> ## 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=` scaffolds a complete app with secure auth wired up. Typed TypeScript SDKs are published as @reactor-models/; 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. # Replace a model's settings > Replaces every mutable field of a model you own. **This is a full replace, not a patch:** a field you omit is written as its zero value or default. Read the model first and send back every field you want to keep. The one exception is `is_public`, which keeps its current value when omitted. To change one field without touching the others, use `PATCH /models/{id}`. Callable by an `account_admin` or `developer` of the owning account when model serving is enabled for the account. The CLI equivalent is `reactor model update`. `model.name`, `name`, `status`, and `display_name` must not appear in the body. To rename a model, delete it and register a new one. A customer cannot change `is_public` from `false` to `true`. A change to the GPU shape, extra arguments, or resources of a deployed model updates its `production` environment and rolls its instances; a GPU shape change is checked against your account's accelerator allocation. A body without `workers` makes the model one session per instance. ## OpenAPI ````yaml /openapi.yaml put /models/{id} openapi: 3.1.0 info: title: Reactor Platform API version: '1' description: > The Reactor Platform API mints session tokens, starts and operates sessions, negotiates media transport, and manages your account, models, and deployments. Every path is relative to `https://api.reactor.inc`. See the [Introduction](/platform-api/introduction) and [Authentication](/platform-api/authentication) pages for credentials, versioning, and errors. contact: name: Reactor support url: https://docs.reactor.inc/resources/support servers: - url: https://api.reactor.inc description: Production security: - apiKey: [] tags: - name: Status description: >- Public, unauthenticated endpoints for service health, pricing, and the values the API accepts. - name: Tokens description: > Exchange a long-lived API key for a short-lived, session-scoped token that a client can use to create and operate sessions without holding the key. - name: Users description: > Read your own user record, your account's roster, and account memberships, and manage member roles as an account admin. - name: API Keys description: >- Revoke API keys. Use the [Dashboard](https://reactor.inc/dashboard) to list or create keys. The CLI can also create a key with `reactor auth login`. - name: Sessions description: > Create, inspect, and end sessions. A session holds one running model for one client application; media and messages flow over a transport you attach to it afterwards. - name: Transport description: > Attach a client to a session. WebRTC signaling carries ICE servers, SDP, and ICE candidates; a LiveKit room connection lets the session join a room you host. - name: Files description: > Upload files a model reads, either for one running session or ahead of time for sessions you have not started yet. - name: Recordings description: > Fetch the recorded video of a session as an HLS playlist, during the session or after it ends. - name: Accounts description: > Read and manage the account your credential acts in: its name and slug, its credit balance, its effective quotas, and its accelerator capacity. - name: Invitations description: > Invite people to your account by email, and manage pending invitations. The recipient accepts from the emailed link while signed in to the dashboard. - name: Usage description: > List the sessions your account has run, filter them by status, date, model, or API key, and read exact session totals for a date window. - name: Models description: > Register, read, update, and delete the models your account serves, and list the models you can use. The `reactor model` CLI commands are built on these endpoints. - name: Releases description: > Register a model's versioned releases, push their container image, and deploy a release with a per-region instance plan. - name: Model Weights description: > Upload and inspect the weights bundle of a release: single-request uploads, multipart uploads for large files, and the server-side finalize that marks a bundle complete. - name: Model Schemas description: > Attach an OpenAPI schema to a release that describes the model's commands, messages, and tracks. Schemas of public models are readable without credentials. - name: Model Access description: | Share a private model with other accounts, one environment at a time. - name: Projects description: > A project is the deploy identity of a model you serve on Reactor. Each model is one project, with its own UUID. Creating a project also creates its `production` environment. - name: Environments description: > An environment is a named deploy target of a project, such as `production` or `staging`. Each write to an environment creates its next revision, and the newest revision is what the environment runs. Environment access grants let another account start sessions on one environment. - name: Revisions description: > A revision is an immutable, numbered snapshot of one environment: its model image, weights, resources, instances, and variables. An environment's revisions, newest first, are its change log. - name: Images description: > Model images are the container images pushed to your model's repository, named by digest. Experimental: this API can change without notice. - name: Weight Sets description: > A weight set is a version-2 weights bundle, named by its set digest. Push the files, then put the manifest. Available when weight sets are enabled for your account. Experimental: this API can change without notice. - name: Tags description: > A tag is a movable name on one model image or one weight set of a project. A release of the model is a read-only tag. Experimental: this API can change without notice. paths: /models/{id}: parameters: - $ref: '#/components/parameters/ModelId' put: tags: - Models summary: Replace a model's settings description: > Replaces every mutable field of a model you own. **This is a full replace, not a patch:** a field you omit is written as its zero value or default. Read the model first and send back every field you want to keep. The one exception is `is_public`, which keeps its current value when omitted. To change one field without touching the others, use `PATCH /models/{id}`. Callable by an `account_admin` or `developer` of the owning account when model serving is enabled for the account. The CLI equivalent is `reactor model update`. `model.name`, `name`, `status`, and `display_name` must not appear in the body. To rename a model, delete it and register a new one. A customer cannot change `is_public` from `false` to `true`. A change to the GPU shape, extra arguments, or resources of a deployed model updates its `production` environment and rolls its instances; a GPU shape change is checked against