Releases

Keep up to date with our product releases

Get the latest information on our product updates, including new features and improvements. Here's a look at what's been released and what's ahead.

mkinf hub

14.11.2024

The waiting list for the mkinf Hub is now open! Be among the first to gain early access to our platform for effortlessly creating and deploying AI agents.

API v0.2

05.10.2024

API v0.2 👾 Now Live!

Featuring:

-

New Regions:

Expanded support in Europe and Canada to better serve our global users.

-

Enhanced GPU Availability:

More GPU models are now available including RTX A4000 / A5000 / A6000, L40, A100 and H100.

-

NVLink support:

For A100 80GB and H100 80GB models.

-

SXM support:

For H100 80GB.

Dashboard

09.09.2024

Access our API via a simplified interface and spin up a GPU instance in less than a minute.

API v0.1

02.09.2024

API v0.1 👾 Now Live! Now with dashboard-supported features and the ability to create and manage multiple projects seamlessly.

New Website

26.07.2024

Explore our brand new website — sleek design and faster access, to make exploring easier than ever.

API v0.0

17.06.2024

API v0 👾 Now Live! Get access to on-demand GPUs via API. Pay per minute and scale your computational resources whenever needed, ideal for making inferences of AI models with variable user base.

Hello World

17.06.2024

Out of stealth mode

Gen AI Infra 🥷

16.02.2024

Coming soon...

A dev tool for building and deploying AI agents

With the mkinf hub, you can seamlessly integrate production-ready AI agents and tools into any framework using a simple SDK or API call — cutting down development time and complexity. Why mkinf?

MCP-powered integrations for smooth and efficient connectivity
Secure managed sandboxes for scalable, hassle-free execution
Constantly evolving — new tools & real-world use cases added weekly
Monetization opportunities — soon, you’ll be able to contribute and earn

Just Need Infrastructure? No Problem.

If you only need access to infrastructure, you can leverage our distributed grid of GPUs. Our unified API simplifies deployment across our network of top tier data centers, delivering the fastest performance for your workloads.