KT: Mi:dm K 3.0 Pro

kt/midm-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.

Modalities

In / out price

$0.2 / $0.8 per 1M

Context

262K

Released

Nov 5, 2026

Why use Mi:dm K 3.0 Pro

Step-by-step reasoning mode
Structured (JSON) outputs

Pricing

Input	$0.2 / 1M tokens
Output	$0.8 / 1M tokens
Cached input (read)	$0.040 / 1M tokens

List prices via OpenRouter, checked daily. Real cost depends on the provider and on reasoning tokens.

Cost calculator

Pick a task, set how often you run it, and compare what it costs on each model.

TaskInput tokens≈ 602 wordsOutput tokens≈ 1,504 wordsRuns per month

Input served from cache: 0%Repeated prompts (same instructions or document) are billed at the cheaper cache-read price where the model supports it.

Model	Per run	Per month	Per 1,000 runs
KT: Mi:dm K 3.0 Pro	$0.0018	$1.76	$1.76

Estimates from list prices via OpenRouter; real bills vary by provider and reasoning tokens.

Will it fit? Context window simulator

Each square is about one page (500 words). Colored squares are your content; grey squares are free space in the model's context window.

Your content

Novel (90,000 words)

Total: about 120,000 tokens (≈ 90,226 words). Token counts are estimates.

Models

Zoom (square size): 6pxZoom out to see a whole million-token window at once.

KT: Mi:dm K 3.0 Pro

261,795 tokens ≈ 394 pages

Fits: uses 46% of the window (room for 2× this much).

Write with the best model for the job

WordGPT picks and switches models for you: drafting, editing and files in one place. Free plan, no credit card.

Try it free