> ## Documentation Index > Fetch the complete documentation index at: https://docs.tensormesh.ai/llms.txt > Use this file to discover all available pages before exploring further. # Deploy Model > Provisions a model after billing checks and forwards to ModelService. ## OpenAPI ````yaml /tensormesh-api/specs/billing/v1/billing_model_service.openapi.json post /v1/models openapi: 3.0.3 info: title: Tensormesh Control Plane API (billing/v1/billing_model_service) version: 0.1.0 description: >- Authentication: Authorization: Bearer (obtain via tm auth login). servers: - url: https://api.tensormesh.ai security: - BearerAuth: [] tags: - name: BillingModelService paths: /v1/models: post: tags: - BillingModelService summary: Deploy Model description: Provisions a model after billing checks and forwards to ModelService. operationId: BillingModelService_DeployModel requestBody: content: application/json: schema: $ref: '#/components/schemas/v1DeployModelRequest' required: true responses: '200': description: A successful response. content: application/json: schema: $ref: '#/components/schemas/v1DeployModelResponse' default: description: An unexpected error response. content: application/json: schema: $ref: '#/components/schemas/rpcStatus' components: schemas: v1DeployModelRequest: type: object properties: modelName: type: string description: Model nick name. Must be unique per user. userId: type: string description: User ID who owns this model. Must be a valid UUID. description: type: string description: Optional description of the model. infra: $ref: '#/components/schemas/v1Infra' modelPath: type: string description: Model path (e.g., HuggingFace model ID). gpuCount: type: integer format: int64 description: Number of GPUs to allocate for this model. gpuType: $ref: '#/components/schemas/v1GPUType' modelSpec: type: object description: Additional model-specific configuration. apiKey: type: string title: User api key optional hfToken: type: string title: User HF token optional kvCacheEnabled: type: boolean description: Enable KV cache. cpuOffloadingEnabled: type: boolean description: Enable CPU offloading. nodeId: type: string title: Node ID optional v1DeployModelResponse: type: object properties: model: $ref: '#/components/schemas/v1Model' rpcStatus: type: object properties: code: type: integer format: int32 description: |- The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. message: type: string description: >- A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. details: type: array items: $ref: '#/components/schemas/protobufAny' description: >- A list of messages that carry the error details. There is a common set of message types for APIs to use. description: >- The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). v1Infra: type: object properties: cloudProvider: $ref: '#/components/schemas/v1CloudProvider' nebiusRegion: $ref: '#/components/schemas/v1NebiusRegion' lambdaRegion: $ref: '#/components/schemas/v1LambdaRegion' onpremRegion: type: string description: >- Infra specifies the infrastructure configuration for deploying and running models. This message defines where a model deployment should run by specifying both the cloud provider and the specific region. It uses a oneof for region selection to ensure type-safe region specification based on the chosen provider. See also: tensormesh/common/v1/cloud_provider.proto for provider and region enum definitions v1GPUType: type: string enum: - GPU_TYPE_UNSPECIFIED - GPU_TYPE_A100 - GPU_TYPE_H100 - GPU_TYPE_H200 - GPU_TYPE_B200 default: GPU_TYPE_UNSPECIFIED description: >- GPUType specifies the type of GPU to use for a model deployment. This enum defines the supported GPU types for model deployments. It allows clients to specify the exact GPU hardware they need for their models. enum definitions v1Model: type: object properties: modelId: type: string title: unique identifier for the model instance deploymentId: type: string title: deployment id associated with the model userId: type: string description: User ID who owns this deployment. description: type: string description: Description of the deployment. modelPath: type: string description: Model path. modelName: type: string description: Display the nick name for the model. status: $ref: '#/components/schemas/v1ModelStatus' events: type: array items: $ref: '#/components/schemas/v1ModelEvent' description: List of events that occurred during deployment lifecycle. createdAt: type: string format: date-time description: Timestamp when the model was created. updatedAt: type: string format: date-time description: Timestamp when the model was last updated. modelSpec: type: object title: model specification infra: $ref: '#/components/schemas/v1Infra' gpuCount: type: integer format: int64 description: Number of GPUs allocated for this model. gpuType: $ref: '#/components/schemas/v1GPUType' replicas: type: integer format: int64 title: Number of replicas for this model endpoint: type: string title: endpoint to connect with this model apiKey: type: string title: api key used for authorizing the request to this model description: Model represents a model instance created by user. protobufAny: type: object properties: '@type': type: string description: >- A URL/resource name that uniquely identifies the type of the serialized protocol buffer message. This