<- All Models

KT: Mi:dm K 3.0 Pro

NEW

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.

262K context·$0.20 in·$0.80 out·Nov 2026 release·Reasoning, Tools / functions, Web search

Available on

Providers

Where KT: Mi:dm K 3.0 Pro runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutputCache read

kt/midm-k-3.0-pro

262K

$0.20

$0.80

$0.04

Specs as reported by each service · usage over the last 2 days · refreshed hourly

Run KT: Mi:dm K 3.0 Pro in Big-AGI.

Connect your own key on any of the services above, at their rates, no markup - and run it side by side with every other model.

Launch Big-AGI

© 2026 Token Fabrics·Built with passion in San Diego