Deploys a model. If a model is already deployed, deploying it has no effect. A model can only serve prediction requests after it gets deployed. For article suggestion, custom model will not be used unless it is deployed.
This method is a long-running operation. The returned Operation type has the following method-specific fields:
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-06-27 UTC."],[[["\u003cp\u003eThis document outlines the process for deploying a conversation model, which is necessary for the model to serve prediction requests, and has no effect if already deployed.\u003c/p\u003e\n"],["\u003cp\u003eDeploying a model involves a long-running operation that returns an \u003ccode\u003eOperation\u003c/code\u003e type with specific metadata and an empty response.\u003c/p\u003e\n"],["\u003cp\u003eThe HTTP request for deployment is a POST request to a specific endpoint, using the gRPC Transcoding syntax.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003ename\u003c/code\u003e parameter in the request is mandatory, specifying the conversation model to deploy in the format of \u003ccode\u003eprojects/<Project ID>/conversationModels/<Conversation Model ID>\u003c/code\u003e, and requires specific IAM permission.\u003c/p\u003e\n"],["\u003cp\u003eThe request body for deploying a model must be empty, while a successful deployment returns an instance of the \u003ccode\u003eOperation\u003c/code\u003e.\u003c/p\u003e\n"]]],[],null,["# Method: projects.conversationModels.deploy\n\n- [HTTP request](#body.HTTP_TEMPLATE)\n- [Path parameters](#body.PATH_PARAMETERS)\n- [Request body](#body.request_body)\n- [Response body](#body.response_body)\n- [Authorization scopes](#body.aspect)\n- [Try it!](#try-it)\n\nDeploys a model. If a model is already deployed, deploying it has no effect. A model can only serve prediction requests after it gets deployed. For article suggestion, custom model will not be used unless it is deployed.\n\nThis method is a [long-running operation](https://cloud.google.com/dialogflow/es/docs/how/long-running-operations). The returned `Operation` type has the following method-specific fields:\n\n- `metadata`: [DeployConversationModelOperationMetadata](/dialogflow/es/docs/reference/rest/v2/DeployConversationModelOperationMetadata)\n- `response`: An [Empty message](https://developers.google.com/protocol-buffers/docs/reference/google.protobuf#empty)\n\n### HTTP request\n\n`POST https://{endpoint}/v2/{name=projects/*/conversationModels/*}:deploy`\n\nWhere `{endpoint}` is one of the [supported service endpoints](/dialogflow/es/docs/reference/rest#rest_endpoints).\n\nThe URLs use [gRPC Transcoding](https://google.aip.dev/127) syntax.\n\n### Path parameters\n\n### Request body\n\nThe request body must be empty.\n\n### Response body\n\nIf successful, the response body contains an instance of [Operation](/dialogflow/es/docs/reference/rest/v2/projects.locations.operations#Operation).\n\n### Authorization scopes\n\nRequires one of the following OAuth scopes:\n\n- `https://www.googleapis.com/auth/cloud-platform`\n- `\n https://www.googleapis.com/auth/dialogflow`\n\nFor more information, see the [Authentication Overview](/docs/authentication#authorization-gcp)."]]
