Documentation – OpenMetal Cloud

These guides cover usage and management of the OpenMetal Cloud product and are intended for:

  • Administrators of an OpenMetal Cloud Core and any expansion nodes
  • Any system administrator running their first OpenStack and Ceph public or private cloud
  • Users of the cloud resources (projects/virtual private cloud) within your public or private cloud
  • Users who will be automating against a project/virtual private cloud

New to OpenMetal?

Explore the power of your own cloud. See it in action as a hosted private cloud, for SaaS companies, for hosting and cloud providers and much more. Check out transparent pricing, and even try a free trial.

Product Manuals

Manuals are available for cloud operators, users of projects/virtual private clouds, and more.

Product Manuals

Specific Goal Tutorials

Included in the documentation is a collection of tutorials, helping guide you through common use cases of the OpenMetal platform, including how to provision a Kubernetes cluster.

View the Tutorials

Educational Articles

The manuals should be your first stop when using an OpenMetal cloud but we also have more general OpenStack content.

Here are a set of articles that can help you determine the makeup and size of your clusters.

Kubernetes

These guides are intended to be used as a reference for how to deploy Kubernetes clusters on OpenStack. We’ve documented the steps we took to deploy Kubernetes clusters with the major Kubernetes distributions on OpenStack.

Engineer’s Notes

The OpenMetal team is often doing things that have not been done commonly or may not have documentation online. We are going to publish these notes from those engineers solving real world problems as they occur. These notes are only a first cut on a subject area that can help get a key technical question answered.

 

 

OpenMetal private clouds use two powerful open source tools, OpenStack and Ceph. OpenStack provides the control plane, compute, networking, and APIs. Ceph supplies high-availability block storage, object storage, and, optionally, file storage.  Explore the power of an OpenStack private cloud, check out transparent pricing, and even try a free trial.

ceph-logo

Browse All OpenMetal Education Categories

We are always looking for suggestions to improve our Learning Center. Just email us at learn-suggestions@openmetal.io with yours!

New Educational Content

Aug
19

Keeping Your Build Pipeline in the EU When GitHub Actions Won’t

We look at why a company’s production data residency doesn’t automatically cover its CI/CD pipeline, what GitHub Actions actually offers EU-based teams today, and how self-hosting runners on Amsterdam hardware closes that gap directly.

Aug
17

Infrastructure for Internet-Wide Security Scanning and Attack Surface Management

We look at why attack surface management and cyber-risk scanning companies, businesses that scan large swaths of the public internet as their core product, run into trouble on hyperscaler infrastructure, what actually needs to be true about a provider’s acceptable use policy and IP allocation to support this workload, and how that differs from running an internal penetration testing lab.

Aug
13

Utilization Is a Tenancy Decision: Why Sustained MFU Lives Below the Kernel

On latency-bound inference, the Model FLOPs Utilization your optimization stack can actually hold is capped by who else shares the box, not by the kernel that runs on it. Sustained

Aug
13

When Inference Becomes COGS: The Two Levers Behind AI Gross Margins

Runway Intelligence is OpenMetal’s executive insight series for late-stage startups and their investors, exploring how cloud economics, infrastructure design, and operational strategy shape valuation, margins, and time to exit.  A

Aug
13

Should You Build Your Own Off-Site Backup Server or Rent One?

We walk through the real total cost of building your own dense storage server for off-site backup and archival data versus renting equivalent capacity, covering drive costs in today’s market, the parts of total cost of ownership that don’t show up on a parts list, and how Ceph’s approach to redundancy compares to a single chassis.

Aug
11

The Real Cost Math Behind Self-Hosted GitHub Actions Runners

We work through the actual cost crossover between GitHub-hosted Actions runners and self-hosted runners on dedicated bare metal, using GitHub’s current 2026 rates, correct a common misconception about a self-hosted runner fee that never took effect, and cover what a self-hosted build pipeline needs beyond just cheaper compute.

Aug
10

Comparing OpenMetal, Hetzner, and OVHcloud for Proxmox VE Hosting

We compare three dedicated server providers commonly considered for Proxmox VE hosting, OpenMetal, Hetzner, and OVHcloud, across real hardware specs, current pricing, storage architecture, and support model, so you can match the provider to your actual workload rather than just the sticker price.

Aug
07

Why the EU Cyber Resilience Act’s Reporting Clock Depends on Your Infrastructure

We break down what the EU Cyber Resilience Act’s vulnerability reporting obligations actually require starting September 2026, why the tight reporting clock is fundamentally an infrastructure visibility problem, and where dedicated infrastructure and controlled build pipelines make that clock achievable.

