> ## 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.

# Model API Reference

> Per-model commands, events, and behavior for every model on Reactor

<Frame>
  <img src="https://mintcdn.com/reactortechnologiesinc/5kBYC6Bj7pWy1ZwU/images/rea-096.webp?fit=max&auto=format&n=5kBYC6Bj7pWy1ZwU&q=85&s=abd61a46c877bbb3c603914266ca6cc5" alt="A weathered stone gateway arching over a dirt track through misty highlands" width="1280" height="768" data-path="images/rea-096.webp" />
</Frame>

The Model API Reference is the source of truth for what each model accepts and emits: every command,
every parameter, every event.

This is distinct from the [SDK Reference](/sdk-reference/using-the-sdk), which documents the JavaScript
and Python client libraries (sessions, connect/disconnect, file uploads, raw event sending).
Learning how to use Reactor is one thing; learning how to drive a specific model is another. For
background on what a Reactor model is, see [What is a Reactor model?](/models/overview).

<Note>
  For the initial release, each model's reference is hand-written here. Longer term, these pages
  will be generated automatically from each model's published schema so they stay in lockstep with
  what's deployed.
</Note>

## Available models

<CardGroup cols={3}>
  <Card title="Helios" icon="sun" href="/model-api-reference/helios/overview">
    Interactive real-time video generation with autoregressive chunked diffusion and image-to-video
    support.
  </Card>

  <Card title="LingBot" icon="gamepad-2" href="/model-api-reference/lingbot/overview">
    Real-time navigable video model with WASD movement, look controls, and live prompt steering.
  </Card>

  <Card title="LingBot World 2" icon="joystick" href="/model-api-reference/lingbot-world-2/overview">
    Image-anchored navigable world model with two-axis WASD driving, directed camera moves, and
    live prompt steering.
  </Card>

  <Card title="LongLive-2.0" icon="clapperboard" href="/model-api-reference/longlive-v2/overview">
    Autoregressive multi-shot video generation: direct a sequence with soft shots and hard cuts,
    live or scheduled.
  </Card>

  <Card title="SANA-Streaming" icon="radio" href="/model-api-reference/sana-streaming/overview">
    Real-time streaming video editing: surgical text-driven edits to uploaded clips or a live
    webcam feed.
  </Card>
</CardGroup>

Each per-model page combines the overview, schema, prompt guide, and tutorial in a single document.

## What you'll find per model

* Every command the model accepts, with parameter types and constraints
* Every event the model emits, with payload shapes
* Track capabilities (which media streams are publishable or receivable)
* Any model-specific preconditions or ordering rules

## Working without a typed SDK

If a model doesn't have a typed SDK published yet, or you're prototyping against a model in
development, drive it from the base [`Reactor`](/sdk-reference/reactor-class) class using
`sendCommand()` and raw event payloads. The Model API Reference tells you exactly what those
payloads should look like.
