nemo-platform-plugin 0.1.0__py3-none-any.whl

nemo_platform/resources/inference/deployments/versions.py

@@ -0,0 +1,434 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import httpx
+
+from ...._types import Body, Query, Headers, NotGiven, not_given
+from ...._utils import path_template
+from ...._compat import cached_property
+from ...._resource import SyncAPIResource, AsyncAPIResource
+from ...._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ...._base_client import make_request_options
+from ....types.inference.model_deployment import ModelDeployment
+from ....types.inference.deployments.version_list_response import VersionListResponse
+
+__all__ = ["VersionsResource", "AsyncVersionsResource"]
+
+
+class VersionsResource(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> VersionsResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers
+        """
+        return VersionsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> VersionsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response
+        """
+        return VersionsResourceWithStreamingResponse(self)
+
+    def retrieve(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        deployment: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ModelDeployment:
+        """
+        Get a specific version of a ModelDeployment.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        if not deployment:
+            raise ValueError(f"Expected a non-empty value for `deployment` but received {deployment!r}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return self._get(
+            path_template(
+                "/apis/models/v2/workspaces/{workspace}/deployments/{deployment}/versions/{name}",
+                workspace=workspace,
+                deployment=deployment,
+                name=name,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelDeployment,
+        )
+
+    def list(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> VersionListResponse:
+        """
+        List all versions of a ModelDeployment.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return self._get(
+            path_template(
+                "/apis/models/v2/workspaces/{workspace}/deployments/{name}/versions", workspace=workspace, name=name
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=VersionListResponse,
+        )
+
+    def delete(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        deployment: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> object:
+        """
+        Delete a specific version of a ModelDeployment.
+
+        If the deployment is in any state other than DELETED, this will set its status
+        to DELETING. The models controller will then:
+
+        1. Delete the infrastructure (e.g., K8s NimService)
+        2. Update the status to DELETED
+
+        If the deployment is already in DELETED status, calling delete again will
+        permanently remove it from the database.
+
+        Returns:
+
+        - 202 Accepted: Deployment version marked for deletion (status set to DELETING)
+        - 204 No Content: Deployment version permanently removed from database (was
+          already DELETED)
+        - 404 Not Found: Deployment version doesn't exist
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        if not deployment:
+            raise ValueError(f"Expected a non-empty value for `deployment` but received {deployment!r}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return self._delete(
+            path_template(
+                "/apis/models/v2/workspaces/{workspace}/deployments/{deployment}/versions/{name}",
+                workspace=workspace,
+                deployment=deployment,
+                name=name,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=object,
+        )
+
+
+class AsyncVersionsResource(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncVersionsResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers
+        """
+        return AsyncVersionsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncVersionsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response
+        """
+        return AsyncVersionsResourceWithStreamingResponse(self)
+
+    async def retrieve(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        deployment: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> ModelDeployment:
+        """
+        Get a specific version of a ModelDeployment.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        if not deployment:
+            raise ValueError(f"Expected a non-empty value for `deployment` but received {deployment!r}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return await self._get(
+            path_template(
+                "/apis/models/v2/workspaces/{workspace}/deployments/{deployment}/versions/{name}",
+                workspace=workspace,
+                deployment=deployment,
+                name=name,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelDeployment,
+        )
+
+    async def list(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> VersionListResponse:
+        """
+        List all versions of a ModelDeployment.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return await self._get(
+            path_template(
+                "/apis/models/v2/workspaces/{workspace}/deployments/{name}/versions", workspace=workspace, name=name
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=VersionListResponse,
+        )
+
+    async def delete(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        deployment: str,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> object:
+        """
+        Delete a specific version of a ModelDeployment.
+
+        If the deployment is in any state other than DELETED, this will set its status
+        to DELETING. The models controller will then:
+
+        1. Delete the infrastructure (e.g., K8s NimService)
+        2. Update the status to DELETED
+
+        If the deployment is already in DELETED status, calling delete again will
+        permanently remove it from the database.
+
+        Returns:
+
+        - 202 Accepted: Deployment version marked for deletion (status set to DELETING)
+        - 204 No Content: Deployment version permanently removed from database (was
+          already DELETED)
+        - 404 Not Found: Deployment version doesn't exist
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        if not deployment:
+            raise ValueError(f"Expected a non-empty value for `deployment` but received {deployment!r}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return await self._delete(
+            path_template(
+                "/apis/models/v2/workspaces/{workspace}/deployments/{deployment}/versions/{name}",
+                workspace=workspace,
+                deployment=deployment,
+                name=name,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=object,
+        )
+
+
+class VersionsResourceWithRawResponse:
+    def __init__(self, versions: VersionsResource) -> None:
+        self._versions = versions
+
+        self.retrieve = to_raw_response_wrapper(
+            versions.retrieve,
+        )
+        self.list = to_raw_response_wrapper(
+            versions.list,
+        )
+        self.delete = to_raw_response_wrapper(
+            versions.delete,
+        )
+
+
+class AsyncVersionsResourceWithRawResponse:
+    def __init__(self, versions: AsyncVersionsResource) -> None:
+        self._versions = versions
+
+        self.retrieve = async_to_raw_response_wrapper(
+            versions.retrieve,
+        )
+        self.list = async_to_raw_response_wrapper(
+            versions.list,
+        )
+        self.delete = async_to_raw_response_wrapper(
+            versions.delete,
+        )
+
+
+class VersionsResourceWithStreamingResponse:
+    def __init__(self, versions: VersionsResource) -> None:
+        self._versions = versions
+
+        self.retrieve = to_streamed_response_wrapper(
+            versions.retrieve,
+        )
+        self.list = to_streamed_response_wrapper(
+            versions.list,
+        )
+        self.delete = to_streamed_response_wrapper(
+            versions.delete,
+        )
+
+
+class AsyncVersionsResourceWithStreamingResponse:
+    def __init__(self, versions: AsyncVersionsResource) -> None:
+        self._versions = versions
+
+        self.retrieve = async_to_streamed_response_wrapper(
+            versions.retrieve,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            versions.list,
+        )
+        self.delete = async_to_streamed_response_wrapper(
+            versions.delete,
+        )

