Red Hat OpenShift
Red Hat's Kubernetes-based container application platform, extended with an MLOps/LLMOps component (OpenShift AI) for training, serving and managing AI models.
Description
Red Hat OpenShift is a Kubernetes-based container application platform developed by Red Hat (an IBM subsidiary since 2019). The first release appeared in 2011, and from version 3 (2015) the platform has been built around Kubernetes. OpenShift 4 uses Red Hat Enterprise Linux CoreOS and Operators to automatically manage the cluster lifecycle.
The platform comes in several variants: the self-managed OpenShift Container Platform (on-premises and in the cloud), fully managed services — ROSA (Red Hat OpenShift Service on AWS), ARO (Azure Red Hat OpenShift) and OpenShift Dedicated — and the community OKD distribution. Clusters are managed through the oc command-line interface, the Kubernetes REST API and Operators.
The AI/ML component is Red Hat OpenShift AI (formerly OpenShift Data Science) — an MLOps/LLMOps platform for training, serving and monitoring models. It uses KServe and vLLM for model serving, data science pipelines (Kubeflow Pipelines), a model registry, MLflow and TrustyAI tooling for drift detection and bias evaluation. It supports hybrid deployments, including disconnected environments and private AI.
MLOps LifecycleMLOps LifecycleFull model lifecycle: registry, feature store, prompt management, monitoring and human-in-the-loop.
Model Registry
Monitoring
Data & KnowledgeData & Knowledge ManagementData connectors, vector database integration, native vector search and data management (PII, provenance, synthetic data).
ApplicationsAI ApplicationsDomains and use cases this platform is best suited for — from RAG and fine-tuning to scientific research.
SecurityEnterprise SecurityCertifications, access controls and data-protection features essential for corporate deployments and cloud privacy compliance.
Developer EcosystemDeveloper EcosystemDeveloper resources: available SDKs, supported programming languages, and infrastructure features and model-deployment methods.
Organization RelationsOrganization RelationsMap of key business and technology relationships with other organizations, including distributors, investors and research labs.
Pricing & Business ModelPricing & Business ModelBilling models (usage-based, provisioned throughput), resource limits and SLA parameters (uptime, support tiers).
Pricing models
Resource quotas
SLA & Support