Red Hat OpenShift AI Self-Managed
Commercial AI and machine-learning platform installed as an Operator on a customer-operated Red Hat OpenShift cluster.
3 sources checked by an editor on · Product website ↗
Read this page as JSON or Markdown.
Deployment terms: BYOC · control plane · data plane · private offer
· Open requirements shortlist · Estimate operating costs
Compare this listing with another →
Red Hat OpenShift AI 3.5.3 critical security update
RHSA-2026:95872 is a critical OpenShift AI 3.5.3 update covering nine CVEs.
Scope: Red Hat OpenShift AI 3.5 packages identified in the erratum.
Installed components and package versions determine applicability.
Action: Apply OpenShift AI 3.5.3 or a later supported update following Red Hat's erratum.
Primary source · Reviewed 2026-11-18
What lands where
Supplied by
Vendor or project
OpenShift AI Operator through OperatorHub or the oc command-line interface
Runs in
Documented customer environment
OpenShift operators and persistent AI workbench, pipeline, model-serving and supporting services on customer Kubernetes infrastructure.
- AWS: Customer cloud account
- Azure: Customer cloud account
- Google Cloud: Customer cloud account
- Oracle Cloud: Customer cloud account
- IBM Cloud: Customer cloud account
- AWS
- Azure
- Google Cloud
- Oracle Cloud
- IBM Cloud
Servers / containers
Operated by
Your team
Customer manages the OpenShift cluster, storage, accelerators, identity, networking, model data, backups and upgrades within Red Hat's supported configuration matrix.
Deployment boundaries by provider
- AWS: Customer cloud account · Customer-operated
Resources in the customer's cloud account, subscription, project or tenancy. Managed cloud services still have shared responsibilities.
OpenShift AI Self-Managed on supported OpenShift public-cloud platforms ↗ · Source checked 2026-11-17
- Azure: Customer cloud account · Customer-operated
Resources in the customer's cloud account, subscription, project or tenancy. Managed cloud services still have shared responsibilities.
OpenShift AI Self-Managed on supported OpenShift public-cloud platforms ↗ · Source checked 2026-11-17
- Google Cloud: Customer cloud account · Customer-operated
Resources in the customer's cloud account, subscription, project or tenancy. Managed cloud services still have shared responsibilities.
OpenShift AI Self-Managed on supported OpenShift public-cloud platforms ↗ · Source checked 2026-11-17
- Oracle Cloud: Customer cloud account · Customer-operated
Resources in the customer's cloud account, subscription, project or tenancy. Managed cloud services still have shared responsibilities.
OpenShift AI Self-Managed on supported OpenShift public-cloud platforms ↗ · Source checked 2026-11-17
- IBM Cloud: Customer cloud account · Customer-operated
Resources in the customer's cloud account, subscription, project or tenancy. Managed cloud services still have shared responsibilities.
OpenShift AI Self-Managed on supported OpenShift public-cloud platforms ↗ · Source checked 2026-11-17
Application operations and account ownership are separate from infrastructure operations. Confirm external services, telemetry, support access and backup destinations for the chosen path.
| Install method | OpenShift AI Operator through OperatorHub or the oc command-line interface |
|---|---|
| Infrastructure | Servers / containers OpenShift AI runs persistent operator-managed workloads on customer OpenShift clusters with storage, compute and optional accelerator dependencies. |
| Licensing model | Commercial Only The selected Self-Managed product requires a Red Hat OpenShift AI subscription and an eligible OpenShift platform entitlement. Open-source components do not grant the complete supported product entitlement. |
| License | Commercial Red Hat OpenShift AI Self-Managed subscription; an eligible OpenShift subscription is also required. |
Buyer diligence
Answers apply to the reviewed edition and deployment. Expand a row for qualifications and sources.
How to read these facts
Not researched means no field-specific review is recorded. Not confirmed means sources were checked but did not establish an answer. Availability, eligibility and edition-dependent findings retain the scope given in their evidence. A vendor’s hosted-service certification does not automatically cover your deployment. Evidence coverage is not a feature score.
12 of 12 fields researched (100%) · 7 documented · 5 unresolved. Evidence coverage is not a feature score.
- Marketplace delivery
Not confirmedEvidence and scope for Marketplace delivery
OperatorHub installation and required subscriptions do not establish a specific cloud Marketplace offer for the Self-Managed AI entitlement. Managed add-ons and generic OpenShift offers are separate.
