diff --git a/src/crewai/agent.py b/src/crewai/agent.py
index 999d1d800..074611542 100644
--- a/src/crewai/agent.py
+++ b/src/crewai/agent.py
@@ -196,9 +196,11 @@ class Agent(BaseAgent):
         else:
             # For any other type, attempt to extract relevant attributes
             llm_params = {
-                "model": getattr(self.llm, "model_name", None)
-                or getattr(self.llm, "deployment_name", None)
-                or str(self.llm),
+                "model": self._normalize_model_name(
+                    getattr(self.llm, "model_name", None)
+                    or getattr(self.llm, "deployment_name", None)
+                    or str(self.llm)
+                ),
                 "temperature": getattr(self.llm, "temperature", None),
                 "max_tokens": getattr(self.llm, "max_tokens", None),
                 "logprobs": getattr(self.llm, "logprobs", None),
@@ -534,5 +536,14 @@ class Agent(BaseAgent):
     def __tools_names(tools) -> str:
         return ", ".join([t.name for t in tools])
 
+    def _normalize_model_name(self, model_name):
+        """
+        Normalize the model name by removing any 'models/' prefix.
+        This fixes the issue with ChatGoogleGenerativeAI and potentially other LLM providers.
+        """
+        if model_name and isinstance(model_name, str) and model_name.startswith("models/"):
+            return model_name[7:]  # Remove "models/" prefix
+        return model_name
+
     def __repr__(self):
         return f"Agent(role={self.role}, goal={self.goal}, backstory={self.backstory})"
diff --git a/tests/test_agent_model_name.py b/tests/test_agent_model_name.py
new file mode 100644
index 000000000..14642d74e
--- /dev/null
+++ b/tests/test_agent_model_name.py
@@ -0,0 +1,39 @@
+import pytest
+from unittest.mock import MagicMock, patch
+from crewai import Agent
+from crewai.llm import LLM
+
+
+def test_normalize_model_name_method():
+    """Test that the _normalize_model_name method correctly handles model names with 'models/' prefix"""
+    agent = Agent(
+        role="Test Agent",
+        goal="Test goal",
+        backstory="Test backstory",
+        llm="gpt-4"
+    )
+    
+    model_with_prefix = "models/gemini/gemini-1.5-flash"
+    normalized_name = agent._normalize_model_name(model_with_prefix)
+    assert normalized_name == "gemini/gemini-1.5-flash"
+    
+    regular_model = "gpt-4"
+    assert agent._normalize_model_name(regular_model) == "gpt-4"
+    
+    assert agent._normalize_model_name(None) is None
+    
+    assert agent._normalize_model_name(123) == 123
+
+
+def test_agent_with_regular_model_name():
+    """Test that the Agent class doesn't modify normal model names"""
+    with patch('crewai.agent.LLM') as mock_llm:
+        agent = Agent(
+            role="Test Agent",
+            goal="Test goal",
+            backstory="Test backstory",
+            llm="gpt-4"
+        )
+        
+        args, kwargs = mock_llm.call_args
+        assert kwargs["model"] == "gpt-4"