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

> ## Agent Instructions
> To build and serve your own model, start at /deploy/development/quickstart and /deploy/development/overview. Deploying is the default path: reactor init scaffolds a workspace, reactor auth login authenticates, and reactor model deploy registers the model, publishes the release with the weights/ folder, and activates it on Reactor's GPUs, in one command from that workspace. Docker must be running, because the publish step builds the image locally. Bump model.version in reactor.yaml before redeploying a change, because a release that already has an image is reactivated as it is. Deployment access is granted per account, so contact team@reactor.inc if a deploy is refused. Every key in reactor.yaml is documented at /deploy/platform/reactor-yaml. Model code imports reactor_runtime; Python client code imports reactor_sdk. The runtime overview explains the model interface. Running the model on your own machine with reactor run is optional and needs a GPU you attach with --gpus; /deploy/development/local-testing covers that loop and pairs a complete brightness model with a Python client test in a separate brightness-test workspace.
> Reactor hosts multiple models, each with its own connect slug (modelName) and command/event schema. The catalog of every model — slug, typed SDK package, and links to its schema — is at /model-api-reference/overview. Some models expose one slug per experience (e.g. HappyOyster); always take the slug from the model's own pages, never guess it.
> Fastest path to a working app: `npx create-reactor-app my-app --model=<slug>` scaffolds a complete app with secure auth wired up. Typed TypeScript SDKs are published as @reactor-models/<model>; Python uses the base reactor-sdk package.
> Auth: exchange an API key (rk_...) for a JWT via POST https://api.reactor.inc/tokens from your server. Never put the API key in client-side code.
> Append .md to any docs URL for clean Markdown. Search these docs via the MCP server at https://docs.reactor.inc/mcp.

# InputFrame

> One frame that arrived from a client.

One frame that arrived from a client.

```python Definition theme={"theme":{"light":"github-light","dark":"github-dark-high-contrast"}}
@dataclass
class InputFrame:
    data: npt.NDArray[Any]
    pts: float | None = None
    metadata: bytes | None = None
    capture_time_us: int | None = None
```

<ResponseField name="data" type="NDArray">
  The payload. Video is `(height, width, 3)` `uint8` RGB; audio is `(1, samples)` `int16` mono at
  48 kHz.
</ResponseField>

<ResponseField name="pts" type="float | None">
  Presentation timestamp in seconds, or `None` when the sender supplied none.
</ResponseField>

<ResponseField name="metadata" type="bytes | None">
  The bytes the sender attached to this frame, or `None`. The transport treats them as opaque, so
  decoding them is yours.
</ResponseField>

<ResponseField name="capture_time_us" type="int | None">
  When the sender captured the frame, in microseconds, or `None`. This reads the sender's clock,
  not yours, so compare two of them with each other rather than against local time.
</ResponseField>