your account's accelerator allocation. A body without `workers` makes the model one session per instance. operationId: updateModel requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ModelUpdateRequest' example: description: Real-time video model, v2 is_gpu: true gpu_type: NVIDIA_H100 gpu_count: 2 extra_args: - '--batch-size' - '8' responses: '200': description: The updated model, without `project_id`. content: application/json: schema: $ref: '#/components/schemas/ModelDetail' example: id: 7b3f1bc2-a4e5-4d78-b9c1-0e6c2f9a1d34 account_id: 8c8b7e12-a4c1-4627-b0a0-5d2e9f3a7b61 account: Your Org name: your-org/your-model description: Real-time video model, v2 status: active is_public: false is_gpu: true gpu_type: NVIDIA_H100 gpu_count: 2 extra_args: - '--batch-size' - '8' created_at: '2025-05-11T21:46:40Z' updated_at: '2025-05-11T22:46:40Z' '400': description: > The body is invalid: an immutable field is present, `gpu_type` is unknown or missing with `is_gpu: true`, `gpu_count` is invalid for the type, a resource quantity is malformed, or `workers` breaks a rule. content: application/json: schema: $ref: '#/components/schemas/Error' '401': $ref: '#/components/responses/Unauthorized' '403': description: > You do not own the model (returned whether or not it exists), model serving is not enabled for your account, or the body sets `is_public: true` on a private model. content: application/json: schema: $ref: '#/components/schemas/Error' '409': description: > The GPU shape change cannot be applied. `error` is `accelerator_quota_exceeded` (the deployed instances would exceed your account's allocation at the new shape), or `failed_precondition` with `reason` `accelerators_required` (a GPU model has no `gpu_type`; send one). Nothing is saved. content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: The CPU or memory request exceeds your account's per-model quota. content: application/json: schema: $ref: '#/components/schemas/Error' '503': $ref: '#/components/responses/ServiceUnavailable' components: parameters: ModelId: name: id in: path required: true description: >- The model's ID (not its project ID). Find it with `GET /models?name=your-org/your-model`. schema: type: string format: uuid schemas: ModelUpdateRequest: type: object description: > Every mutable field. Omitted fields are reset to their zero value or default, except `is_public`. Must not contain `model.name`, `name`, `status`, or `display_name`. properties: description: type: string is_public: type: boolean description: >- Omit to keep the current value. A customer may only send `false`, or `true` on an already-public model. is_gpu: type: boolean gpu_type: type: string example: NVIDIA_H100 gpu_count: type: integer minimum: 0 extra_args: type: array items: type: string cpu_request: type: string cpu_limit: type: string memory_request: type: string memory_limit: type: string workers: $ref: '#/components/schemas/ModelWorkers' ModelDetail: type: object description: The full view of a model, for its owner. required: - id - name - status - is_public - is_gpu - created_at - updated_at properties: id: type: string format: uuid account_id: type: string format: uuid description: The owning account. account: type: string description: The owning account's name. name: type: string example: your-org/your-model description: type: string status: $ref: '#/components/schemas/ModelStatus' is_public: type: boolean is_gpu: type: boolean gpu_type: type: string example: NVIDIA_H100 gpu_count: type: integer extra_args: type: array items: type: string cpu_request: type: string example: '4' cpu_limit: type: string memory_request: type: string example: 32Gi memory_limit: type: string workers: $ref: '#/components/schemas/ModelWorkers' pod_total: type: object readOnly: true description: > For a model with `workers`: the CPU and memory of one whole instance, with defaults filled in. This is what your account's per-model quotas are checked against. properties: cpu: $ref: '#/components/schemas/ModelQuantityPair' memory: $ref: '#/components/schemas/ModelQuantityPair' created_at: type: string format: date-time description: When it was created, as an RFC 3339 timestamp. example: '2026-01-15T10:30:00Z' updated_at: type: string format: date-time description: When it was last updated, as an RFC 3339 timestamp. example: '2026-01-15T10:30:00Z' project_id: type: string format: uuid description: The model's project. Only on `GET /models/{id}`. Error: type: object required: - error properties: error: type: string description: >- A stable error code (for example `not_found`) on newer routes, or a sentence on older ones. When `message` is present, branch on `error`. message: type: string description: >- A human-readable explanation. Do not parse it; its wording may change. resource: type: string description: The type of the resource a `not_found` refers to. reason: type: string description: >- A more specific cause for `failed_precondition`, `aborted`, and some `invalid_request` errors. ModelWorkers: type: object description: > Makes the model multi-session: each instance runs one model server, which holds the model and the GPUs, plus `count` workers, each serving one session. The model's own `gpu_*`, `cpu_*`, and `memory_*` fields apply to the model server. Omit `workers` for one session per instance. The CLI sends this from `model.resources.workers` in `reactor.yaml`. required: - count properties: count: type: integer minimum: 1 maximum: 64 description: Workers per instance. cpu: allOf: - $ref: '#/components/schemas/ModelQuantityPair' description: CPU of each worker. Defaults to `500m` request and `2000m` limit. memory: allOf: - $ref: '#/components/schemas/ModelQuantityPair' description: >- Memory of each worker. Defaults to `1Gi` request and `4Gi` limit. The limit must hold 2 × `shared_memory.input`. shared_memory: type: object description: >- Sizes of each worker's input and output blocks, in whole bytes (`1Mi`, `25165824`). One worker's blocks (2 × input + output) may hold at most 16 GiB. properties: input: type: string description: Defaults to 1 MiB. example: 1Mi output: type: string description: Defaults to 32 MiB. example: 24Mi ModelStatus: type: string enum: - active - deprecated - disabled description: The model's status, always lowercase in responses. ModelQuantityPair: type: object properties: request: type: string description: A resource quantity such as `500m` or `2Gi`. limit: type: string description: A resource quantity such as `2000m` or `4Gi`. responses: Unauthorized: description: The credential is missing, invalid, or expired. content: application/json: schema: $ref: '#/components/schemas/Error' ServiceUnavailable: description: A dependency is temporarily unavailable. Retry with backoff. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: apiKey: type: http scheme: bearer description: >- A Reactor API key (`rk_...`), sent as `Authorization: Bearer rk_...`. Keep it on a server. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.