research
Holds up to 261.8K tokens of source material in context without losing the thread.
Ask KT: Mi:dm K 3.0 Pro anything.
A preview of the real UltraGPT composer — the model you see here is the model you get.
Continues in the UltraGPT app — one login, every model.
How KT: Mi:dm K 3.0 Pro stacks up.
The closest models in the catalog by provider, capability and score — real entries, pulled from the same directory.
Technical details.
Specification
- Context window
- 261.8K tokens
- Max output
- 235.6K tokens
- Input modalities
- Text
- Output modalities
- Text
- Release date
- Nov 5, 2026
- Streaming
- Supported
- Tool calling
- Not supported
- JSON mode
- Supported
More from Kt, and everything else.
This model is one entry in the full UltraGPT catalog — browse the rest, compare pricing and context windows, or filter by capability.