Aug
06

Intel TDX on OpenMetal: Bare Metal Today, OpenStack Orchestration Next

Intel TDX confidential VMs run on OpenMetal dedicated bare metal hardware today, available on on XL v5, with OpenStack Nova orchestration slated for after Hibiscus.

Aug
05

Infrastructure for Post-Quantum Cryptography and Crypto-Agility

We look at why post-quantum cryptography has moved from a research topic to a binding compliance deadline, why “harvest now, decrypt later” makes this an infrastructure problem today rather than a future one, and why crypto-agile key management needs hardware you control directly.

Aug
03

Infrastructure for GENIUS Act Stablecoin Reserve and Redemption Systems

We look at what the GENIUS Act actually requires of payment stablecoin issuers, why reserve tracking, redemption, and transaction monitoring systems need dedicated and auditable infrastructure rather than shared platforms, and where that requirement does and doesn’t touch broader blockchain infrastructure.

Aug
01

Inkling-Small: One FP4 Checkpoint, Two Execution Modes, Two Different Cards

A first-party FP4 checkpoint moves GPU selection from memory capacity to native tensor-core format support, and inverts the usual verdict. Based on the Inkling-Small.

Jul
31

One Memory Decision on OpenMetal v5 Buys Confidential Computing and Full Bandwidth

On OpenMetal v5, one memory decision buys Intel TDX eligibility, full DDR5-6400 bandwidth, and SGX enclave headroom. XL v5 ships ready.

Jul
30

Self-Hosting Your Claude Stack on OpenMetal

Claude is closed-weight and cannot run on your own hardware, but you can self-host the entire application and data plane around it on OpenMetal. Here is how.

Jul
30

Self-Hosting Your Gemini Stack on OpenMetal

Gemini is closed and cannot run on your own hardware, but you can self-host the entire application and data plane around it on OpenMetal. Here is how.

Jul
30

Self-Hosting Your GPT Stack on OpenMetal

GPT is closed-weight and cannot run on your own hardware, but you can self-host the entire application and data plane around it on OpenMetal. Here is how.

Jul
30

Self-Hosting a Closed Model: What’s Actually Possible on OpenMetal

Claude, GPT, and Gemini cannot run on hardware you own, but you can self-host the entire stack around them on OpenMetal. Here is what is actually possible.

Jul
29

Large-Scale Ceph Storage for Financial Data Retention and Audit Archives

We look at why financial services firms accumulate large, long-lived data retention and audit archive requirements, why hyperscaler storage pricing works against that access pattern specifically, and how a large-scale Ceph cluster handles the same requirement with predictable costs and full control.

Jul
28

What US CLOUD Act Jurisdiction Means for Your Singapore Infrastructure

We answer a specific legal question that general Singapore sovereignty content doesn’t: whether US CLOUD Act jurisdiction reaches infrastructure physically hosted in Singapore, how that’s separate from Singapore’s own PDPA framework, and what that means if you’re evaluating a US-owned infrastructure provider for APAC deployment.

Jul
27

Self-Hosting an AI Agent Code Execution Sandbox on Bare Metal

We explain why AI agents that execute code need microVM-level isolation, why that isolation requires direct hardware access that public cloud VMs can’t provide, and how self-hosting a Firecracker or Kata sandbox on dedicated bare metal compares to managed platforms like E2B on cost and control.

Jul
24

Running Confidential Computing Workloads in the EU in Amsterdam

We explain what Intel TDX confidential computing actually protects, confirm which hardware configuration delivers it in our Amsterdam data center today, and walk through why pairing TDX with EU data residency matters for regulated workloads.

Jul
24

Per-Token vs. Dedicated GPU for Coding Agents: Where Fixed Cost Wins

Coding-agent fleets hit dedicated-GPU break-even at ~5-10M tokens/month or 15-25% utilization. Why metered per-token billing punishes the agent workload.

Jul
22

Amsterdam vs Other EU Data Center Locations for Latency and Compliance

We compare Amsterdam against Frankfurt, Dublin, and Paris as EU infrastructure locations, covering network connectivity, latency to key regions, and data residency considerations, then explain why Amsterdam is where OpenMetal actually operates.

Jul
20

Neocloud Became a Power Race, and It Skipped the Middle

Neocloud became a capital-and-power race, leaving sustained mid-market inference underserved. Why predictable cost, not GPU count, is the defensible position.