Reviewed public evidence for Red Hat OpenShift AI Self-Managed; unresolved within this edition/deployment · Source ↗ · Reviewed 2026-11-17
Sources checked — unresolved · Editor reviewed.
- Cloud commitment eligibility
Not confirmedEvidence and scope for Cloud commitment eligibility
Self-Managed AI and underlying OpenShift subscriptions need offer-specific confirmation before software charges are treated as eligible cloud commitment spend.
Reviewed public evidence for Red Hat OpenShift AI Self-Managed; unresolved within this edition/deployment · Source ↗ · Reviewed 2026-11-17
Sources checked — unresolved · Editor reviewed.
- Single sign-on
AvailableEvidence and scope for Single sign-on
OpenShift AI uses the identity provider configured for its OpenShift cluster. Configure cluster identity and AI user/admin groups; this does not establish a separate application SCIM endpoint.
Self-managed OpenShift AI 3.5 identity through the cluster · Source ↗ · Reviewed 2026-11-17
Documented · Editor reviewed.
- SCIM provisioning
Not confirmedEvidence and scope for SCIM provisioning
AI authentication delegates to the OpenShift IdP. The reviewed installation guide does not establish a separate AI SCIM endpoint or the provisioning capabilities of the buyer’s chosen IdP.
Reviewed public evidence for Red Hat OpenShift AI Self-Managed; unresolved within this edition/deployment · Source ↗ · Reviewed 2026-11-17
Sources checked — unresolved · Editor reviewed.
- Compliance attestations
Not confirmedEvidence and scope for Compliance attestations
The reviewed Red Hat OpenShift AI Self-Managed material establishes configuration/operating controls, but not an independent current attestation covering this edition and customer deployment. Obtain the actual report/certificate, audit period and scope before claiming coverage.
Customer deployment attestation; vendor SaaS, cloud-provider and component certifications are not automatically inherited · Source ↗ · Reviewed 2026-11-17
Sources checked — unresolved · Editor reviewed.
- Security controls
DocumentedEvidence and scope for Security controls
Installation requires cluster administrator access, a configured IdP and compatible subscriptions. Configure access groups and certificate trust for workbenches, models, pipelines and object storage. Current advisory review: RHSA-2026:95872 is a critical OpenShift AI 3.5.3 update covering nine CVEs. Apply OpenShift AI 3.5.3 or a later supported update following Red Hat's erratum.
OpenShift AI cluster access prerequisites Red Hat OpenShift AI 3.5 packages identified in the erratum. · Source ↗ · Certificate trust in disconnected deployments ↗ · Prior security-controls source ↗ · Reviewed 2026-11-18
Documented · Editor reviewed.
- Air-gapped operation
AvailableEvidence and scope for Air-gapped operation
Red Hat supplies a separate disconnected installation guide using mirrored Operator/container content. Required model, notebook, accelerator and object-storage dependencies must also be staged for the selected components.
Self-managed OpenShift AI disconnected installation · Source ↗ · Reviewed 2026-11-17
Documented · Editor reviewed.
- Deployment artifact / IaC
DocumentedEvidence and scope for Deployment artifact / IaC
Install the supported OpenShift AI Operator on an entitled, compatible OpenShift cluster and enable the required components. Cluster creation, storage, accelerators and model assets remain separate deployment work.
OpenShift AI Self-Managed 3.5 Operator installation · Source ↗ · Reviewed 2026-11-17
Documented · Editor reviewed.
- Minimum footprint / sizing
DocumentedEvidence and scope for Minimum footprint / sizing
Installing the Operator requires at least two workers with 8 CPU/32 GiB each; single-node OpenShift requires 32 CPU/128 GiB. Workloads, models, accelerators and storage need additional resources; these installation minima do not establish HA workload capacity.
OpenShift AI 3.5 installation minima; platform/control-plane resources additional · Source ↗ · Reviewed 2026-11-17
Documented · Editor reviewed.
- License pricing
DocumentedEvidence and scope for License pricing
The selected Self-Managed product requires a Red Hat OpenShift AI subscription and an eligible OpenShift platform entitlement. Open-source components do not grant the complete supported product entitlement.
Red Hat OpenShift AI Self-Managed: software entitlement and edition boundary; infrastructure and operating costs are separate · Source ↗ · Reviewed 2026-11-17
Documented · Editor reviewed.
- Operating cost estimate
Not confirmedEvidence and scope for Operating cost estimate
Select OpenShift HA topology, enabled AI components, model size, GPU needs, concurrency, object storage and both subscription entitlements. Operator installation minima do not size inference/training. A complete monthly operating estimate is not established.
