[Feat] New LLM API Endpoint - Add List input items for Responses API

litellm/llms/azure/responses/transformation.py

@@ -170,3 +170,35 @@ def transform_get_response_api_request(
         data: Dict = {}
         verbose_logger.debug(f"get response url={get_url}")
         return get_url, data
+
+    def transform_list_input_items_request(
+        self,
+        response_id: str,
+        api_base: str,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+        after: Optional[str] = None,
+        before: Optional[str] = None,
+        include: Optional[List[str]] = None,
+        limit: int = 20,
+        order: Literal["asc", "desc"] = "desc",
+    ) -> Tuple[str, Dict]:
+        url = (
+            self._construct_url_for_response_id_in_path(
+                api_base=api_base, response_id=response_id
+            )
+            + "/input_items"
+        )
+        params: Dict[str, Any] = {}
+        if after is not None:
+            params["after"] = after
+        if before is not None:
+            params["before"] = before
+        if include:
+            params["include"] = ",".join(include)
+        if limit is not None:
+            params["limit"] = limit
+        if order is not None:
+            params["order"] = order
+        verbose_logger.debug(f"list input items url={url}")
+        return url, params

litellm/llms/base_llm/responses/transformation.py

@@ -156,7 +156,7 @@ def transform_get_response_api_request(
         headers: dict,
     ) -> Tuple[str, Dict]:
         pass
-    
+
     @abstractmethod
     def transform_get_response_api_response(
         self,
@@ -165,10 +165,36 @@ def transform_get_response_api_response(
     ) -> ResponsesAPIResponse:
         pass
 
+    #########################################################
+    ########## LIST INPUT ITEMS API TRANSFORMATION ##########
+    #########################################################
+    @abstractmethod
+    def transform_list_input_items_request(
+        self,
+        response_id: str,
+        api_base: str,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+        after: Optional[str] = None,
+        before: Optional[str] = None,
+        include: Optional[List[str]] = None,
+        limit: int = 20,
+        order: Literal["asc", "desc"] = "desc",
+    ) -> Tuple[str, Dict]:
+        pass
+
+    @abstractmethod
+    def transform_list_input_items_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+    ) -> Dict:
+        pass
+
     #########################################################
     ########## END GET RESPONSE API TRANSFORMATION ##########
     #########################################################
-    
+
     def get_error_class(
         self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
     ) -> BaseLLMException:

litellm/llms/custom_httpx/llm_http_handler.py

@@ -6,6 +6,7 @@
     Coroutine,
     Dict,
     List,
+    Literal,
     Optional,
     Tuple,
     Union,
@@ -1812,6 +1813,168 @@ async def async_get_responses(
             logging_obj=logging_obj,
         )
 
