diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 55052761c7..760a7c7842 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -7058,6 +7058,17 @@
         "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
         "supports_tool_choice": true
     },
+    "command-a-03-2025": {
+        "max_tokens": 8000,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 8000,
+        "input_cost_per_token": 0.0000025,
+        "output_cost_per_token": 0.00001,
+        "litellm_provider": "cohere_chat",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
     "command-r": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,
diff --git a/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py b/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py
index f87444141e..1da0e740a9 100644
--- a/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py
+++ b/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py
@@ -73,7 +73,7 @@ def validate_stream_chunk(chunk):
 def test_basic_response():
     client = get_test_client()
     response = client.responses.create(
-        model="gpt-4.0", input="just respond with the word 'ping'"
+        model="gpt-4o", input="just respond with the word 'ping'"
     )
     print("basic response=", response)
 
@@ -97,7 +97,7 @@ def test_basic_response():
 def test_streaming_response():
     client = get_test_client()
     stream = client.responses.create(
-        model="gpt-4.0", input="just respond with the word 'ping'", stream=True
+        model="gpt-4o", input="just respond with the word 'ping'", stream=True
     )
 
     collected_chunks = []
@@ -120,5 +120,5 @@ def test_bad_request_bad_param_error():
     with pytest.raises(BadRequestError):
         # Trigger error with invalid model name
         client.responses.create(
-            model="gpt-4.0", input="This should fail", temperature=2000
+            model="gpt-4o", input="This should fail", temperature=2000
         )