Requested planning scenario: AWS us-east-1, 100 internal users, 1 TB data, HA, average usage; missing workload metrics and commercial terms are explicit · Source ↗ · Reviewed 2026-11-17
Sources checked — unresolved · Editor reviewed.
- Release snapshot / cadence
DocumentedEvidence and scope for Release snapshot / cadence
Red Hat OpenShift AI 3.5.3 was published as critical security advisory RHSA-2026:95872 on November 6, 2026 and covers nine CVEs.
Red Hat OpenShift AI self-managed 3.5 · Source ↗ · Reviewed 2026-11-18
Documented · Editor reviewed.
Scope & considerations
This entry covers OpenShift AI Self-Managed, not Red Hat's managed cloud-service add-on. Support depends on a compatible OpenShift Container Platform release, storage and accelerator matrix, and active subscriptions. Underlying OpenShift and cloud infrastructure are operated by the customer. RHSA-2026:95872 is a critical OpenShift AI 3.5.3 security update covering nine CVEs. Use Red Hat's package and deployment scope to determine affected components, then apply 3.5.3 or a later supported update.
Category fit
- AI tools & infrastructure
- AI workbenches, pipelines, model serving and lifecycle tooling delivered on a customer-operated OpenShift platform.
Compare within AI tools & infrastructure
- AnythingLLM DockerSelf-hosted application for document-grounded AI chat, retrieval and agents.
- AWS
- Google Cloud
- Railway
- Arize Phoenix Self-HostedAI observability and evaluation server for traces, datasets and application experiments.
- AWS
- Azure
- Google Cloud
- Railway
- Render
- Cloudera on CloudCloudera-managed control plane that provisions data, analytics and AI workload services into a customer's public-cloud account.
- AWS
- Azure
- Google Cloud
- Dataiku DSS Cloud StacksCommercial Dataiku DSS deployment managed through Fleet Manager inside a customer AWS, Azure or Google Cloud tenant.
- AWS
- Azure
- Google Cloud
- Dify Self-HostedVisual AI application and RAG workflow platform available as a self-hosted container stack.
- Alibaba Cloud
- Elastic Cloud on KubernetesElastic's Kubernetes operator for deploying and operating Elasticsearch, Kibana and related Elastic Stack resources in customer clusters.
- AWS
- Azure
- Google Cloud
- Hyperscience HypercellCommercial document-intake and extraction platform installed into customer Kubernetes infrastructure.
- AWS
- Azure
- Google Cloud
- KNIME Business HubCommercial workflow collaboration and automation platform launched from AWS, Azure or Google Cloud Marketplace VM images.
- AWS
- Azure
- Google Cloud
Showing 8 of 30 other listings in AI tools & infrastructure. These products address related workflows; read their category-fit notes before comparing scope. See all of AI tools & infrastructure →
Installation outline
- Choose the documented deployment option and a dedicated cloud environment. Follow the launch methodology.
- Review the vendor's installation documentation, required permissions and outbound data flows.
- Deploy to a non-production environment; configure identity, networking and monitoring.
- Test backup recovery and upgrades before promoting to production.
Evidence trail
Every claim on this page traces to the sources below. They document the deployment option; they do not constitute a security certification.
- Deployment sourcesChecked
- OpenShift AI supported configurations ↗access.redhat.com
- OpenShift AI Self-Managed 3.5 installation and subscription ↗docs.redhat.com
- RHSA-2026:95872 ↗access.redhat.com
- Cloud deployment evidenceChecked
The linked sources describe each deployment path, edition and support scope. Community templates and partner statements are identified in the notes.
- OpenShift AI Self-Managed on supported OpenShift public-cloud platforms ↗ · AWS, Azure, Google Cloud, Oracle Cloud, IBM Cloud
Vendor / upstream documentation · Reviewed 2026-11-17. Vendor support commitment: not assessed; confirm the selected release and contract.
Red Hat's Self-Managed matrix explicitly lists OpenShift Container Platform on AWS, Azure, Google Cloud, IBM Cloud and Oracle Cloud. The selected OpenShift release, subscriptions, storage, accelerator and component restrictions apply; managed cloud-service add-ons are a separate offering.
- OpenShift AI Self-Managed on supported OpenShift public-cloud platforms ↗ · AWS, Azure, Google Cloud, Oracle Cloud, IBM Cloud
- Infrastructure evidenceChecked
- Licensing evidenceChecked