diff --git a/litellm/llms/azure.py b/litellm/llms/azure.py
index f1a882bb2e..f07dc60cf2 100644
--- a/litellm/llms/azure.py
+++ b/litellm/llms/azure.py
@@ -1130,7 +1130,8 @@ class AzureChatCompletion(BaseLLM):
             else:
                 azure_client = client
             ## COMPLETION CALL
-            response = azure_client.embeddings.with_raw_response.create(**data, timeout=timeout)  # type: ignore
+            raw_response = azure_client.embeddings.with_raw_response.create(**data, timeout=timeout)  # type: ignore
+            response = raw_response.parse()
             ## LOGGING
             logging_obj.post_call(
                 input=input,
diff --git a/litellm/llms/openai.py b/litellm/llms/openai.py
index 5c48eef4dd..d62e89f8af 100644
--- a/litellm/llms/openai.py
+++ b/litellm/llms/openai.py
@@ -2126,7 +2126,8 @@ class OpenAITextCompletion(BaseLLM):
             openai_client = client
 
         try:
-            response = openai_client.completions.with_raw_response.create(**data)
+            raw_response = openai_client.completions.with_raw_response.create(**data)
+            response = raw_response.parse()
         except Exception as e:
             status_code = getattr(e, "status_code", 500)
             error_headers = getattr(e, "headers", None)
@@ -2170,8 +2171,8 @@ class OpenAITextCompletion(BaseLLM):
         else:
             openai_client = client
 
-        response = await openai_client.completions.with_raw_response.create(**data)
-
+        raw_response = await openai_client.completions.with_raw_response.create(**data)
+        response = raw_response.parse()
         streamwrapper = CustomStreamWrapper(
             completion_stream=response,
             model=model,