InferenceHosted Inference

Use NVIDIA Endpoints

View as Markdown

NVIDIA Endpoints routes NemoClaw to models hosted on build.nvidia.com through an OpenAI-compatible API. The sandbox keeps using inference.local while OpenShell forwards requests to the NVIDIA endpoint.

Credential

Set NVIDIA_INFERENCE_API_KEY in the host shell before onboarding. NemoClaw applies the nvapi- prefix check only to this credential and keeps the key on the host.

Model Choices

The bundled fallback choices include these models.

  • nvidia/nemotron-3-ultra-550b-a55b.
  • nvidia/nemotron-3-super-120b-a12b.
  • minimaxai/minimax-m3.

Interactive onboarding loads NVIDIA’s public featured model catalog and can show additional live models. You can also choose Other and enter a model ID from the catalog.

Onboard

Run the onboarding wizard and select NVIDIA Endpoints.

$nemo-deepagents onboard

The wizard validates a manual model entry against the catalog before it continues. If the live catalog is unavailable or does not contain safe model IDs, the wizard warns you and uses the bundled fallback list.

Validation

NemoClaw validates NVIDIA Endpoints through /v1/chat/completions only. It skips /v1/responses because NVIDIA Build does not expose that route. The wizard retries transient upstream failures before it reports a provider failure.