Jul
20

EU Data Residency and Data Sovereignty Are Not the Same Thing

We break down the real difference between data residency and data sovereignty, why many “sovereign cloud” claims from US-owned providers don’t hold up under scrutiny, and what EU-based infrastructure can and can’t actually guarantee.

Jul
17

Migrating Off Azure: Entra ID and Cosmos DB Are the Hard Part

We look at why Azure’s egress fees are no longer the sharpest lock-in mechanism, and walk through the specific managed services (Azure Functions, Cosmos DB, Service Bus, Logic Apps, Azure AD B2C / Entra External ID) that actually make leaving Azure hard, including the one place Azure is more open than either AWS or GCP, and the one place it’s arguably worse.

Jul
17

Prefill Wants Compute, Decode Wants Bandwidth: The Case for Two Inference Pools

Prefill is compute-bound, decode is memory-bandwidth-bound. Why splitting inference into two purpose-fit GPU pools beats one uniform fleet.

Jul
16

After the Weights: How H200 Headroom Becomes KV-Cache and Concurrency

After weights load, the HBM left over is your KV-cache budget. Why the H200’s 141GB buys more context and concurrency than a 94GB H100.

Jul
16

Role Before Size: Mapping Stateful Workloads to Fixed Hardware SKUs

Map MongoDB, Redis, Kafka, ClickHouse, and Kubernetes workers to OpenMetal SKUs by the resource each role saturates, then size the failure domain.

Jul
16

OpenMetal Central – July 2026

Check out what’s new with OpenMetal Central and our cloud management and control capabilities in July 2026.

Jul
15

Google Cloud’s Real Lock-In Lives in Spanner and Firestore, Not Egress Fees

We look at why Google Cloud’s egress fees are no longer the sharpest lock-in mechanism, and walk through the specific managed services (Cloud Functions, Firestore, Cloud Spanner, Pub/Sub, Cloud Workflows, Identity Platform) that actually make leaving Google Cloud hard, including where GCP’s lock-in profile is genuinely different from AWS’s.

Jul
13

The Real AWS Lock-In Is Managed Services, Not Egress

We look at why AWS egress fees are no longer the lock-in mechanism people think they are, and walk through the specific managed services (Lambda, DynamoDB, Step Functions, EventBridge, SQS/SNS, Cognito, API Gateway) that actually make leaving AWS hard.

Jul
09

Running Llama 3.3 70B on an OpenMetal H200

Yes, Llama 3.3 70B runs on a single OpenMetal H200 at FP8 with full 128K context. See the VRAM fit math, KV-cache budget, and vLLM setup.

Jul
09

Day-2 for a Single-Tenant H200 GPU Node: Provisioning, Drivers, and Blast Radius

An ordered Day-2 playbook for a single-tenant H200: full root and IPMI, owning the CUDA stack, boot-data isolation, and a node-bounded blast radius.

Jul
09

Why MEV Block Building Infrastructure Is Moving to TDX Bare Metal

The operator trust problem in MEV block building has a hardware solution. This article explains why Intel TDX has become the substrate of choice for confidential block building, and what bare metal adds that cloud TDX doesn’t.

Jul
08

How to Prevent Private Cloud Migration Delays

Planning a private cloud project? Organizing well from the start can prevent expensive and time-consuming delays. Our guide explains why hosted private cloud projects stall across migration and day two operations and shows how to prevent delays with better planning, architecture, ownership, and operational readiness.

Jul
08

OpenMetal XL v5 Adds No Cores over XL v4. It Reworks Everything Around Them

OpenMetal XL v5 keeps 64 cores but changes node, memory, I/O, power, AMX, and TDX readiness. Where v5 wins, and the one spec that regresses.

Jul
08

OpenMetal XL v5 vs XL v4 — Same 64 Cores, Different Generation: How to Choose

OpenMetal XL v5 vs XL v4: same 64 cores, but v5 adds 33% memory bandwidth, more PCIe lanes and drive bays, and CPU-side AI; v4 keeps more L3 cache.

Jul
06

Top 8 Reasons Companies Leave Public Cloud in 2026

A skimmable breakdown of the main business and technical drivers pushing companies from public cloud to hosted private cloud, covering cost control, compliance, performance, and operational control.

Jul
02

What HIPAA Requires from the Infrastructure Running Your Healthcare AI Workloads

Healthcare AI workloads carry the same HIPAA obligations as any system touching PHI. This article covers what the 2026 Security Rule update requires from AI infrastructure, why vector embeddings count as PHI, and how dedicated private cloud simplifies the compliance documentation burden.

