diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index ac9c4d897e..c4098f31b1 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index 43308aa168..7a20c6cb2e 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -40,7 +40,8 @@ def test_completion_cohere_stream():
         # Add any assertions here to check the response
         for chunk in response:
             print(f"chunk: {chunk}")
-            complete_response += chunk["choices"][0]["delta"]["content"]
+            if "content" in chunk["choices"][0]["delta"]:
+                complete_response += chunk["choices"][0]["delta"]["content"]
         if complete_response == "": 
             raise Exception("Empty response received")
         print(f"completion_response: {complete_response}")
@@ -79,7 +80,8 @@ def test_openai_text_completion_call():
         for chunk in response:
             chunk_time = time.time()
             print(f"chunk: {chunk}")
-            complete_response += chunk["choices"][0]["delta"]["content"]
+            if "content" in chunk["choices"][0]["delta"]:
+                complete_response += chunk["choices"][0]["delta"]["content"]
         if complete_response == "": 
             raise Exception("Empty response received")
     except:
@@ -98,15 +100,15 @@ def ai21_completion_call():
         for chunk in response:
             chunk_time = time.time()
             print(f"time since initial request: {chunk_time - start_time:.5f}")
-            print(chunk["choices"][0]["delta"])
-            complete_response += chunk["choices"][0]["delta"]["content"]
+            print(chunk)
+            if "content" in chunk["choices"][0]["delta"]:
+                complete_response += chunk["choices"][0]["delta"]["content"]
         if complete_response == "": 
             raise Exception("Empty response received")
     except:
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
-ai21_completion_call()
 # test on openai completion call
 def test_openai_chat_completion_call():
     try:
@@ -118,14 +120,16 @@ def test_openai_chat_completion_call():
         for chunk in response:
             chunk_time = time.time() 
             print(f"time since initial request: {chunk_time - start_time:.5f}")
-            print(chunk["choices"][0]["delta"])
-            complete_response += chunk["choices"][0]["delta"]["content"]
+            print(chunk)
+            if "content" in chunk["choices"][0]["delta"]:
+                complete_response += chunk["choices"][0]["delta"]["content"]
         if complete_response == "": 
             raise Exception("Empty response received")
     except:
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
+# test_openai_chat_completion_call()
 async def completion_call():
     try:
         response = completion(
@@ -139,7 +143,8 @@ async def completion_call():
             chunk_time = time.time()
             print(f"time since initial request: {chunk_time - start_time:.5f}")
             print(chunk["choices"][0]["delta"])
-            complete_response += chunk["choices"][0]["delta"]["content"]
+            if "content" in chunk["choices"][0]["delta"]:
+                complete_response += chunk["choices"][0]["delta"]["content"]
         if complete_response == "": 
             raise Exception("Empty response received")
     except:
@@ -205,6 +210,8 @@ def test_together_ai_completion_call_replit():
             )
         if complete_response == "":
             raise Exception("Empty response received")
+    except KeyError as e:
+        pass
     except:
         print(f"error occurred: {traceback.format_exc()}")
         pass
@@ -232,6 +239,8 @@ def test_together_ai_completion_call_starcoder():
                 print(complete_response)
         if complete_response == "":
             raise Exception("Empty response received")
+    except KeyError as e:
+        pass
     except:
         print(f"error occurred: {traceback.format_exc()}")
         pass
@@ -281,6 +290,8 @@ async def ai21_async_completion_call():
             complete_response += chunk["choices"][0]["delta"]["content"]
         if complete_response == "": 
             raise Exception("Empty response received")
+    except KeyError as e:
+        pass
     except:
         print(f"error occurred: {traceback.format_exc()}")
         pass
\ No newline at end of file
diff --git a/litellm/utils.py b/litellm/utils.py
index e3547dc1c6..20206461a1 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -103,7 +103,7 @@ class Choices(OpenAIObject):
         self.message = message
 
 class StreamingChoices(OpenAIObject):
-    def __init__(self, finish_reason="stop", index=0, delta=Delta(), **params):
+    def __init__(self, finish_reason=None, index=0, delta: Optional[Delta]={}, **params):
         super(StreamingChoices, self).__init__(**params)
         self.finish_reason = finish_reason
         self.index = index
@@ -2493,7 +2493,10 @@ class CustomStreamWrapper:
             model_response.choices[0].delta = completion_obj
             return model_response
         except Exception as e:
-            raise StopIteration
+            model_response = ModelResponse(stream=True)
+            model_response.choices[0].finish_reason = "stop"
+            return model_response
+            # raise StopIteration
     
     async def __anext__(self):
         try:
diff --git a/pyproject.toml b/pyproject.toml
index dd424cb157..5e62451466 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.632"
+version = "0.1.633"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"