> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workloads/workloads-v-2/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/run-ai/_mcp/server.

# Workloads V2

The Workloads V2 API allows you to create, retrieve, and delete workloads that originate from third-party ML frameworks, tools, or the broader Kubernetes ecosystem. These workloads are registered in the platform through the Workload Types API, some are already registered in NVIDIA Run:ai, while others can be added by administrators.
Each submission combines the user's Kubernetes manifest with NVIDIA Run:ai scheduling metadata, enabling consistent orchestration, monitoring, and governance. See [Extending workload support](/run-ai/self-hosted/documentation/workloads-in-nvidia-run-ai/workload-types/extending-workload-support) for more details.


## API Docs

- Workloads V2 [Create a workload.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workloads/workloads-v-2/create-workload-v-2.md)
- Workloads V2 [Get a specific workload.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workloads/workloads-v-2/get-workload-v-2-by-id.md)
- Workloads V2 [Update workload spec.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workloads/workloads-v-2/update-workload-v-2.md)
- Workloads V2 [Delete a workload.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workloads/workloads-v-2/delete-workload-v-2.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workloads/workloads-v-2/openapi.json)
- [OpenAPI YAML](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workloads/workloads-v-2/openapi.yaml)