> ## 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 video model catalog — slug, typed SDK package, and links to its schema — is at /model-api-reference/overview. Robotics policy documentation starts at /robotics/overview; The launch policies are Cosmos Nano DROID (/robotics/cosmos/nano-policy-droid/), DreamZero DROID (/robotics/dreamzero/droid/), and FLUX Action DROID (/robotics/flux-action/droid/), organized by model family and embodiment. 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.

# Clip generation

> Generate a video clip with sound through the Reactor HTTP API.

Generate a video clip with sound from a prompt and optional reference media. Your server
submits an HTTP request, polls for completion, and downloads the finished files. You do not need to
connect a streaming client or manage media tracks.

## How it works

1. If your request uses reference files, upload them and save their `file_id` values.
2. Send the model name and its inputs to `POST /generations`.
3. Poll `GET /generations/{id}` until the status is `succeeded` or `failed`.
4. Download the video and supporting files before their signed URLs expire.

Use `https://api.reactor.inc` as the base URL.
Send your Reactor API key in `Authorization: Bearer rk_...` on API requests. Keep the key on your server. Signed upload and
download URLs do not need your API key.

## Supported models

Browse [Model APIs](https://docs.reactor.inc/model-api-reference/overview.md#available-models) to choose a model. Open its
**API reference** and go to **Generate a clip** for the HTTP request example and input limits.
Use an API key from an account that can run the selected model.

## Start building

> [card] [Quickstart](https://docs.reactor.inc/generations/quickstart)
>
> Generate and download your first clip with JavaScript or Python.

> [card] [API reference](https://docs.reactor.inc/generations/api-reference)
>
> Upload files, submit requests, poll results, and handle errors.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.