> 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.

# Configure Model Limits

> Set the context-window and output-token limits baked into a NemoClaw-managed sandbox.

Configure model limits before onboarding so NemoClaw can bake them into the sandbox image.
Changing a build-time model limit on an existing sandbox requires fresh recreation.

## Set OpenClaw Limits

## Set the Hermes Context Window

Hermes accepts `NEMOCLAW_CONTEXT_WINDOW` as its model-limit override.

| Variable                  | Values                     | Default                      |
| ------------------------- | -------------------------- | ---------------------------- |
| `NEMOCLAW_CONTEXT_WINDOW` | Positive integer in tokens | Unset so Hermes auto-detects |

```bash
export NEMOCLAW_CONTEXT_WINDOW=65536
nemohermes onboard
```

When onboarding resolves a valid value, NemoClaw writes it as `model.context_length` in `/sandbox/.hermes/config.yaml`.
If no explicit or probed value is available, the field remains unset so Hermes can auto-detect it from the endpoint.

## Use Detected Local Limits

When `NEMOCLAW_CONTEXT_WINDOW` is unset, NemoClaw can use a context length reported by the selected local server.
Local Ollama reports the loaded model's runtime context length.
Local vLLM and OpenAI-compatible endpoints can report `max_model_len` through `/v1/models`.

Set `NEMOCLAW_CONTEXT_WINDOW` when you need to override the detected value.

## Recreate an Existing Sandbox

Model limits are build-time settings.
Recreate the named sandbox after changing a supported value.

```bash
nemohermes onboard --fresh --name <sandbox-name> --recreate-sandbox
```

## Related Topics

* [Configure Inference Timeouts](configure-inference-timeouts) for request, validation, and readiness budgets.
* [Switch Models](switch-models) to change the model without changing model limits.