nemo_platform/resources/inference/gateway/__init__.py

@@ -0,0 +1,76 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .model import (
+    ModelResource,
+    AsyncModelResource,
+    ModelResourceWithRawResponse,
+    AsyncModelResourceWithRawResponse,
+    ModelResourceWithStreamingResponse,
+    AsyncModelResourceWithStreamingResponse,
+)
+from .openai import (
+    OpenAIResource,
+    AsyncOpenAIResource,
+    OpenAIResourceWithRawResponse,
+    AsyncOpenAIResourceWithRawResponse,
+    OpenAIResourceWithStreamingResponse,
+    AsyncOpenAIResourceWithStreamingResponse,
+)
+from .gateway import (
+    GatewayResource,
+    AsyncGatewayResource,
+    GatewayResourceWithRawResponse,
+    AsyncGatewayResourceWithRawResponse,
+    GatewayResourceWithStreamingResponse,
+    AsyncGatewayResourceWithStreamingResponse,
+)
+from .provider import (
+    ProviderResource,
+    AsyncProviderResource,
+    ProviderResourceWithRawResponse,
+    AsyncProviderResourceWithRawResponse,
+    ProviderResourceWithStreamingResponse,
+    AsyncProviderResourceWithStreamingResponse,
+)
+
+__all__ = [
+    "OpenAIResource",
+    "AsyncOpenAIResource",
+    "OpenAIResourceWithRawResponse",
+    "AsyncOpenAIResourceWithRawResponse",
+    "OpenAIResourceWithStreamingResponse",
+    "AsyncOpenAIResourceWithStreamingResponse",
+    "ModelResource",
+    "AsyncModelResource",
+    "ModelResourceWithRawResponse",
+    "AsyncModelResourceWithRawResponse",
+    "ModelResourceWithStreamingResponse",
+    "AsyncModelResourceWithStreamingResponse",
+    "ProviderResource",
+    "AsyncProviderResource",
+    "ProviderResourceWithRawResponse",
+    "AsyncProviderResourceWithRawResponse",
+    "ProviderResourceWithStreamingResponse",
+    "AsyncProviderResourceWithStreamingResponse",
+    "GatewayResource",
+    "AsyncGatewayResource",
+    "GatewayResourceWithRawResponse",
+    "AsyncGatewayResourceWithRawResponse",
+    "GatewayResourceWithStreamingResponse",
+    "AsyncGatewayResourceWithStreamingResponse",
+]

