Kt

KT 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.

Context window
262Ktokens
Max output
236Ktokens
Input
$0.20/ 1M
Output
$0.80/ 1M

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://neurongate.net/v1",
    api_key="sk-ng-your-api-key",
)

completion = client.chat.completions.create(
    model="kt/midm-k-3.0-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)

Cost

Example requestTokensCost
Short prompt1K in$0.0002
Typical chat turn1K in · 500 out$0.0006
Document analysis10K in · 2K out$0.0036
Long context100K in · 10K out$0.028
Estimated cost per request$0.0006

Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.

Frequently asked questions

What is KT 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.

How much does KT Mi:dm K 3.0 Pro cost?

KT Mi:dm K 3.0 Pro is priced at $0.2 per 1 million input tokens and $0.8 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).

Does KT Mi:dm K 3.0 Pro support streaming?

Yes, KT Mi:dm K 3.0 Pro supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.

What is the context window of KT Mi:dm K 3.0 Pro?

KT Mi:dm K 3.0 Pro has a context window of 262K tokens (~196K words). Maximum output is 236K tokens.

Does KT Mi:dm K 3.0 Pro support function calling (tools)?

Yes, KT Mi:dm K 3.0 Pro supports function calling / tool use via NeuronGate's standard API.

How do I use KT Mi:dm K 3.0 Pro with NeuronGate?

Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id kt/midm-k-3.0-pro in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.