kt/midm-k-3.0-pro

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-11-06 收录该模型(收录时间不等于模型正式发布日期);上下文:261,795 tokens;输入价:$0.2000/百万 tokens;输出价:$0.8000/百万 tokens;定位(来源描述):Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active…

全文

KT: Mi:dm K 3.0 Pro

kt/midm-k-3.0-pro

Compare

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

$0.20 / $0.80per 1M

Context

262K

Released

Nov 5, 2026

Compare

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput

$0.20$0.80$0.040.41s229 tok/s

97.82%

ProviderInput / Output /M

Input $0.20 / Output $0.80

229 tok/s97.82% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.1216/M tokens

Output

$0.7994/M tokens

Mi:dm K 3.0 Pro — Price history

Price history

No effective price data for this selection

$0.122$0.79948.9%100.0%

ProviderInput / Output /M

Token share

Effective in $0.122 / Effective out $0.799

Token share

100.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

229tok/s

P50, best across providers

Latency

0.41s

P50, best provider

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

74.91%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

73.63%

Availability over the last 3 days

Last 72 hours

Availability 73.63%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

98.21%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

Docfu

new

1.69Mtokens

2.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

1.46Mtokens

3.

Nous Research API

Nous Research is an AI research team focused on advancing open-source AI.

1.43Mtokens

4.

Janitor AI

Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.

1.41Mtokens

5.

US Guard ultra review

new

1.08Mtokens

Rest of OpenRouter

6.22M

Top 5 Apps

2.22M

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

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.

Mi:dm K 3.0 Pro costs $0.20/M input tokens and $0.80/M output tokens, with separate rates for Cache Read at $0.04/M tokens.

Mi:dm K 3.0 Pro has a 261,795 token context window. It supports up to 261,795 completion tokens.

Yes. Mi:dm K 3.0 Pro accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Mi:dm K 3.0 Pro is served by 1 provider on OpenRouter: KT.

Mi:dm K 3.0 Pro was released on November 5, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报