> 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/workload-assets/compute/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/run-ai/_mcp/server.

# Compute

A compute resource is a building block that represents compute resources such as GPUs, CPU cores, and CPU memory.
The compute resources may consist of multiple physical resources, for example, 0.5 GPU, 8 cores and 200 Megabytes of CPU memory. 
A compute resource is available to a scope and and all of the organizational units within that scope. 

For more information, see [Compute resource](/run-ai/self-hosted/documentation/workloads-in-nvidia-run-ai/assets/compute-resources).


## API Docs

- Compute [List compute assets.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workload-assets/compute/list-compute-assets.md)
- Compute [Create compute asset.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workload-assets/compute/create-compute-asset.md)
- Compute [Retrieve a compute asset.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workload-assets/compute/get-compute-asset-by-id.md)
- Compute [Update a compute asset.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workload-assets/compute/update-compute-asset-by-id.md)
- Compute [Delete a compute asset.](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workload-assets/compute/delete-compute-asset-by-id.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/workload-assets/compute/openapi.json)
- [OpenAPI YAML](https://docs.nvidia.com/run-ai/self-hosted/v3.0/reference/rest-api/endpoints/workload-assets/compute/openapi.yaml)