Skip to main content
Send synthetic observations to the DROID policy and inspect its first action chunk.

Install the reference client

New to Reactor? How the API works explains the session, camera streams, commands, and action messages used below. You need Python 3.12, uv, a Reactor API key, and Reactor’s public cookbook. The client code is public; your Reactor account still needs access to the selected hosted model. No local model weights or GPU are required for this example.
Run the example below from robotics/sim/notebooks/. This environment installs the Python SDK (reactor-sdk, imported as reactor_sdk) and the reactor_robotics helper directory in Reactor’s public cookbook. The helpers provide camera publishing and message queues; they are separate from the SDK. Keep your API key in the environment. On Linux, the published glibc wheel requires glibc 2.34 or newer. The default endpoint is https://api.reactor.inc; REACTOR_API_URL overrides it. Examples select a model by slug, not a frozen release; check its release notes when the deployed contract changes. If setup or connection fails, see first-run troubleshooting.

Request a chunk

Run the cookbook example from the current robotics/sim/notebooks/ directory:
Expect actions: (32, 8) and eight values for the first step. The synthetic images and sample state check connectivity and reply shape; do not execute these outputs on hardware. Sampling is unseeded, so values can differ between runs. The printed time excludes connection setup and the 200 ms frame-delivery wait. It is not total observation-to-action latency. The helper retains replies that arrive while the state command is being acknowledged. Next, run in simulation or use the integration guide.