diff --git a/litellm/llms/aleph_alpha.py b/litellm/llms/aleph_alpha.py
index 0e83b76a7..090262461 100644
--- a/litellm/llms/aleph_alpha.py
+++ b/litellm/llms/aleph_alpha.py
@@ -262,11 +262,9 @@ def completion(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 def embedding():
diff --git a/litellm/llms/baseten.py b/litellm/llms/baseten.py
index aecacd84f..05abb0005 100644
--- a/litellm/llms/baseten.py
+++ b/litellm/llms/baseten.py
@@ -136,11 +136,9 @@ def completion(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 def embedding():
diff --git a/litellm/llms/cohere.py b/litellm/llms/cohere.py
index cd6032c56..c5fb4cf56 100644
--- a/litellm/llms/cohere.py
+++ b/litellm/llms/cohere.py
@@ -179,11 +179,9 @@ def completion(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 def embedding(
diff --git a/litellm/llms/huggingface_restapi.py b/litellm/llms/huggingface_restapi.py
index b3c3e5e38..496cbc3c9 100644
--- a/litellm/llms/huggingface_restapi.py
+++ b/litellm/llms/huggingface_restapi.py
@@ -345,11 +345,9 @@ def completion(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 
diff --git a/litellm/llms/nlp_cloud.py b/litellm/llms/nlp_cloud.py
index b12c23ff5..a4647bc08 100644
--- a/litellm/llms/nlp_cloud.py
+++ b/litellm/llms/nlp_cloud.py
@@ -171,11 +171,9 @@ def completion(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 def embedding():
diff --git a/litellm/llms/oobabooga.py b/litellm/llms/oobabooga.py
index e49eba422..74f3957be 100644
--- a/litellm/llms/oobabooga.py
+++ b/litellm/llms/oobabooga.py
@@ -111,11 +111,9 @@ def completion(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 def embedding():
diff --git a/litellm/llms/replicate.py b/litellm/llms/replicate.py
index 0912af5c0..afa56d978 100644
--- a/litellm/llms/replicate.py
+++ b/litellm/llms/replicate.py
@@ -240,11 +240,9 @@ def completion(
         prompt_tokens = len(encoding.encode(prompt))
         completion_tokens = len(encoding.encode(model_response["choices"][0]["message"].get("content", "")))
         model_response["model"] = "replicate/" + model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 
diff --git a/litellm/llms/together_ai.py b/litellm/llms/together_ai.py
index 9fc48b4f6..f49cd13b7 100644
--- a/litellm/llms/together_ai.py
+++ b/litellm/llms/together_ai.py
@@ -175,11 +175,9 @@ def completion(
             model_response.choices[0].finish_reason = completion_response["output"]["choices"][0]["finish_reason"]
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 def embedding():
diff --git a/litellm/llms/vllm.py b/litellm/llms/vllm.py
index 379d54ae8..7519c381f 100644
--- a/litellm/llms/vllm.py
+++ b/litellm/llms/vllm.py
@@ -90,11 +90,9 @@ def completion(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         return model_response
 
 def batch_completions(
@@ -172,11 +170,9 @@ def batch_completions(
 
         model_response["created"] = time.time()
         model_response["model"] = model
-        model_response["usage"] = {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        }
+        model_response.usage.completion_tokens = completion_tokens
+        model_response.usage.prompt_tokens = prompt_tokens
+        model_response.usage.total_tokens = prompt_tokens + completion_tokens
         final_outputs.append(model_response)
     return final_outputs