string must contain at least one "/" character. The last segment of the URL's path must represent the fully qualified name of the type (as in `path/google.protobuf.Duration`). The name should be in a canonical form (e.g., leading "." is not accepted). In practice, teams usually precompile into the binary all types that they expect it to use in the context of Any. However, for URLs which use the scheme `http`, `https`, or no scheme, one can optionally set up a type server that maps type URLs to message definitions as follows: * If no scheme is provided, `https` is assumed. * An HTTP GET on the URL must yield a [google.protobuf.Type][] value in binary format, or produce an error. * Applications are allowed to cache lookup results based on the URL, or have them precompiled into a binary to avoid any lookup. Therefore, binary compatibility needs to be preserved on changes to types. (Use versioned type names to manage breaking changes.) Note: this functionality is not currently available in the official protobuf release, and it is not used for type URLs beginning with type.googleapis.com. As of May 2023, there are no widely used type server implementations and no plans to implement one. Schemes other than `http`, `https` (or the empty scheme) might be used with implementation specific semantics. additionalProperties: {} description: >- `Any` contains an arbitrary serialized protocol buffer message along with a URL that describes the type of the serialized message. Protobuf library provides support to pack/unpack Any values in the form of utility functions or additional generated methods of the Any type. Example 1: Pack and unpack a message in C++. Foo foo = ...; Any any; any.PackFrom(foo); ... if (any.UnpackTo(&foo)) { ... } Example 2: Pack and unpack a message in Java. Foo foo = ...; Any any = Any.pack(foo); ... if (any.is(Foo.class)) { foo = any.unpack(Foo.class); } // or ... if (any.isSameTypeAs(Foo.getDefaultInstance())) { foo = any.unpack(Foo.getDefaultInstance()); } Example 3: Pack and unpack a message in Python. foo = Foo(...) any = Any() any.Pack(foo) ... if any.Is(Foo.DESCRIPTOR): any.Unpack(foo) ... Example 4: Pack and unpack a message in Go foo := &pb.Foo{...} any, err := anypb.New(foo) if err != nil { ... } ... foo := &pb.Foo{} if err := any.UnmarshalTo(foo); err != nil { ... } The pack methods provided by protobuf library will by default use 'type.googleapis.com/full.type.name' as the type URL and the unpack methods only use the fully qualified type name after the last '/' in the type URL, for example "foo.bar.com/x/y.z" will yield type name "y.z". JSON ==== The JSON representation of an `Any` value uses the regular representation of the deserialized, embedded message, with an additional field `@type` which contains the type URL. Example: package google.profile; message Person { string first_name = 1; string last_name = 2; } { "@type": "type.googleapis.com/google.profile.Person", "firstName": , "lastName": } If the embedded message type is well-known and has a custom JSON representation, that representation will be embedded adding a field `value` which holds the custom JSON in addition to the `@type` field. Example (for message [google.protobuf.Duration][]): { "@type": "type.googleapis.com/google.protobuf.Duration", "value": "1.212s" } v1CloudProvider: type: string enum: - CLOUD_PROVIDER_UNSPECIFIED - CLOUD_PROVIDER_ONPREM - CLOUD_PROVIDER_NEBIUS - CLOUD_PROVIDER_LAMBDA - CLOUD_PROVIDER_YOTTA default: CLOUD_PROVIDER_UNSPECIFIED description: >- CloudProvider specifies which cloud infrastructure provider to use for deployment. Currently supported providers: - On-premise infrastructure (self-hosted) - Nebius (https://nebius.com) - European and US cloud GPU provider - Lambda Labs (https://lambdalabs.com) - US-based GPU cloud provider - Yotta provider v1NebiusRegion: type: string enum: - NEBIUS_REGION_UNSPECIFIED - NEBIUS_REGION_EU_NORTH_1 - NEBIUS_REGION_EU_WEST_1 - NEBIUS_REGION_US_CENTRAL_1 default: NEBIUS_REGION_UNSPECIFIED description: >- NebiusRegion specifies the geographic region for Nebius cloud deployments. v1LambdaRegion: type: string enum: - LAMBDA_REGION_UNSPECIFIED - LAMBDA_REGION_US_SOUTH_1 - LAMBDA_REGION_US_SOUTH_2 - LAMBDA_REGION_US_SOUTH_3 - LAMBDA_REGION_EAST_1 - LAMBDA_REGION_MIDWEST_1 default: LAMBDA_REGION_UNSPECIFIED description: |- LambdaRegion specifies the geographic region for Lambda Labs cloud deployments. v1ModelStatus: type: string enum: - MODEL_STATUS_UNSPECIFIED - MODEL_STATUS_INIT - MODEL_STATUS_UP - MODEL_STATUS_FAILED - MODEL_STATUS_DELETED default: MODEL_STATUS_UNSPECIFIED v1ModelEvent: type: object properties: createdAt: type: string format: date-time description: Timestamp when the event occurred. log: type: string description: Log message associated with the event. eventType: $ref: '#/components/schemas/v1EventType' description: ModelEvent represents a single event in the model lifecycle. v1EventType: type: string enum: - EVENT_TYPE_UNSPECIFIED - EVENT_TYPE_ERROR - EVENT_TYPE_INFO default: EVENT_TYPE_UNSPECIFIED description: |- EventType categorizes model events. - EVENT_TYPE_UNSPECIFIED: Unspecified event type. - EVENT_TYPE_ERROR: Error event. - EVENT_TYPE_INFO: Informational event. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- Bearer authentication using an access token. Format: Bearer ````