fix(main.py): route vllm calls via the openai sdk route

consistent with other openai-like implementations

litellm/llms/openai/transcriptions/handler.py

@@ -34,6 +34,7 @@ class OpenAIAudioTranscription(OpenAIChatCompletion):
         - call openai_aclient.audio.transcriptions.create by default
         """
         try:
+
             raw_response = (
                 await openai_aclient.audio.transcriptions.with_raw_response.create(
                     **data, timeout=timeout

litellm/llms/openai/transcriptions/whisper_transformation.py

@@ -18,6 +18,34 @@ from ..common_utils import OpenAIError
 
 
 class OpenAIWhisperAudioTranscriptionConfig(BaseAudioTranscriptionConfig):
+    def get_complete_url(
+        self,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        model: str,
+        optional_params: dict,
+        litellm_params: dict,
+        stream: Optional[bool] = None,
+    ) -> str:
+        """
+        OPTIONAL
+
+        Get the complete url for the request
+
+        Some providers need `model` in `api_base`
+        """
+        ## get the api base, attach the endpoint - v1/audio/transcriptions
+        # strip trailing slash if present
+        api_base = api_base.rstrip("/") if api_base else ""
+
+        # if endswith "/v1"
+        if api_base and api_base.endswith("/v1"):
+            api_base = f"{api_base}/audio/transcriptions"
+        else:
+            api_base = f"{api_base}/v1/audio/transcriptions"
+
+        return api_base or ""
+
     def get_supported_openai_params(
         self, model: str
     ) -> List[OpenAIAudioTranscriptionOptionalParams]:
@@ -77,7 +105,6 @@ class OpenAIWhisperAudioTranscriptionConfig(BaseAudioTranscriptionConfig):
         """
         Transform the audio transcription request
         """
-
         data = {"model": model, "file": audio_file, **optional_params}
 
         if "response_format" not in data or (

litellm/main.py

@@ -5267,7 +5267,10 @@ def transcription(
     model_response = litellm.utils.TranscriptionResponse()
 
     model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(
-        model=model, custom_llm_provider=custom_llm_provider, api_base=api_base
+        model=model,
+        custom_llm_provider=custom_llm_provider,
+        api_base=api_base,
+        api_key=api_key,
     )  # type: ignore
 
     if dynamic_api_key is not None:
@@ -5283,6 +5286,7 @@ def transcription(
         custom_llm_provider=custom_llm_provider,
         **non_default_params,
     )
+
     litellm_params_dict = get_litellm_params(**kwargs)
 
     litellm_logging_obj.update_environment_variables(
@@ -5349,7 +5353,6 @@ def transcription(
         )
     elif custom_llm_provider == "openai" or (
         custom_llm_provider in litellm.openai_compatible_providers
-        and provider_config is None
     ):
         api_base = (
             api_base
@@ -5364,6 +5367,7 @@ def transcription(
             or None  # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105
         )
         # set API KEY
+
         api_key = api_key or litellm.api_key or litellm.openai_key or get_secret("OPENAI_API_KEY")  # type: ignore
         response = openai_audio_transcriptions.audio_transcriptions(
             model=model,

litellm/proxy/_new_secret_config.yaml

@@ -10,3 +10,11 @@ model_list:
   - model_name: xai-grok-3
     litellm_params:
       model: xai/grok-3
+  - model_name: hosted_vllm/whisper-v3
+    litellm_params:
+      model: hosted_vllm/whisper-v3
+      api_base: "https://webhook.site/2f385e05-00aa-402b-86d1-efc9261471a5"
+      api_key: dummy
+
+
+

litellm/utils.py

@@ -2428,6 +2428,8 @@ def get_optional_params_transcription(
 
     # retrieve all parameters passed to the function
     passed_params = locals()
+
+    passed_params.pop("OPENAI_TRANSCRIPTION_PARAMS")
     custom_llm_provider = passed_params.pop("custom_llm_provider")
     drop_params = passed_params.pop("drop_params")
     special_params = passed_params.pop("kwargs")
@@ -2492,6 +2494,7 @@ def get_optional_params_transcription(
             model=model,
             drop_params=drop_params if drop_params is not None else False,
         )
+
     optional_params = add_provider_specific_params_to_optional_params(
         optional_params=optional_params,
         passed_params=passed_params,
@@ -4089,6 +4092,7 @@ def add_provider_specific_params_to_optional_params(
     """
     Add provider specific params to optional_params
     """
+
     if (
         custom_llm_provider
         in ["openai", "azure", "text-completion-openai"]