KT · live price
Mi:dm K 3.0 Pro API pricing
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.
Small and cheap (under $1 per 1M)Tool callingReasoning
- Input
- $0.2
- per 1M tokens
- Output
- $0.8
- per 1M tokens
- Cached input
- $0.04
- per 1M tokens
- Context
- 262K
- 236K max output
List price from OpenRouter, which passes KT's price through without markup. Refreshed hourly. Released November 5, 2026. Model id kt/midm-k-3.0-pro.
What Mi:dm K 3.0 Pro costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$0.60
1,000 input + 500 output tokens each
1,000 RAG questions
$2.00
8,000 input + 500 output tokens each
100 coding-agent steps
$0.76
30,000 input + 2,000 output tokens each, no caching
Mi:dm K 3.0 Pro price history
No price change since we started tracking on 2026-11-11. We record prices daily; changes will show here.
Mi:dm K 3.0 Pro price by host
One host serves this model through OpenRouter.
- KT$0.2 in · $0.8 out · 262K ctx · 100.0% uptime 24h
Where to buy KT credits for less
Mi:dm K 3.0 Pro costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
Mi:dm K 3.0 Pro cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$18.00/ month
Cheaper alternatives to Mi:dm K 3.0 Pro
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiniMax: MiniMax M3.1 Flash | $0.15 | $0.6 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.036 | $0.5 |
| Anthropic: Claude Haiku 5.5 | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 |