{"resourceId":"redhat-ai-americas-platform-billing-operator-openshift-ai-maas-metering-20261030","versions":[{"version":"external-322c076bd7129bbf868cd552be7c6bf1f64f2ff87e4a1e9e5323e43a6e703d25","resource":{"id":"redhat-ai-americas-platform-billing-operator-openshift-ai-maas-metering-20261030","title":"Red Hat AI Americas field build: platform-billing-operator adds token metering, prepaid wallets, budgets and GPU reservations to OpenShift AI Models-as-a-Service, with an untested setup guide","organization":"Red Hat AI Americas field organization (GitHub: redhat-ai-americas)","sector":"AI platform engineering; shared inference services and GPU capacity management","geography":"Not location-specific; applicable to US SLED shared-services and research-computing platforms","publishedAt":"Demo cluster setup guide committed Oct. 30, 2026; repository created July 30, 2026; OLM bundle v0.0.1 (alpha) listed Aug. 6, 2026","publicationDate":"2026-10-30","eventDate":null,"sourceName":"GitHub (redhat-ai-americas/platform-billing-operator)","sourceLabel":"Demo Cluster Setup Guide","sourceUrl":"https://github.com/redhat-ai-americas/platform-billing-operator/blob/main/docs/demo-cluster-setup.md","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["infrastructure","governance-procurement","operating-model"],"finding":"Vendor field build: a Red Hat-copyrighted, Apache-2.0 Kubernetes operator that adds billing, metering and FinOps to OpenShift AI Models-as-a-Service. It compiles billing Plans into Kuadrant enforcement policies, meters per-request token usage, manages prepaid wallets, supports Stripe, applies budget actions (Notify, Throttle, Freeze) and offers Guaranteed or Preemptible GPU reservations through Kueue. The guide added on Oct. 30, 2026 calls itself a first draft that nobody has followed end to end on a fresh cluster, marks several OpenShift steps unverified, and lists a tested stack of Connectivity Link 1.4.2, OpenShift AI 3.4.2 (vLLM 0.13.0+rhai19) and Service Mesh 3.1.0. It warns that some OpenShift AI 3.x versions ship a conflicting Authorino version. The repository has no releases. The OperatorHub community bundle (v0.0.1, alpha) is not from a verified publisher, and Artifact Hub's Oct. 31 image scan reports 37 high, 71 medium, 19 low and 4 unknown findings (no critical).","sledRelevance":"State IT shared-services agencies, county consolidated IT and university research-computing centers increasingly run one GPU pool for many departments or labs. Chargeback, quotas and reserved capacity are what turn that pool into a governed service. This build shows one Red Hat-aligned way to do it on OpenShift AI. It is a prototype, and public-sector chargeback usually runs through internal journal entries rather than card payments, so the Stripe path has limited relevance.","evidence":"Read the setup guide and README in the repository, checked the GitHub repository metadata and commit history (guide added Oct. 30, 2026 15:42 UTC; zero stars; no releases), and pulled the Artifact Hub package record (version 0.0.1, alpha channel, unverified publisher, security scan summary). Also read the upstreambeat.ai Oct. 30 write-up, which agrees the project is a field reference implementation rather than a supported product. No usage, cost or accuracy results are published.","architectureImplications":"Metering sits at the Gateway API data plane (a WebAssembly capture filter on Envoy) with a PostgreSQL ledger, and enforcement uses Kuadrant rate-limit and auth policies. That places billing and access control at the same gateway layer Red Hat recommends for protecting inference endpoints. Install order matters because of the Authorino conflict.","governanceImplications":"Budget thresholds and per-tenant plans give a mechanism for enforcing departmental AI spending limits, but the policies, prices and appeal processes remain the agency's to define.","securityPrivacyImplications":"Per-request usage capture creates a ledger of who called which model and when; agencies should decide retention and whether prompts or only token counts are recorded. The community bundle's image scan findings and unverified publisher status need review before any non-lab use.","caveats":"Prototype with no releases; setup guide untested end to end by its own account; Artifact Hub scan findings on the alpha community bundle; no published outcomes. Committed the morning of Oct. 30, before the 10-30 run started, but not in the archive.","streamIds":["red-hat"],"roles":{"sales":"Sales framing: use this to open a chargeback and capacity-governance conversation with central IT and research computing, not to sell a product. Many SLED customers want one GPU pool shared fairly across agencies or labs, with spending caps. This field build shows the pieces on OpenShift AI, but it is unsupported, unreleased and untested end to end. Position any work as requirements discovery or a lab proof of concept, and set expectations that a supported path must come from Red Hat product roadmaps.","engineering":"Engineering