scale-gp-beta 0.1.0a2__py3-none-any.whl

scale_gp/resources/models.py

@@ -0,0 +1,834 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Optional
+from typing_extensions import Literal, overload
+
+import httpx
+
+from ..types import model_list_params, model_create_params, model_update_params
+from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from .._utils import (
+    required_args,
+    maybe_transform,
+    async_maybe_transform,
+)
+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 ..pagination import SyncCursorPage, AsyncCursorPage
+from .._base_client import AsyncPaginator, make_request_options
+from ..types.inference_model import InferenceModel
+from ..types.model_delete_response import ModelDeleteResponse
+
+__all__ = ["ModelsResource", "AsyncModelsResource"]
+
+
+class ModelsResource(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> ModelsResourceWithRawResponse:
+        """
+        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://www.github.com/scaleapi/sgp-python-beta#accessing-raw-response-data-eg-headers
+        """
+        return ModelsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> ModelsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/scaleapi/sgp-python-beta#with_streaming_response
+        """
+        return ModelsResourceWithStreamingResponse(self)
+
+    @overload
+    def create(
+        self,
+        *,
+        name: str,
+        vendor_configuration: model_create_params.LaunchModelCreateRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        model_type: Literal["generic"] | NotGiven = NOT_GIVEN,
+        model_vendor: Literal["launch"] | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "update"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Create Model
+
+        Args:
+          name: Unique name to reference your model
+
+          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
+        """
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        name: str,
+        vendor_configuration: model_create_params.LlmEngineModelCreateRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        model_type: Literal["chat_completion"] | NotGiven = NOT_GIVEN,
+        model_vendor: Literal["llmengine"] | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "update"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Create Model
+
+        Args:
+          name: Unique name to reference your model
+
+          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
+        """
+        ...
+
+    @required_args(["name", "vendor_configuration"])
+    def create(
+        self,
+        *,
+        name: str,
+        vendor_configuration: model_create_params.LaunchModelCreateRequestVendorConfiguration
+        | model_create_params.LlmEngineModelCreateRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        model_type: Literal["generic"] | Literal["chat_completion"] | NotGiven = NOT_GIVEN,
+        model_vendor: Literal["launch"] | Literal["llmengine"] | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "update"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        return self._post(
+            "/v5/models",
+            body=maybe_transform(
+                {
+                    "name": name,
+                    "vendor_configuration": vendor_configuration,
+                    "model_metadata": model_metadata,
+                    "model_type": model_type,
+                    "model_vendor": model_vendor,
+                    "on_conflict": on_conflict,
+                },
+                model_create_params.ModelCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=InferenceModel,
+        )
+
+    def retrieve(
+        self,
+        model_id: 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,
+    ) -> InferenceModel:
+        """
+        Get Model
+
+        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 not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return self._get(
+            f"/v5/models/{model_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=InferenceModel,
+        )
+
+    @overload
+    def update(
+        self,
+        model_id: str,
+        *,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Update Model
+
+        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
+        """
+        ...
+
+    @overload
+    def update(
+        self,
+        model_id: str,
+        *,
+        vendor_configuration: model_update_params.ModelConfigurationPatchRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Update Model
+
+        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
+        """
+        ...
+
+    @overload
+    def update(
+        self,
+        model_id: str,
+        *,
+        name: str,
+        on_conflict: Literal["error", "swap"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Update Model
+
+        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
+        """
+        ...
+
+    def update(
+        self,
+        model_id: str,
+        *,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        vendor_configuration: model_update_params.ModelConfigurationPatchRequestVendorConfiguration
+        | NotGiven = NOT_GIVEN,
+        name: str | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "swap"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        if not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return self._patch(
+            f"/v5/models/{model_id}",
+            body=maybe_transform(
+                {
+                    "model_metadata": model_metadata,
+                    "vendor_configuration": vendor_configuration,
+                    "name": name,
+                    "on_conflict": on_conflict,
+                },
+                model_update_params.ModelUpdateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=InferenceModel,
+        )
+
+    def list(
+        self,
+        *,
+        ending_before: Optional[str] | NotGiven = NOT_GIVEN,
+        limit: int | NotGiven = NOT_GIVEN,
+        model_vendor: Optional[
+            Literal["openai", "cohere", "vertex_ai", "anthropic", "launch", "llmengine", "model_zoo"]
+        ]
+        | NotGiven = NOT_GIVEN,
+        name: Optional[str] | NotGiven = NOT_GIVEN,
+        starting_after: Optional[str] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> SyncCursorPage[InferenceModel]:
+        """
+        List Models
+
+        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
+        """
+        return self._get_api_list(
+            "/v5/models",
+            page=SyncCursorPage[InferenceModel],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "ending_before": ending_before,
+                        "limit": limit,
+                        "model_vendor": model_vendor,
+                        "name": name,
+                        "starting_after": starting_after,
+                    },
+                    model_list_params.ModelListParams,
+                ),
+            ),
+            model=InferenceModel,
+        )
+
+    def delete(
+        self,
+        model_id: 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,
+    ) -> ModelDeleteResponse:
+        """
+        Delete Model
+
+        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 not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return self._delete(
+            f"/v5/models/{model_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelDeleteResponse,
+        )
+
+
+class AsyncModelsResource(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncModelsResourceWithRawResponse:
+        """
+        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://www.github.com/scaleapi/sgp-python-beta#accessing-raw-response-data-eg-headers
+        """
+        return AsyncModelsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncModelsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/scaleapi/sgp-python-beta#with_streaming_response
+        """
+        return AsyncModelsResourceWithStreamingResponse(self)
+
+    @overload
+    async def create(
+        self,
+        *,
+        name: str,
+        vendor_configuration: model_create_params.LaunchModelCreateRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        model_type: Literal["generic"] | NotGiven = NOT_GIVEN,
+        model_vendor: Literal["launch"] | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "update"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Create Model
+
+        Args:
+          name: Unique name to reference your model
+
+          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
+        """
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        name: str,
+        vendor_configuration: model_create_params.LlmEngineModelCreateRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        model_type: Literal["chat_completion"] | NotGiven = NOT_GIVEN,
+        model_vendor: Literal["llmengine"] | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "update"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Create Model
+
+        Args:
+          name: Unique name to reference your model
+
+          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
+        """
+        ...
+
+    @required_args(["name", "vendor_configuration"])
+    async def create(
+        self,
+        *,
+        name: str,
+        vendor_configuration: model_create_params.LaunchModelCreateRequestVendorConfiguration
+        | model_create_params.LlmEngineModelCreateRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        model_type: Literal["generic"] | Literal["chat_completion"] | NotGiven = NOT_GIVEN,
+        model_vendor: Literal["launch"] | Literal["llmengine"] | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "update"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        return await self._post(
+            "/v5/models",
+            body=await async_maybe_transform(
+                {
+                    "name": name,
+                    "vendor_configuration": vendor_configuration,
+                    "model_metadata": model_metadata,
+                    "model_type": model_type,
+                    "model_vendor": model_vendor,
+                    "on_conflict": on_conflict,
+                },
+                model_create_params.ModelCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=InferenceModel,
+        )
+
+    async def retrieve(
+        self,
+        model_id: 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,
+    ) -> InferenceModel:
+        """
+        Get Model
+
+        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 not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return await self._get(
+            f"/v5/models/{model_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=InferenceModel,
+        )
+
+    @overload
+    async def update(
+        self,
+        model_id: str,
+        *,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Update Model
+
+        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
+        """
+        ...
+
+    @overload
+    async def update(
+        self,
+        model_id: str,
+        *,
+        vendor_configuration: model_update_params.ModelConfigurationPatchRequestVendorConfiguration,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Update Model
+
+        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
+        """
+        ...
+
+    @overload
+    async def update(
+        self,
+        model_id: str,
+        *,
+        name: str,
+        on_conflict: Literal["error", "swap"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        """
+        Update Model
+
+        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
+        """
+        ...
