[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-08-18 UTC."],[],[],null,["# Undeploy a model and delete the endpoint\n\nUse one of the following methods to undeploy a model and delete the endpoint.\n**Note:** You can only delete the endpoint after all models have been undeployed from it. \n\n### Google Cloud console\n\n1. Undeploy the model as follows:\n\n 1. In the Google Cloud console, in the Vertex AI section, go\n to the **Endpoints** page.\n\n [Go to the Endpoints page](https://console.cloud.google.com/vertex-ai/endpoints)\n 2. Click the name and version ID of the model you want to undeploy to open\n its details page.\n\n 3. On the row for your model, click more_vert\n **Actions** , and then click **Undeploy model from endpoint**.\n\n 4. In the **Undeploy model from endpoint** dialog, click **Undeploy**.\n\n 5. To delete additional models, repeat the preceding steps.\n\n2. Optional: Delete the online inference endpoint as follows:\n\n 1. In the Google Cloud console, in the **Vertex AI** section,\n go to the **Online prediction** page.\n\n [Go to Online prediction](https://console.cloud.google.com/vertex-ai/online-prediction/endpoints)\n 2. Select the endpoint.\n\n 3. To delete the endpoint, click more_vert\n **Actions** , and then click **Delete endpoint**.\n\n### gcloud\n\n1. List the endpoint IDs for all endpoints in your project:\n\n gcloud ai endpoints list \\\n --project=\u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e \\\n --region=\u003cvar translate=\"no\"\u003eLOCATION_ID\u003c/var\u003e\n\n Replace \u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e with your project name and\n \u003cvar translate=\"no\"\u003eLOCATION_ID\u003c/var\u003e with the region where you are using\n Vertex AI.\n2. List the model IDs for the models that are deployed to an endpoint:\n\n gcloud ai endpoints describe \u003cvar translate=\"no\"\u003eENDPOINT_ID\u003c/var\u003e \\\n --project=\u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e \\\n --region=\u003cvar translate=\"no\"\u003eLOCATION_ID\u003c/var\u003e\n\n Replace \u003cvar translate=\"no\"\u003eENDPOINT_ID\u003c/var\u003e with the endpoint ID.\n3. Undeploy a model from the endpoint:\n\n gcloud ai endpoints undeploy-model \u003cvar translate=\"no\"\u003eENDPOINT_ID\u003c/var\u003e \\\n --project=\u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e \\\n --region=\u003cvar translate=\"no\"\u003eLOCATION_ID\u003c/var\u003e \\\n --deployed-model-id=\u003cvar translate=\"no\"\u003eDEPLOYED_MODEL_ID\u003c/var\u003e\n\n Replace \u003cvar translate=\"no\"\u003eDEPLOYED_MODEL_ID\u003c/var\u003e with the model ID.\n4. Optional: Delete the online inference endpoint:\n\n gcloud ai endpoints delete \u003cvar translate=\"no\"\u003eENDPOINT_ID\u003c/var\u003e \\\n --project=\u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e \\\n --region=\u003cvar translate=\"no\"\u003eLOCATION_ID\u003c/var\u003e"]]
