diff --git a/src/bentoml/_internal/cloud/bento.py b/src/bentoml/_internal/cloud/bento.py
index e45cf053e4e..f24018900b4 100644
--- a/src/bentoml/_internal/cloud/bento.py
+++ b/src/bentoml/_internal/cloud/bento.py
@@ -562,6 +562,19 @@ def list(self) -> BentoWithRepositoryListSchema:
         ]
         return res
 
+    def delete(self, name: str, version: str) -> None:
+        """Delete a bento from the remote bento store
+
+        Args:
+            name: The name of the bento repository
+            version: The version of the bento to delete
+        """
+        rest_client = self._client
+        res = rest_client.v1.get_bento(bento_repository_name=name, version=version)
+        if res is None:
+            raise NotFound(f'Bento "{name}:{version}" not found on remote')
+        rest_client.v1.delete_bento(bento_repository_name=name, version=version)
+
     def get(self, name: str, version: str | None) -> BentoSchema:
         """Get a bento by name and version
 
diff --git a/src/bentoml/_internal/cloud/client.py b/src/bentoml/_internal/cloud/client.py
index 77dad1136af..1fba7a4a5f3 100644
--- a/src/bentoml/_internal/cloud/client.py
+++ b/src/bentoml/_internal/cloud/client.py
@@ -231,6 +231,11 @@ def finish_upload_bento(
         self._check_resp(resp)
         return schema_from_object(resp.json(), BentoSchema)
 
+    def delete_bento(self, bento_repository_name: str, version: str) -> None:
+        url = f"/api/v1/bento_repositories/{bento_repository_name}/bentos/{version}"
+        resp = self.session.delete(url)
+        self._check_resp(resp)
+
     def upload_bento(
         self, bento_repository_name: str, version: str, data: t.IO[bytes]
     ) -> None:
diff --git a/src/bentoml/bentos.py b/src/bentoml/bentos.py
index fa46a72d9ab..2621fa3774d 100644
--- a/src/bentoml/bentos.py
+++ b/src/bentoml/bentos.py
@@ -76,9 +76,19 @@ def get(
 def delete(
     tag: Tag | str,
     *,
+    cloud: bool = False,
     _bento_store: BentoStore = Provide[BentoMLContainer.bento_store],
+    _cloud_client: BentoCloudClient = Provide[BentoMLContainer.bentocloud_client],
 ):
-    _bento_store.delete(tag)
+    if cloud:
+        _tag = Tag.from_taglike(tag)
+        if _tag.version is None:
+            raise BentoMLException(
+                f'Bento version is required for cloud deletion. Please specify a version, e.g. "{_tag.name}:<version>"'
+            )
+        _cloud_client.bento.delete(_tag.name, _tag.version)
+    else:
+        _bento_store.delete(tag)
 
 
 @inject
diff --git a/src/bentoml_cli/bentos.py b/src/bentoml_cli/bentos.py
index 6090b058719..eb62af42ee8 100644
--- a/src/bentoml_cli/bentos.py
+++ b/src/bentoml_cli/bentos.py
@@ -220,13 +220,21 @@ def list_bentos(
         is_flag=True,
         help="Skip confirmation when deleting a specific bento bundle",
     )
+    @click.option(
+        "--cloud",
+        is_flag=True,
+        default=False,
+        help="Delete Bento from BentoCloud remote server",
+    )
     @inject
     def delete(
         delete_targets: list[str],
         yes: bool,
+        cloud: bool,
         bento_store: BentoStore = Provide[BentoMLContainer.bento_store],
+        cloud_client: BentoCloudClient = Provide[BentoMLContainer.bentocloud_client],
     ) -> None:  # type: ignore (not accessed)
-        """Delete Bento in local bento store.
+        """Delete Bento in local bento store or from BentoCloud.
 
         \b
         Examples:
@@ -235,25 +243,37 @@ def delete(
             * Bulk delete multiple bento bundles by name and version, separated by ",", e.g.: `bentoml delete Irisclassifier:v1,MyPredictService:v2`
             * Bulk delete multiple bento bundles by name and version, separated by " ", e.g.: `bentoml delete Irisclassifier:v1 MyPredictService:v2`
             * Bulk delete without confirmation, e.g.: `bentoml delete IrisClassifier --yes`
+            * Delete from BentoCloud, e.g.: `bentoml delete IrisClassifier:v1 --cloud`
         """
 
         def delete_target(target: str) -> None:
             tag = Tag.from_str(target)
 
-            if tag.version is None:
-                to_delete_bentos = bento_store.list(target)
+            if cloud:
+                if tag.version is None:
+                    raise click.BadParameter(
+                        f'Deleting all versions is not supported for cloud bentos. Please specify a version, e.g. "{tag.name}:<version>"'
+                    )
+                if not yes:
+                    if not click.confirm(f"delete bento {tag} from BentoCloud?"):
+                        return
+                cloud_client.bento.delete(tag.name, tag.version)
+                rich.print(f"Bento {tag} deleted from BentoCloud.")
             else:
-                to_delete_bentos = [bento_store.get(tag)]
-
-            for bento in to_delete_bentos:
-                if yes:
-                    delete_confirmed = True
+                if tag.version is None:
+                    to_delete_bentos = bento_store.list(target)
                 else:
-                    delete_confirmed = click.confirm(f"delete bento {bento.tag}?")
+                    to_delete_bentos = [bento_store.get(tag)]
+
+                for bento in to_delete_bentos:
+                    if yes:
+                        delete_confirmed = True
+                    else:
+                        delete_confirmed = click.confirm(f"delete bento {bento.tag}?")
 
-                if delete_confirmed:
-                    bento_store.delete(bento.tag)
-                    rich.print(f"{bento} deleted.")
+                    if delete_confirmed:
+                        bento_store.delete(bento.tag)
+                        rich.print(f"{bento} deleted.")
 
         for target in delete_targets:
             delete_target(target)