diff --git a/litellm/llms/ollama.py b/litellm/llms/ollama.py
index b0d06ef62..5a0b450c7 100644
--- a/litellm/llms/ollama.py
+++ b/litellm/llms/ollama.py
@@ -137,13 +137,14 @@ def get_ollama_response(
         additional_args={"api_base": url, "complete_input_dict": data, "headers": {},  "acompletion": acompletion,},
     )
     if acompletion is True: 
-        if optional_params.get("stream", False):
+        if optional_params.get("stream", False) == True:
             response = ollama_async_streaming(url=url, data=data, model_response=model_response, encoding=encoding, logging_obj=logging_obj)
         else:
             response = ollama_acompletion(url=url, data=data, model_response=model_response, encoding=encoding, logging_obj=logging_obj)
         return response
-    elif optional_params.get("stream", False):
+    elif optional_params.get("stream", False) == True:
         return ollama_completion_stream(url=url, data=data, logging_obj=logging_obj)
+    
     response = requests.post(
                     url=f"{url}",
                     json=data,
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index 8cecd270a..b46fb0099 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -571,6 +571,22 @@ def test_completion_openai_litellm_key():
 
 # test_completion_openai_litellm_key()
 
+def test_completion_ollama_hosted(): 
+    try:
+        litellm.set_verbose = True
+        response = completion(
+            model="ollama/phi",
+            messages=messages,
+            max_tokens=10,
+            api_base="https://test-ollama-endpoint.onrender.com"
+        )
+        # Add any assertions here to check the response
+        print(response)
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+# test_completion_ollama_hosted()
+
 def test_completion_openrouter1():
     try:
         response = completion(
@@ -626,7 +642,7 @@ def test_completion_anyscale_with_functions():
         print(response)
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
-test_completion_anyscale_with_functions()
+# test_completion_anyscale_with_functions()
 
 def test_completion_azure_key_completion_arg():
     # this tests if we can pass api_key to completion, when it's not in the env 
diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index 8e6bd346f..2dfd5778a 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -276,6 +276,33 @@ def test_completion_azure_function_calling_stream():
 
 # test_completion_azure_function_calling_stream()
 
+def test_completion_ollama_hosted_stream(): 
+    try:
+        litellm.set_verbose = True
+        response = completion(
+            model="ollama/phi",
+            messages=messages,
+            max_tokens=10,
+            api_base="https://test-ollama-endpoint.onrender.com",
+            stream=True
+        )
+        # Add any assertions here to check the response
+        complete_response = ""
+        # Add any assertions here to check the response
+        for idx, init_chunk in enumerate(response):
+            chunk, finished = streaming_format_tests(idx, init_chunk)
+            complete_response += chunk
+            if finished:
+                assert isinstance(init_chunk.choices[0], litellm.utils.StreamingChoices)
+                break
+        if complete_response.strip() == "": 
+            raise Exception("Empty response received")
+        print(f"complete_response: {complete_response}")
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+# test_completion_ollama_hosted_stream()
+
 def test_completion_claude_stream():
     try:
         messages = [