We built Hyperbolic’s GPU Marketplace to give AI developers fast, affordable access to compute, with zero friction. From day one, the focus has been on giving you more control, better performance, and a smoother developer experience.
After dozens of user interviews and feature requests, we’re launching something many of you have been asking for: Custom Port Configuration for GPU Instances.
This update allows you to specify custom ports, enabling you to open any number of services to the public. Whether you're running inference servers, custom APIs, full-stack apps, or specialized workflows, now you can expose the ports you need, directly from your instance.
Key features include
Custom Port Range: Set and expose any ports your app requires
Flexible App Support: Run anything that needs external network access, from model inference to data analytics platforms
Direct Communication: Talk directly to your instance over specific ports with no proxies or extra config
You now have more flexibility to run your own stack, experiment with new workflows, and treat your GPU instance like real infrastructure, not just a one-trick endpoint. We’re continuing to evolve the platform based on how you build. Get started by heading to app.hyperbolic.xyz.
Want to share feedback? Hit us up on X, LinkedIn, or Discord.
About Hyperbolic
Hyperbolic is democratizing AI by delivering a complete open ecosystem of AI infrastructure, services, and models. Through coordinating a decentralized network of global GPUs and leveraging proprietary verification technology, developers and researchers have access to reliable, scalable, and affordable compute as well as the latest open-source models.
Founded by award-winning Math and AI researchers from UC Berkeley and the University of Washington, Hyperbolic is committed to creating a future where AI technology is universally accessible, verified, and collectively governed.
Website | X | Discord | LinkedIn | YouTube | GitHub | Documentation
