> 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 Anthropic

> Configure NemoClaw to use the Anthropic Messages API for hosted inference.

The Anthropic provider routes supported agents to the native Anthropic Messages API through OpenShell.
The provider uses the `anthropic-messages` protocol.

## Credential

Set `ANTHROPIC_API_KEY` in the host shell before onboarding.
NemoClaw keeps the credential on the host and uses provider-aware validation during retries.

## Model Choices

The onboarding wizard offers these curated model IDs.

* `claude-sonnet-4-6`.
* `claude-haiku-4-5`.
* `claude-opus-4-6`.

## Onboard

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

```bash
nemoclaw onboard
```

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

## Validation

NemoClaw uses provider-aware validation during credential retries.
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 Claude models by task fit.
* [Set Up an Anthropic-Compatible Endpoint](../custom-endpoints/set-up-anthropic-compatible-endpoint) covers custom gateways and proxies instead of the native Anthropic provider.
* [Understand Provider Validation](../validate-inference/understand-provider-validation) describes provider validation behavior.