Skip to content
ModelPriceLab

Search model prices

Find source-linked rates by model, vendor, or platform.

Model Services/kt/Mi:dm K 3.0 Pro
kt

Mi:dm K 3.0 Pro

Active

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.

View current API pricing for this model
Input, output, and cached rates with source and verification time, plus same-workload cost examples.
Go to pricing page →
Input / 1M tokens
$0.20
Output / 1M tokens
$0.80
Record updated 2026-11-11
Modality:LLM
Context:261,795 tokens

Pricing

Platform
Scope
Input
Output
Details
OpenRouter
Unified API Router
Standard
$0.20
$0.80
262k context · 236k max output

How much are you overpaying?

Enter your monthly spend on this model to see what the same workload could cost on cheaper alternatives.

$
Enter a monthly spend to see the listed-rate comparison.

Latest changes

No recent changes.

Benchmarks

No benchmark data available.

⚡Mi:dm K 3.0 Pro Comparisons & Scenario Guides

❓Mi:dm K 3.0 Pro Frequently Asked Questions

How much does Mi:dm K 3.0 Pro cost per 1M tokens?▼

Mi:dm K 3.0 Pro is priced at $0.20 per 1M input tokens and $0.80 per 1M output tokens, with cached input at $0.04/1M on openrouter. Check provider terms before deployment.

What is the context window for Mi:dm K 3.0 Pro?▼

Mi:dm K 3.0 Pro supports up to 261,795 tokens context with a max completion limit of 235,615 tokens.

What are cost-saving alternatives to Mi:dm K 3.0 Pro?▼

ModelPriceLab automatically calculates cheaper alternatives in the same model class, showing monthly spend differences and migration guides.

AI Cost Optimization

Does this change your best option?

Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.