UltraGPT
KKt
Every Kt model UltraGPT can reach, kept in sync with the live catalog — pricing, context window and capabilities for each one.
1 model from Kt Up to 261.8K tokens of context
1
Models tracked
1
Providers
1
Reasoning models
0
See images (vision)
262K
Largest context window
0
Free to run
All Kt models.
Search and filter this provider's lineup — pricing per million tokens, context window, modalities, reasoning effort and independent benchmark scores where available.
1 of 1 models
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.
ReasoningStreamingJSON mode
Context window261.8K tok
Max output235.6K tok
ReleasedNov 5, 2026
Knowledge cutoff—
TextText
Input$0.2 / 1M tok
Output$0.8 / 1M tok
Cache read$0.04 / 1M tok