# Product Support Policy

The product support levels for the NVIDIA Run:ai software are as follows:

|                  | Critical Bug Fixes | Important Bug Fixes |
| ---------------- | ------------------ | ------------------- |
| Full support     | X                  | X                   |
| Extended support | X                  | N/A                 |

* Full support period: Months 0-9 following the release date of a Major Version.
* Extended support period: Months 10-12 following the release date of a Major Version.
* End of support: Occurs at the conclusion of month 12 following the release date of a Major Version.

For specific versions, see [Product version life cycle](/self-hosted/2.23/support-policy/product-version-life-cycle.md).

Definitions:

1. **Critical Bug**: a bug that represents a severity 1 support ticket, as listed in the NVIDIA Run:ai support agreement.
2. **Important Bug**: a bug that represents a severity 1 or severity 2 support ticket, as listed in the NVIDIA Run:ai support agreement.

Notes:

1. Versioning: NVIDIA Run:ai versioning follows Semantic Version (SemVer) numbering scheme, “Ma.Mi.Pa”, where:
   * **Ma.Mi** is a major version that contains new features, bug fixes and security updates (“**Major Version**”).
   * **Pa** is a patch level version that is focused on bug fixes and security updates. NVIDIA Run:ai version release dates are listed in the NVIDIA Run:ai product documentation.
2. NVIDIA Run:ai Components: NVIDIA Run:ai is built from 3 components: NVIDIA Run:ai Control Plane, NVIDIA Run:ai Cluster and NVIDIA Run:ai Command Line Inference (CLI). For full details about NVIDIA Run:ai system components, see [System components](/self-hosted/2.23/getting-started/overview.md#nvidia-run-ai-system-components).
   * NVIDIA Run:ai Control Plane, NVIDIA Run:ai Cluster & NVIDIA Run:ai CLI are always released together with the same version number.
3. Supported Environments: Enterprise Support applies to an NVIDIA Run:ai environment built with the following components:
   * NVIDIA Run:ai Control Plane of a version equal to or greater than the versions of each of the NVIDIA Run:ai Clusters.
   * NVIDIA Run:ai CLI of a version equal to the version on the NVIDIA Run:ai Cluster.
4. From time to time, NVIDIA Run:ai may provide deprecation notices under the product documentation of the applicable NVIDIA Run:ai version.
5. NVIDIA Run:ai support periods are governed by the terms of the [NVIDIA Cloud Agreement](https://www.nvidia.com/en-us/agreements/cloud-services/nvidia-cloud-agreement/) or [NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/), as applicable, including the [Service Specific Terms for NVIDIA Run:ai Control Plane Service](https://www.nvidia.com/en-us/agreements/cloud-services/runai-control-plane/).

Last update: March 22, 2026


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://run-ai-docs.nvidia.com/self-hosted/2.23/support-policy/product-support-policy.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.