Merge pull request #15240 from BerriAI/litellm_dev_10_06_2025_p1

Azure - passthrough support with router models

Author: krrishdholakia

litellm/llms/azure/common_utils.py

@@ -665,10 +665,6 @@ def _base_validate_azure_environment(
     ) -> dict:
         litellm_params = litellm_params or GenericLiteLLMParams()
 
-        # If api-key is already in headers, preserve it
-        if "api-key" in headers:
-            return headers
-
         api_key = (
             litellm_params.api_key
             or litellm.api_key
@@ -693,7 +689,7 @@ def _base_validate_azure_environment(
     def _get_base_azure_url(
         api_base: Optional[str],
         litellm_params: Optional[Union[GenericLiteLLMParams, Dict[str, Any]]],
-        route: Literal["/openai/responses", "/openai/vector_stores"],
+        route: Union[Literal["/openai/responses", "/openai/vector_stores"], str],
         default_api_version: Optional[Union[str, Literal["latest", "preview"]]] = None,
     ) -> str:
         """

litellm/llms/azure/passthrough/transformation.py

@@ -0,0 +1,85 @@
+from typing import TYPE_CHECKING, List, Optional, Tuple
+
+import httpx
+
+from litellm.llms.azure.common_utils import BaseAzureLLM
+from litellm.llms.base_llm.passthrough.transformation import BasePassthroughConfig
+from litellm.secret_managers.main import get_secret_str
+from litellm.types.llms.openai import AllMessageValues
+from litellm.types.router import GenericLiteLLMParams
+
+if TYPE_CHECKING:
+    from httpx import URL
+
+
+class AzurePassthroughConfig(BasePassthroughConfig):
+    def is_streaming_request(self, endpoint: str, request_data: dict) -> bool:
+        return "stream" in request_data
+
+    def get_complete_url(
+        self,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        model: str,
+        endpoint: str,
+        request_query_params: Optional[dict],
+        litellm_params: dict,
+    ) -> Tuple["URL", str]:
+        base_target_url = self.get_api_base(api_base)
+
+        if base_target_url is None:
+            raise Exception("Azure api base not found")
+
+        litellm_metadata = litellm_params.get("litellm_metadata") or {}
+        model_group = litellm_metadata.get("model_group")
+        if model_group and model_group in endpoint:
+            endpoint = endpoint.replace(model_group, model)
+
+        complete_url = BaseAzureLLM._get_base_azure_url(
+            api_base=base_target_url,
+            litellm_params=litellm_params,
+            route=endpoint,
+            default_api_version=litellm_params.get("api_version"),
+        )
+        return (
+            httpx.URL(complete_url),
+            base_target_url,
+        )
+
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> dict:
+        return BaseAzureLLM._base_validate_azure_environment(
+            headers=headers,
+            litellm_params=GenericLiteLLMParams(
+                **{**litellm_params, "api_key": api_key}
+            ),
+        )
+
+    @staticmethod
+    def get_api_base(
+        api_base: Optional[str] = None,
+    ) -> Optional[str]:
+        return api_base or get_secret_str("AZURE_API_BASE")
+
+    @staticmethod
+    def get_api_key(
+        api_key: Optional[str] = None,
+    ) -> Optional[str]:
+        return api_key or get_secret_str("AZURE_API_KEY")
+
+    @staticmethod
+    def get_base_model(model: str) -> Optional[str]:
+        return model
+
+    def get_models(
+        self, api_key: Optional[str] = None, api_base: Optional[str] = None
+    ) -> List[str]:
+        return super().get_models(api_key, api_base)

litellm/passthrough/main.py

@@ -242,12 +242,14 @@ def llm_passthrough_route(
         request_query_params=request_query_params,
         litellm_params=litellm_params_dict,
     )
-    
-    # need to encode the id of application-inference-profile for bedrock
+
+    # [TODO: Refactor to bedrockpassthroughconfig] need to encode the id of application-inference-profile for bedrock
     if custom_llm_provider == "bedrock" and "application-inference-profile" in endpoint:
-        encoded_url_str = CommonUtils.encode_bedrock_runtime_modelid_arn(str(updated_url))
+        encoded_url_str = CommonUtils.encode_bedrock_runtime_modelid_arn(
+            str(updated_url)
+        )
         updated_url = httpx.URL(encoded_url_str)
-    
+
     # Add or update query parameters
     provider_api_key = provider_config.get_api_key(api_key)