+
+    async def update(
+        self,
+        model_id: str,
+        *,
+        model_metadata: Dict[str, object] | NotGiven = NOT_GIVEN,
+        vendor_configuration: model_update_params.ModelConfigurationPatchRequestVendorConfiguration
+        | NotGiven = NOT_GIVEN,
+        name: str | NotGiven = NOT_GIVEN,
+        on_conflict: Literal["error", "swap"] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> InferenceModel:
+        if not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return await self._patch(
+            f"/v5/models/{model_id}",
+            body=await async_maybe_transform(
+                {
+                    "model_metadata": model_metadata,
+                    "vendor_configuration": vendor_configuration,
+                    "name": name,
+                    "on_conflict": on_conflict,
+                },
+                model_update_params.ModelUpdateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=InferenceModel,
+        )
+
+    def list(
+        self,
+        *,
+        ending_before: Optional[str] | NotGiven = NOT_GIVEN,
+        limit: int | NotGiven = NOT_GIVEN,
+        model_vendor: Optional[
+            Literal["openai", "cohere", "vertex_ai", "anthropic", "launch", "llmengine", "model_zoo"]
+        ]
+        | NotGiven = NOT_GIVEN,
+        name: Optional[str] | NotGiven = NOT_GIVEN,
+        starting_after: Optional[str] | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> AsyncPaginator[InferenceModel, AsyncCursorPage[InferenceModel]]:
+        """
+        List Models
+
+        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
+        """
+        return self._get_api_list(
+            "/v5/models",
+            page=AsyncCursorPage[InferenceModel],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "ending_before": ending_before,
+                        "limit": limit,
+                        "model_vendor": model_vendor,
+                        "name": name,
+                        "starting_after": starting_after,
+                    },
+                    model_list_params.ModelListParams,
+                ),
+            ),
+            model=InferenceModel,
+        )
+
+    async def delete(
+        self,
+        model_id: 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,
+    ) -> ModelDeleteResponse:
+        """
+        Delete Model
+
+        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 not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return await self._delete(
+            f"/v5/models/{model_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelDeleteResponse,
+        )
+
+
+class ModelsResourceWithRawResponse:
+    def __init__(self, models: ModelsResource) -> None:
+        self._models = models
+
+        self.create = to_raw_response_wrapper(
+            models.create,
+        )
+        self.retrieve = to_raw_response_wrapper(
+            models.retrieve,
+        )
+        self.update = to_raw_response_wrapper(
+            models.update,
+        )
+        self.list = to_raw_response_wrapper(
+            models.list,
+        )
+        self.delete = to_raw_response_wrapper(
+            models.delete,
+        )
+
+
+class AsyncModelsResourceWithRawResponse:
+    def __init__(self, models: AsyncModelsResource) -> None:
+        self._models = models
+
+        self.create = async_to_raw_response_wrapper(
+            models.create,
+        )
+        self.retrieve = async_to_raw_response_wrapper(
+            models.retrieve,
+        )
+        self.update = async_to_raw_response_wrapper(
+            models.update,
+        )
+        self.list = async_to_raw_response_wrapper(
+            models.list,
+        )
+        self.delete = async_to_raw_response_wrapper(
+            models.delete,
+        )
+
+
+class ModelsResourceWithStreamingResponse:
+    def __init__(self, models: ModelsResource) -> None:
+        self._models = models
+
+        self.create = to_streamed_response_wrapper(
+            models.create,
+        )
+        self.retrieve = to_streamed_response_wrapper(
+            models.retrieve,
+        )
+        self.update = to_streamed_response_wrapper(
+            models.update,
+        )
+        self.list = to_streamed_response_wrapper(
+            models.list,
+        )
+        self.delete = to_streamed_response_wrapper(
+            models.delete,
+        )
+
+
+class AsyncModelsResourceWithStreamingResponse:
+    def __init__(self, models: AsyncModelsResource) -> None:
+        self._models = models
+
+        self.create = async_to_streamed_response_wrapper(
+            models.create,
+        )
+        self.retrieve = async_to_streamed_response_wrapper(
+            models.retrieve,
+        )
+        self.update = async_to_streamed_response_wrapper(
+            models.update,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            models.list,
+        )
+        self.delete = async_to_streamed_response_wrapper(
+            models.delete,
+        )