nemo_platform/resources/inference/gateway/gateway.py

@@ -0,0 +1,181 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .model import (
+    ModelResource,
+    AsyncModelResource,
+    ModelResourceWithRawResponse,
+    AsyncModelResourceWithRawResponse,
+    ModelResourceWithStreamingResponse,
+    AsyncModelResourceWithStreamingResponse,
+)
+from .provider import (
+    ProviderResource,
+    AsyncProviderResource,
+    ProviderResourceWithRawResponse,
+    AsyncProviderResourceWithRawResponse,
+    ProviderResourceWithStreamingResponse,
+    AsyncProviderResourceWithStreamingResponse,
+)
+from ...._compat import cached_property
+from ...._resource import SyncAPIResource, AsyncAPIResource
+from .openai.openai import (
+    OpenAIResource,
+    AsyncOpenAIResource,
+    OpenAIResourceWithRawResponse,
+    AsyncOpenAIResourceWithRawResponse,
+    OpenAIResourceWithStreamingResponse,
+    AsyncOpenAIResourceWithStreamingResponse,
+)
+
+__all__ = ["GatewayResource", "AsyncGatewayResource"]
+
+
+class GatewayResource(SyncAPIResource):
+    @cached_property
+    def openai(self) -> OpenAIResource:
+        return OpenAIResource(self._client)
+
+    @cached_property
+    def model(self) -> ModelResource:
+        return ModelResource(self._client)
+
+    @cached_property
+    def provider(self) -> ProviderResource:
+        return ProviderResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> GatewayResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers
+        """
+        return GatewayResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> GatewayResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response
+        """
+        return GatewayResourceWithStreamingResponse(self)
+
+
+class AsyncGatewayResource(AsyncAPIResource):
+    @cached_property
+    def openai(self) -> AsyncOpenAIResource:
+        return AsyncOpenAIResource(self._client)
+
+    @cached_property
+    def model(self) -> AsyncModelResource:
+        return AsyncModelResource(self._client)
+
+    @cached_property
+    def provider(self) -> AsyncProviderResource:
+        return AsyncProviderResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncGatewayResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers
+        """
+        return AsyncGatewayResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncGatewayResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response
+        """
+        return AsyncGatewayResourceWithStreamingResponse(self)
+
+
+class GatewayResourceWithRawResponse:
+    def __init__(self, gateway: GatewayResource) -> None:
+        self._gateway = gateway
+
+    @cached_property
+    def openai(self) -> OpenAIResourceWithRawResponse:
+        return OpenAIResourceWithRawResponse(self._gateway.openai)
+
+    @cached_property
+    def model(self) -> ModelResourceWithRawResponse:
+        return ModelResourceWithRawResponse(self._gateway.model)
+
+    @cached_property
+    def provider(self) -> ProviderResourceWithRawResponse:
+        return ProviderResourceWithRawResponse(self._gateway.provider)
+
+
+class AsyncGatewayResourceWithRawResponse:
+    def __init__(self, gateway: AsyncGatewayResource) -> None:
+        self._gateway = gateway
+
+    @cached_property
+    def openai(self) -> AsyncOpenAIResourceWithRawResponse:
+        return AsyncOpenAIResourceWithRawResponse(self._gateway.openai)
+
+    @cached_property
+    def model(self) -> AsyncModelResourceWithRawResponse:
+        return AsyncModelResourceWithRawResponse(self._gateway.model)
+
+    @cached_property
+    def provider(self) -> AsyncProviderResourceWithRawResponse:
+        return AsyncProviderResourceWithRawResponse(self._gateway.provider)
+
+
+class GatewayResourceWithStreamingResponse:
+    def __init__(self, gateway: GatewayResource) -> None:
+        self._gateway = gateway
+
+    @cached_property
+    def openai(self) -> OpenAIResourceWithStreamingResponse:
+        return OpenAIResourceWithStreamingResponse(self._gateway.openai)
+
+    @cached_property
+    def model(self) -> ModelResourceWithStreamingResponse:
+        return ModelResourceWithStreamingResponse(self._gateway.model)
+
+    @cached_property
+    def provider(self) -> ProviderResourceWithStreamingResponse:
+        return ProviderResourceWithStreamingResponse(self._gateway.provider)
+
+
+class AsyncGatewayResourceWithStreamingResponse:
+    def __init__(self, gateway: AsyncGatewayResource) -> None:
+        self._gateway = gateway
+
+    @cached_property
+    def openai(self) -> AsyncOpenAIResourceWithStreamingResponse:
+        return AsyncOpenAIResourceWithStreamingResponse(self._gateway.openai)
+
+    @cached_property
+    def model(self) -> AsyncModelResourceWithStreamingResponse:
+        return AsyncModelResourceWithStreamingResponse(self._gateway.model)
+
+    @cached_property
+    def provider(self) -> AsyncProviderResourceWithStreamingResponse:
+        return AsyncProviderResourceWithStreamingResponse(self._gateway.provider)