framing: treat it as reference code for how metering, plans and GPU reservations can be enforced at the Gateway API layer with Kuadrant on OpenShift AI MaaS. Start with the kind path and fake GPUs to examine policy compilation and the ledger. On OpenShift, follow the install order to avoid the Authorino conflict, rebuild images yourself, and review the community bundle's scan findings. Expect to fix unverified steps such as WASM delivery and model routes.","delivery":"Delivery framing: limit any engagement to a time-boxed lab that produces a chargeback design, not a production billing system. Deliverables should be a tested install record, a list of failed or unverified steps, sample plans and budgets mapped to the customer's departments, and a decision on whether to wait for supported capability. Include a security review of images before connecting real tenants, and keep finance staff involved so plans match internal journal-entry chargeback rules."},"roleDetails":{"sales":{"customerProblem":"Shared GPU and model-serving capacity has no fair, enforceable way to allocate and charge back usage across agencies, departments or labs.","stakeholders":["State or county CIO shared-services lead","Research computing director","Finance / chargeback office","AI platform engineering lead"],"discoveryQuestions":["How do you allocate GPU or model-serving costs to departments today?","Do tenants need reserved capacity or is best effort acceptable?","What spending caps or approvals apply to AI usage?","Can you run unsupported reference code in a lab?"],"valueHypothesis":"A lab proof of concept can turn chargeback policy into testable gateway rules and clarify requirements for a supported solution (interpretation).","potentialEngagement":"Time-boxed lab evaluation (two to three weeks) of metering and plan enforcement on a non-production OpenShift AI cluster.","unsupportedClaims":["That this is a supported Red Hat product","Any cost savings or billing accuracy figures","Production readiness of the OpenShift install path"]},"engineering":{"fit":"Fits OpenShift AI 3.4-era Models-as-a-Service deployments using Connectivity Link (Kuadrant) and Gateway API.","architectureIntegration":"WASM capture filter on the Envoy gateway feeds a PostgreSQL ledger; Plans compile to Kuadrant TokenRateLimitPolicy, RateLimitPolicy and AuthPolicy; Kueue handles GPU reservations.","prerequisites":["OpenShift 4.14+ with cluster-admin, 16+ vCPU, 32 GB RAM, x86_64","Connectivity Link 1.4.2 and OpenShift AI with MaaS enabled","Go and Rust toolchains to build components"],"constraints":["No releases; setup guide untested end to end","Authorino version conflict on some OpenShift AI 3.x versions","Community bundle from an unverified publisher with scan findings"],"security":"Review image scan findings, rebuild images from source, and set retention rules for the per-request usage ledger.","proofOfValue":["Confirm a tenant over budget is throttled or frozen as configured","Reconcile ledger token counts with model-server metrics on a test workload","Document every unverified step that fails"]},"delivery":{"work":"Stand up the lab, run the demo scenarios, map sample plans to real departments and record gaps.","dependencies":["Non-production OpenShift AI cluster","Finance input on chargeback rules","Platform team time"],"ownership":"Central IT shared-services or research computing platform team.","skillsAdoption":"Kubernetes gateway and policy skills are needed; pair platform engineers with finance analysts on plan design.","governanceCheckpoints":["Security review before any real tenant traffic","Finance approval of plan and price definitions","Decision gate on supported versus custom path"],"acceptanceCriteria":["Proposed: ledger and model-server token counts agree within an agreed tolerance on test traffic","Proposed: budget Freeze blocks requests within one minute of threshold","Proposed: written list of unverified steps with outcomes"],"risks":["Code drift with no release or support","Image vulnerabilities","Stakeholders mistaking a lab for a product"]}},"retrievedAt":"2026-11-01T03:08:28Z","enrichedAt":"2026-11-01T03:14:07Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Requires Kubernetes, Gateway API, Kuadrant, Go and Rust (for the WASM filter) skills; this is an engineering kit, not an administrator tool.","procurementImplications":"Unsupported field code: buyers should not treat it as a Red Hat product commitment. It can inform requirements for a supported chargeback capability in RFPs for shared AI platforms.","operatingModelImplications":"Enables a provider-and-tenant model in which central IT runs inference as a service and departments consume against plans or reservations, similar to existing cloud chargeback.","sourceVerification":{"openedUrl":"https://github.com/redhat-ai-americas/platform-billing-operator/blob/main/docs/demo-cluster-setup.md","referenceExcerpt":"Nobody has followed it end to end on a fresh cluster yet.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}