+    #####################################################################
+    ################ LIST RESPONSES INPUT ITEMS HANDLER ###########################
+    #####################################################################
+    def list_responses_input_items(
+        self,
+        response_id: str,
+        responses_api_provider_config: BaseResponsesAPIConfig,
+        litellm_params: GenericLiteLLMParams,
+        logging_obj: LiteLLMLoggingObj,
+        custom_llm_provider: Optional[str] = None,
+        after: Optional[str] = None,
+        before: Optional[str] = None,
+        include: Optional[List[str]] = None,
+        limit: int = 20,
+        order: Literal["asc", "desc"] = "desc",
+        extra_headers: Optional[Dict[str, Any]] = None,
+        timeout: Optional[Union[float, httpx.Timeout]] = None,
+        client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
+        _is_async: bool = False,
+    ) -> Union[Dict, Coroutine[Any, Any, Dict]]:
+        if _is_async:
+            return self.async_list_responses_input_items(
+                response_id=response_id,
+                responses_api_provider_config=responses_api_provider_config,
+                litellm_params=litellm_params,
+                logging_obj=logging_obj,
+                custom_llm_provider=custom_llm_provider,
+                after=after,
+                before=before,
+                include=include,
+                limit=limit,
+                order=order,
+                extra_headers=extra_headers,
+                timeout=timeout,
+                client=client,
+            )
+
+        if client is None or not isinstance(client, HTTPHandler):
+            sync_httpx_client = _get_httpx_client(
+                params={"ssl_verify": litellm_params.get("ssl_verify", None)}
+            )
+        else:
+            sync_httpx_client = client
+
+        headers = responses_api_provider_config.validate_environment(
+            api_key=litellm_params.api_key,
+            headers=extra_headers or {},
+            model="None",
+        )
+
+        if extra_headers:
+            headers.update(extra_headers)
+
+        api_base = responses_api_provider_config.get_complete_url(
+            api_base=litellm_params.api_base,
+            litellm_params=dict(litellm_params),
+        )
+
+        url, params = responses_api_provider_config.transform_list_input_items_request(
+            response_id=response_id,
+            api_base=api_base,
+            litellm_params=litellm_params,
+            headers=headers,
+            after=after,
+            before=before,
+            include=include,
+            limit=limit,
+            order=order,
+        )
+
+        logging_obj.pre_call(
+            input="",
+            api_key="",
+            additional_args={
+                "complete_input_dict": params,
+                "api_base": api_base,
+                "headers": headers,
+            },
+        )
+
+        try:
+            response = sync_httpx_client.get(url=url, headers=headers, params=params)
+        except Exception as e:
+            raise self._handle_error(e=e, provider_config=responses_api_provider_config)
+
+        return responses_api_provider_config.transform_list_input_items_response(
+            raw_response=response,
+            logging_obj=logging_obj,
+        )
+
+    async def async_list_responses_input_items(
+        self,
+        response_id: str,
+        responses_api_provider_config: BaseResponsesAPIConfig,
+        litellm_params: GenericLiteLLMParams,
+        logging_obj: LiteLLMLoggingObj,
+        custom_llm_provider: Optional[str] = None,
+        after: Optional[str] = None,
+        before: Optional[str] = None,
+        include: Optional[List[str]] = None,
+        limit: int = 20,
+        order: Literal["asc", "desc"] = "desc",
+        extra_headers: Optional[Dict[str, Any]] = None,
+        timeout: Optional[Union[float, httpx.Timeout]] = None,
+        client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
+    ) -> Dict:
+        if client is None or not isinstance(client, AsyncHTTPHandler):
+            async_httpx_client = get_async_httpx_client(
+                llm_provider=litellm.LlmProviders(custom_llm_provider),
+                params={"ssl_verify": litellm_params.get("ssl_verify", None)},
+            )
+        else:
+            async_httpx_client = client
+
+        headers = responses_api_provider_config.validate_environment(
+            api_key=litellm_params.api_key,
+            headers=extra_headers or {},
+            model="None",
+        )
+
+        if extra_headers:
+            headers.update(extra_headers)
+
+        api_base = responses_api_provider_config.get_complete_url(
+            api_base=litellm_params.api_base,
+            litellm_params=dict(litellm_params),
+        )
+
+        url, params = responses_api_provider_config.transform_list_input_items_request(
+            response_id=response_id,
+            api_base=api_base,
+            litellm_params=litellm_params,
+            headers=headers,
+            after=after,
+            before=before,
+            include=include,
+            limit=limit,
+            order=order,
+        )
+
+        logging_obj.pre_call(
+            input="",
+            api_key="",
+            additional_args={
+                "complete_input_dict": params,
+                "api_base": api_base,
+                "headers": headers,
+            },
+        )
+
+        try:
+            response = await async_httpx_client.get(
+                url=url, headers=headers, params=params
+            )
+        except Exception as e:
+            raise self._handle_error(e=e, provider_config=responses_api_provider_config)
+
+        return responses_api_provider_config.transform_list_input_items_response(
+            raw_response=response,
+            logging_obj=logging_obj,
+        )
+
     def create_file(
         self,
         create_file_data: CreateFileRequest,
@@ -2134,7 +2297,10 @@ def image_edit_handler(
         _is_async: bool = False,
         fake_stream: bool = False,
         litellm_metadata: Optional[Dict[str, Any]] = None,
-    ) -> Union[ImageResponse, Coroutine[Any, Any, ImageResponse],]:
+    ) -> Union[
+        ImageResponse,
+        Coroutine[Any, Any, ImageResponse],
+    ]:
         """
 
