> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemoclaw/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemoclaw/_mcp/server.

# Use OpenAI

> Configure NemoClaw to use the OpenAI API for hosted inference.

The OpenAI provider routes NemoClaw inference to the OpenAI API through OpenShell.
The sandbox uses the managed `inference.local` route and does not receive the raw OpenAI API key.

## Credential

Set `OPENAI_API_KEY` in the host shell before onboarding.
NemoClaw uses provider-aware validation during credential retries.

## Model Choices

The onboarding wizard offers these curated model IDs.

* `gpt-5.4`.
* `gpt-5.4-mini`.
* `gpt-5.4-nano`.
* `gpt-5.4-pro-2026-03-05`.

## Onboard

Run the onboarding wizard and select **OpenAI**.

```bash
nemoclaw onboard
```

Select a model when the wizard prompts you.
NemoClaw validates the selected provider and model before creating the sandbox.

## Validation

NemoClaw tries the OpenAI `/responses` route first and then falls back to `/chat/completions` during validation.
The wizard retries transient upstream failures before it reports a provider failure.

## Related Topics

* [Choose a Model](../learn-and-choose/choose-model) compares the curated OpenAI models by task fit.
* [Understand Provider Validation](../validate-inference/understand-provider-validation) describes the validation sequence.