Sign in to Hivenet
Access your files and manage your storage account.
Store
Access your files and manage your storage account.
Compute
Launch instances and manage your compute resources.
Store and Compute still use separate accounts today. We’re working on a unified sign-in.
Just need to send a file?
Use Send directlyNew to Hivenet? Get Started
Get started with Hivenet
Choose what you want to use first.
Store
Back up photos and files across your devices.
Compute
Launch self-serve GPU compute for demanding work.
Store and Compute still use separate accounts today. We’re working on a unified account experience.
Need Hivenet for business?
Talk to salesNeed to send a file?
Open SendAlready have an account? Sign in
Contact Hivenet
Choose the path that fits your question.
General contact
Questions, support, partnerships, press, or anything else not tied to a sales conversation.
Talk to sales
Ask about Compute, storage, private AI, or a larger business deployment.
Need help with setup, billing, or troubleshooting? Start with Support for the fastest answer.
Inference with Compute
Run GPU inference without the usual overhead
Launch inference workloads on RTX 4090 and RTX 5090 instances, start quickly with managed vLLM, and pay only for the time you use.
Why teams choose Compute for inference
Managed inference with vLLM
Start serving in minutes with a managed vLLM template instead of building the whole serving layer from scratch.
Straightforward pricing
Use per-second billing with no separate egress charges and pricing that already includes compute, storage, and network volume.
Flexible networking
Expose the ports your service needs and run behind HTTPS, TCP, or UDP.
Regional deployment options
Run workloads closer to where your users and systems operate when latency and deployment choices matter.
How it works
Swipe left to see more
Choose the 4090 or 5090 tier that fits your model and traffic profile.
Launch from a clean PyTorch or vLLM image and start with a setup that already matches the job.
Enable HTTPS, TCP, or UDP and point your application to the endpoint it needs.
Turn your setup into a custom template so the next launch takes less work.
What people run on Compute
Conversational AI for support and tutoring
LLM endpoints tuned for apps and APIs
Voice models for real-time transcription or captions
Pricing at a glance
Inference workloads often spend long stretches idle, which makes pricing model matter as much as raw GPU speed. Compute keeps that simpler with per-second billing and bundled pricing.
RTX 5090
1 × - 8 ×
vCPU - - -
RAM - - - GB
Disk space - - - GB
Bandwidth - Mb/s
RTX 4090
1 × - 8 ×
vCPU - - -
RAM - - - GB
Disk space - - - GB
Bandwidth - Mb/s
Start self-serve, go deeper when needed
Try Compute directly if you want to test inference pricing, setup, and workflow fit for yourself. Talk to sales if your team needs regional planning, larger deployments, or a more structured rollout. The docs are there when you want to move faster.
Questions teams usually ask