         Handles image edit requests.

litellm/llms/openai/responses/transformation.py

@@ -251,7 +251,7 @@ def transform_delete_response_api_response(
                 message=raw_response.text, status_code=raw_response.status_code
             )
         return DeleteResponseResult(**raw_response_json)
-    
+
     #########################################################
     ########## GET RESPONSE API TRANSFORMATION ###############
     #########################################################
@@ -271,7 +271,7 @@ def transform_get_response_api_request(
         url = f"{api_base}/{response_id}"
         data: Dict = {}
         return url, data
-    
+
     def transform_get_response_api_response(
         self,
         raw_response: httpx.Response,
@@ -287,3 +287,44 @@ def transform_get_response_api_response(
                 message=raw_response.text, status_code=raw_response.status_code
             )
         return ResponsesAPIResponse(**raw_response_json)
+
+    #########################################################
+    ########## LIST INPUT ITEMS TRANSFORMATION #############
+    #########################################################
+    def transform_list_input_items_request(
+        self,
+        response_id: str,
+        api_base: str,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+        after: Optional[str] = None,
+        before: Optional[str] = None,
+        include: Optional[List[str]] = None,
+        limit: int = 20,
+        order: Literal["asc", "desc"] = "desc",
+    ) -> Tuple[str, Dict]:
+        url = f"{api_base}/{response_id}/input_items"
+        params: Dict[str, Any] = {}
+        if after is not None:
+            params["after"] = after
+        if before is not None:
+            params["before"] = before
+        if include:
+            params["include"] = ",".join(include)
+        if limit is not None:
+            params["limit"] = limit
+        if order is not None:
+            params["order"] = order
+        return url, params
+
+    def transform_list_input_items_response(
+        self,
+        raw_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+    ) -> Dict:
+        try:
+            return raw_response.json()
+        except Exception:
+            raise OpenAIError(
+                message=raw_response.text, status_code=raw_response.status_code
+            )

litellm/model_prices_and_context_window_backup.json

@@ -4153,6 +4153,32 @@
         "supports_assistant_prefill": true,
         "supports_tool_choice": true
     },
+    "mistral/magistral-medium-2506": {
+        "max_tokens": 40000,
+        "max_input_tokens": 40000,
+        "max_output_tokens": 40000,
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 5e-06,
+        "litellm_provider": "mistral",
+        "mode": "chat",
+        "source": "https://mistral.ai/news/magistral",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_tool_choice": true
+    },
+    "mistral/magistral-small-2506": {
+        "max_tokens": 40000,
+        "max_input_tokens": 40000,
+        "max_output_tokens": 40000,
+        "input_cost_per_token": 0.0,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "mistral",
+        "mode": "chat",
+        "source": "https://mistral.ai/news/magistral",
+        "supports_function_calling": true,
+        "supports_assistant_prefill": true,
+        "supports_tool_choice": true
+    },
     "mistral/mistral-embed": {
         "max_tokens": 8192,
         "max_input_tokens": 8192,

litellm/proxy/common_request_processing.py

@@ -250,6 +250,7 @@ async def common_processing_pre_call_logic(
             "acancel_fine_tuning_job",
             "alist_fine_tuning_jobs",
             "aretrieve_fine_tuning_job",
+            "alist_input_items",
             "aimage_edit",
         ],
         version: Optional[str] = None,
@@ -329,6 +330,7 @@ async def base_process_llm_request(
             "adelete_responses",
             "atext_completion",
             "aimage_edit",
+            "alist_input_items",
         ],
         proxy_logging_obj: ProxyLogging,
         general_settings: dict,