kt / text-generation API-only released 2026-11-05

Mi:dm 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.

Input / 1M

$0.20

Output / 1M

$0.80

Context

261.8K

AA Intelligence

—

Closed weights — available only as a hosted API text → text View on OpenRouter ↗

Pricing

via OpenRouter · USD per 1M tokens · synced 2026-11-11

$0.20

input / 1M

$0.80

output / 1M

$0.04

cached input / 1M

$1.00

1M in + 1M out

Context window: 261,795 tokens
Max output: 235,615 tokens
Providers: 1
Cheapest provider: KT · $0.20 / $0.80
Best throughput: —
AA Intelligence / Coding / Agentic: — / — / —

✗ Tool calling ✓ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✓ Prompt caching

Price history

tracking started — chart appears after 7 days of snapshots (1 recorded)

Current: $0.20 input · $0.80 output per 1M tokens

Providers

1 provider · per 1M tokens · last 30 min metrics

Provider	Quant	Context	Input	Output	Uptime	Tok/s
KT	unknown	261.8K	$0.20	$0.80	100%	—

Provider data from OpenRouter's endpoint listing, refreshed daily.

Specifications

Organisation: kt
Released on OpenRouter: 2026-11-05
Context window: 261,795 tokens
Max output: 235,615 tokens
Input: text
Output: text
Tokenizer: Other
Moderated by provider: No
OpenRouter id: kt/midm-k-3.0-pro

Compare with

Browse

All API-only models Open-weights alternatives Best value via API

Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.