> ## Documentation Index
> Fetch the complete documentation index at: https://docs.generalrobotics.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# rdt-1b

> Run RDT-1B policy inference on robot observations

Run RDT-1B policy inference on robot observations.

## Parameters

<ParamField body="current_rgb" type="ImageInput" required>
  Current camera frame as file path, URL, PIL Image, or numpy array.
</ParamField>

<ParamField body="proprio" type="Union[np.ndarray, list]" required>
  Robot joint state as numpy array or list (7 arm joints + gripper).
</ParamField>

<ParamField body="prompt" type="str" required>
  Natural-language task instruction string.
</ParamField>

<ParamField body="prev_rgb" type="Optional[ImageInput]">
  Previous camera frame, or None on the first call of an episode.
</ParamField>

<ParamField body="timeout" type="float | None">
  Optional timeout in seconds for the HTTP request.
</ParamField>

## Returns

Action dictionary containing:

* "actions": numpy array of shape (64, 8) with predicted actions

## Example

```python theme={null}
from grid_cortex_client import CortexClient, ModelType
client = CortexClient()
result = client.run(ModelType.RDT_1B, ...)
```