Jul
01

What AI Startups Need to Plan for Before Their Cloud Credits Run Out

Hyperscaler credits are worth taking, but the architecture built during the subsidized period determines your real cost when billing starts. This covers the credit lifecycle, which decisions create long-term cost exposure, and when private infrastructure makes sense for AI startups in production.

Jun
29

How Nutanix and OpenMetal Compare as VMware Alternatives for Mid-Market IT Teams

Nutanix is a legitimate VMware alternative with real advantages. But its per-core subscription model has cost implications that compound at scale. This article compares both platforms honestly across pricing, operations, migration tooling, and use case fit.

Jun
26

Why MSPs Should Own Their Cloud Infrastructure Instead of Reselling It

Azure CSP resale margins are thin and getting thinner as Microsoft shifts incentives away from transaction volume. This article covers the commercial model for MSPs who own their infrastructure instead, how OpenStack multi-tenancy enables per-client isolation on shared hardware, and what the right client segment looks like.

Jun
24

How the H200 Is Built for Memory-Bound AI Workloads

The H200 is a memory upgrade on the Hopper architecture, not a new compute platform. This article covers why bandwidth matters as much as VRAM capacity, where the 141GB floor changes what fits on a single GPU, and how the NVL PCIe variant differs from the SXM5 for dedicated private infrastructure.

Jun
22

When Running Apache Spark and Delta Lake Without Databricks Makes Financial Sense

Databricks’ Standard tier is being retired, forcing Premium upgrades with higher DBU rates. This article covers how the DBU billing model works, what the open-source stack underneath Databricks looks like, what you give up by self-managing it, and when private cloud infrastructure changes the economics.

Jun
19

Why 96GB VRAM Changes the Economics of Private LLM Inference

The RTX PRO 6000’s 96GB VRAM fits 70B models at FP8 on a single card with real KV cache headroom. This article covers what that unlocks, how dedicated fixed-cost GPU infrastructure compares structurally to cloud rental, and where the H200 is the better choice.

Jun
18

NVIDIA H200 vs H100 — GPU Comparison for AI Training and Inference

NVIDIA H200 vs H100 for AI training and inference: 141GB HBM3e vs 80–94GB, same Hopper compute with more memory. OpenMetal runs the H200 on bare metal.

Jun
18

NVIDIA RTX PRO 6000 vs H200 — Which OpenMetal GPU Server Should You Choose?

NVIDIA RTX Pro 6000 vs H200 on OpenMetal: 96GB GDDR7 + FP4 for cost-efficient AI vs 141GB HBM3e for the largest models. Both single-tenant bare metal.

Jun
18

Bare Metal GPU Server — NVIDIA H200 NVL — Dual Intel Xeon 6530P, 1TB DDR5, 141GB HBM3e

OpenMetal NVIDIA H200 bare metal GPU server: 141GB HBM3e, dual Xeon 6530P, 1TB DDR5. Single-tenant bare metal, fixed monthly pricing.

Jun
18

OpenMetal GPU Clusters — Dedicated Multi-GPU Infrastructure for AI Training and Inference

OpenMetal GPU clusters: dedicated single-tenant multi-GPU infrastructure. All-RP6000, all-H200, or mixed on a private 40 Gbps mesh, fixed monthly pricing.

Additional Resources

Account Management

If you are a current customer and need to connect with your account manager or dedicated support engineer, please log in to your OpenMetal Central account and navigate to the account services section.

OpenMetal Central Login

Pricing Estimator

Are you new to OpenMetal and need to estimate or compare costs? We stand for transparent pricing free of hidden costs and unnecessary license fees. Check out our online pricing estimator and then contact us if you have any questions.

View Pricing

Your Customer Success Team

Account Managers

Gateway to the team that can quickly assess next steps.

Engineers

Ready to guide, train, and configure against your priorities.

Business Analysts

Calculate ROIs, manage migrations, keep the teams aligned.

Executive Connect

Accountable executives available to your leadership as needed.

The Next Generation of Cloud Infrastructure Solutions

Cloud Cores

Start with all the top OpenMetal features in a highly available configuration.

Explore Cloud Cores

Cloud Expansion Nodes

Scale your cloud with flexible building blocks that fit your business.

Explore Cloud Expansion

Storage Clusters

Get high performance object, block, and file storage with fair egress at simple prices.

Explore Storage Clusters