diff --git a/libs/langchain_v1/langchain/chat_models/base.py b/libs/langchain_v1/langchain/chat_models/base.py
index b5f7cec785b..977cfffac6d 100644
--- a/libs/langchain_v1/langchain/chat_models/base.py
+++ b/libs/langchain_v1/langchain/chat_models/base.py
@@ -449,6 +449,13 @@ def init_chat_model(
         ```
 
     """  # noqa: E501
+    if model is not None and not isinstance(model, str):
+        msg = (  # type: ignore[unreachable]
+            f"`model` must be a string (e.g., 'openai:gpt-4o'), got "
+            f"{type(model).__name__}. If you've already constructed a chat model "
+            f"object, use it directly instead of passing it to init_chat_model()."
+        )
+        raise TypeError(msg)
     if not model and not configurable_fields:
         configurable_fields = ("model", "model_provider")
     config_prefix = config_prefix or ""
diff --git a/libs/langchain_v1/tests/unit_tests/chat_models/test_chat_models.py b/libs/langchain_v1/tests/unit_tests/chat_models/test_chat_models.py
index 33dd48b4540..51449b4c3d2 100644
--- a/libs/langchain_v1/tests/unit_tests/chat_models/test_chat_models.py
+++ b/libs/langchain_v1/tests/unit_tests/chat_models/test_chat_models.py
@@ -3,6 +3,7 @@ from typing import TYPE_CHECKING
 from unittest import mock
 
 import pytest
+from langchain_core.language_models.fake_chat_models import FakeChatModel
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.runnables import RunnableConfig, RunnableSequence
 from pydantic import SecretStr
@@ -52,6 +53,12 @@ def test_init_chat_model(model_name: str, model_provider: str | None) -> None:
     assert llm1.dict() == llm2.dict()
 
 
+def test_init_chat_model_rejects_model_object() -> None:
+    """Passing a model object instead of a string should raise TypeError."""
+    with pytest.raises(TypeError, match="must be a string"):
+        init_chat_model(model=FakeChatModel())  # type: ignore[call-overload]
+
+
 def test_init_missing_dep() -> None:
     with pytest.raises(ImportError):
         init_chat_model("mixtral-8x7b-32768", model_provider="groq")