fix using pass_through_all_models

litellm/proxy/proxy_config.yaml

@@ -11,6 +11,10 @@ model_list:
   - model_name: "*"
     litellm_params:
       model: "*"
+  - model_name: "*"
+    litellm_params:
+      model: openai/*
+      api_key: os.environ/OPENAI_API_KEY
 general_settings: 
   master_key: sk-1234
   alerting: ["slack"]

litellm/proxy/proxy_server.py

@@ -2882,14 +2882,15 @@ async def chat_completion(
         elif (
             llm_router is not None
             and data["model"] not in router_model_names
-            and llm_router.default_deployment is not None
-        ):  # model in router deployments, calling a specific deployment on the router
-            tasks.append(llm_router.acompletion(**data))
-        elif (
-            llm_router is not None
             and llm_router.router_general_settings.pass_through_all_models is True
         ):
             tasks.append(litellm.acompletion(**data))
+        elif (
+            llm_router is not None
+            and data["model"] not in router_model_names
+            and llm_router.default_deployment is not None
+        ):  # model in router deployments, calling a specific deployment on the router
+            tasks.append(llm_router.acompletion(**data))
         elif user_model is not None:  # `litellm --model <your-model-name>`
             tasks.append(litellm.acompletion(**data))
         else:
@@ -3144,6 +3145,12 @@ async def completion(
             llm_router is not None and data["model"] in llm_router.get_model_ids()
         ):  # model in router model list
             llm_response = asyncio.create_task(llm_router.atext_completion(**data))
+        elif (
+            llm_router is not None
+            and data["model"] not in router_model_names
+            and llm_router.router_general_settings.pass_through_all_models is True
+        ):
+            llm_response = asyncio.create_task(litellm.atext_completion(**data))
         elif (
             llm_router is not None
             and data["model"] not in router_model_names
@@ -3152,11 +3159,6 @@ async def completion(
             llm_response = asyncio.create_task(llm_router.atext_completion(**data))
         elif user_model is not None:  # `litellm --model <your-model-name>`
             llm_response = asyncio.create_task(litellm.atext_completion(**data))
-        elif (
-            llm_router is not None
-            and llm_router.router_general_settings.pass_through_all_models is True
-        ):
-            llm_response = asyncio.create_task(litellm.atext_completion(**data))
         else:
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
@@ -3412,14 +3414,15 @@ async def embeddings(
         elif (
             llm_router is not None
             and data["model"] not in router_model_names
-            and llm_router.default_deployment is not None
-        ):  # model in router deployments, calling a specific deployment on the router
-            tasks.append(llm_router.aembedding(**data))
-        elif (
-            llm_router is not None
             and llm_router.router_general_settings.pass_through_all_models is True
         ):
             tasks.append(litellm.aembedding(**data))
+        elif (
+            llm_router is not None
+            and data["model"] not in router_model_names
+            and llm_router.default_deployment is not None
+        ):  # model in router deployments, calling a specific deployment on the router
+            tasks.append(llm_router.aembedding(**data))
         elif user_model is not None:  # `litellm --model <your-model-name>`
             tasks.append(litellm.aembedding(**data))
         else: