diff --git a/libs/cli/langchain_cli/integration_template/README.md b/libs/cli/langchain_cli/integration_template/README.md
index f8d70df8005..15741c62f85 100644
--- a/libs/cli/langchain_cli/integration_template/README.md
+++ b/libs/cli/langchain_cli/integration_template/README.md
@@ -19,8 +19,8 @@ And you should configure credentials by setting the following environment variab
 ```python
 from __module_name__ import Chat__ModuleName__
 
-llm = Chat__ModuleName__()
-llm.invoke("Sing a ballad of LangChain.")
+model = Chat__ModuleName__()
+model.invoke("Sing a ballad of LangChain.")
 ```
 
 ## Embeddings
@@ -41,6 +41,6 @@ embeddings.embed_query("What is the meaning of life?")
 ```python
 from __module_name__ import __ModuleName__LLM
 
-llm = __ModuleName__LLM()
-llm.invoke("The meaning of life is")
+model = __ModuleName__LLM()
+model.invoke("The meaning of life is")
 ```
diff --git a/libs/cli/langchain_cli/integration_template/docs/chat.ipynb b/libs/cli/langchain_cli/integration_template/docs/chat.ipynb
index 86221b5fc63..ff6e4d8cab2 100644
--- a/libs/cli/langchain_cli/integration_template/docs/chat.ipynb
+++ b/libs/cli/langchain_cli/integration_template/docs/chat.ipynb
@@ -72,7 +72,9 @@
    "cell_type": "markdown",
    "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
    "metadata": {},
-   "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+   "source": [
+    "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+   ]
   },
   {
    "cell_type": "code",
@@ -126,7 +128,7 @@
    "source": [
     "from __module_name__ import Chat__ModuleName__\n",
     "\n",
-    "llm = Chat__ModuleName__(\n",
+    "model = Chat__ModuleName__(\n",
     "    model=\"model-name\",\n",
     "    temperature=0,\n",
     "    max_tokens=None,\n",
@@ -162,7 +164,7 @@
     "    ),\n",
     "    (\"human\", \"I love programming.\"),\n",
     "]\n",
-    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg = model.invoke(messages)\n",
     "ai_msg"
    ]
   },
@@ -207,7 +209,7 @@
     "    ]\n",
     ")\n",
     "\n",
-    "chain = prompt | llm\n",
+    "chain = prompt | model\n",
     "chain.invoke(\n",
     "    {\n",
     "        \"input_language\": \"English\",\n",
diff --git a/libs/cli/langchain_cli/integration_template/docs/llms.ipynb b/libs/cli/langchain_cli/integration_template/docs/llms.ipynb
index 217929fff71..eb58d4fafbf 100644
--- a/libs/cli/langchain_cli/integration_template/docs/llms.ipynb
+++ b/libs/cli/langchain_cli/integration_template/docs/llms.ipynb
@@ -65,7 +65,9 @@
    "cell_type": "markdown",
    "id": "4b6e1ca6",
    "metadata": {},
-   "source": "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+   "source": [
+    "To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:"
+   ]
   },
   {
    "cell_type": "code",
@@ -119,7 +121,7 @@
    "source": [
     "from __module_name__ import __ModuleName__LLM\n",
     "\n",
-    "llm = __ModuleName__LLM(\n",
+    "model = __ModuleName__LLM(\n",
     "    model=\"model-name\",\n",
     "    temperature=0,\n",
     "    max_tokens=None,\n",
@@ -141,7 +143,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "035dea0f",
    "metadata": {
     "tags": []
@@ -150,7 +152,7 @@
    "source": [
     "input_text = \"__ModuleName__ is an AI company that \"\n",
     "\n",
-    "completion = llm.invoke(input_text)\n",
+    "completion = model.invoke(input_text)\n",
     "completion"
    ]
   },
@@ -177,7 +179,7 @@
     "\n",
     "prompt = PromptTemplate(\"How to say {input} in {output_language}:\\n\")\n",
     "\n",
-    "chain = prompt | llm\n",
+    "chain = prompt | model\n",
     "chain.invoke(\n",
     "    {\n",
     "        \"output_language\": \"German\",\n",
diff --git a/libs/cli/langchain_cli/integration_template/docs/retrievers.ipynb b/libs/cli/langchain_cli/integration_template/docs/retrievers.ipynb
index 300d3d87958..254633bdf23 100644
--- a/libs/cli/langchain_cli/integration_template/docs/retrievers.ipynb
+++ b/libs/cli/langchain_cli/integration_template/docs/retrievers.ipynb
@@ -155,7 +155,7 @@
     "\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
    ]
   },
   {
@@ -185,7 +185,7 @@
     "chain = (\n",
     "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
     "    | prompt\n",
-    "    | llm\n",
+    "    | model\n",
     "    | StrOutputParser()\n",
     ")"
    ]
diff --git a/libs/cli/langchain_cli/integration_template/docs/tools.ipynb b/libs/cli/langchain_cli/integration_template/docs/tools.ipynb
index a160b95658a..97853ad8669 100644
--- a/libs/cli/langchain_cli/integration_template/docs/tools.ipynb
+++ b/libs/cli/langchain_cli/integration_template/docs/tools.ipynb
@@ -192,7 +192,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "id": "af3123ad-7a02-40e5-b58e-7d56e23e5830",
    "metadata": {},
    "outputs": [],
@@ -203,7 +203,7 @@
     "# !pip install -qU langchain langchain-openai\n",
     "from langchain.chat_models import init_chat_model\n",
     "\n",
-    "llm = init_chat_model(model=\"gpt-4o\", model_provider=\"openai\")"
+    "model = init_chat_model(model=\"gpt-4o\", model_provider=\"openai\")"
    ]
   },
   {
@@ -216,7 +216,7 @@
     "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "tools = [tool]\n",
-    "agent = create_react_agent(llm, tools)"
+    "agent = create_react_agent(model, tools)"
    ]
   },
   {
diff --git a/libs/cli/langchain_cli/integration_template/integration_template/chat_models.py b/libs/cli/langchain_cli/integration_template/integration_template/chat_models.py
index 0e077cd4856..fedf46fb95d 100644
--- a/libs/cli/langchain_cli/integration_template/integration_template/chat_models.py
+++ b/libs/cli/langchain_cli/integration_template/integration_template/chat_models.py
@@ -60,7 +60,7 @@ class Chat__ModuleName__(BaseChatModel):
         ```python
         from __module_name__ import Chat__ModuleName__
 
-        llm = Chat__ModuleName__(
+        model = Chat__ModuleName__(
             model="...",
             temperature=0,
             max_tokens=None,
@@ -77,7 +77,7 @@ class Chat__ModuleName__(BaseChatModel):
             ("system", "You are a helpful translator. Translate the user sentence to French."),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
         ```python
@@ -87,7 +87,7 @@ class Chat__ModuleName__(BaseChatModel):
     # TODO: Delete if token-level streaming isn't supported.
     Stream:
         ```python
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.text, end="")
         ```
 
@@ -96,7 +96,7 @@ class Chat__ModuleName__(BaseChatModel):
         ```
 
         ```python
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -110,13 +110,13 @@ class Chat__ModuleName__(BaseChatModel):
     # TODO: Delete if native async isn't supported.
     Async:
         ```python
-        await llm.ainvoke(messages)
+        await model.ainvoke(messages)
 
         # stream:
-        # async for chunk in (await llm.astream(messages))
+        # async for chunk in (await model.astream(messages))
 
         # batch:
-        # await llm.abatch([messages])
+        # await model.abatch([messages])
         ```
 
         ```python
@@ -137,8 +137,8 @@ class Chat__ModuleName__(BaseChatModel):
 
             location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
 
-        llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
-        ai_msg = llm_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
+        model_with_tools = model.bind_tools([GetWeather, GetPopulation])
+        ai_msg = model_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
         ai_msg.tool_calls
         ```
 
@@ -162,8 +162,8 @@ class Chat__ModuleName__(BaseChatModel):
             punchline: str = Field(description="The punchline to the joke")
             rating: int | None = Field(description="How funny the joke is, from 1 to 10")
 
-        structured_llm = llm.with_structured_output(Joke)
-        structured_llm.invoke("Tell me a joke about cats")
+        structured_model = model.with_structured_output(Joke)
+        structured_model.invoke("Tell me a joke about cats")
         ```
 
         ```python
@@ -176,8 +176,8 @@ class Chat__ModuleName__(BaseChatModel):
     JSON mode:
         ```python
         # TODO: Replace with appropriate bind arg.
-        json_llm = llm.bind(response_format={"type": "json_object"})
-        ai_msg = json_llm.invoke("Return a JSON object with key 'random_ints' and a value of 10 random ints in [0-99]")
+        json_model = model.bind(response_format={"type": "json_object"})
+        ai_msg = json_model.invoke("Return a JSON object with key 'random_ints' and a value of 10 random ints in [0-99]")
         ai_msg.content
         ```
 
@@ -204,7 +204,7 @@ class Chat__ModuleName__(BaseChatModel):
                 },
             ],
         )
-        ai_msg = llm.invoke([message])
+        ai_msg = model.invoke([message])
         ai_msg.content
         ```
 
@@ -235,7 +235,7 @@ class Chat__ModuleName__(BaseChatModel):
     # TODO: Delete if token usage metadata isn't supported.
     Token usage:
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.usage_metadata
         ```
 
@@ -247,8 +247,8 @@ class Chat__ModuleName__(BaseChatModel):
     Logprobs:
         ```python
         # TODO: Replace with appropriate bind arg.
-        logprobs_llm = llm.bind(logprobs=True)
-        ai_msg = logprobs_llm.invoke(messages)
+        logprobs_model = model.bind(logprobs=True)
+        ai_msg = logprobs_model.invoke(messages)
         ai_msg.response_metadata["logprobs"]
         ```
 
@@ -257,7 +257,7 @@ class Chat__ModuleName__(BaseChatModel):
         ```
     Response metadata
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.response_metadata
         ```
 
diff --git a/libs/cli/langchain_cli/integration_template/integration_template/retrievers.py b/libs/cli/langchain_cli/integration_template/integration_template/retrievers.py
index 48c5f735788..d4c6a966bfc 100644
--- a/libs/cli/langchain_cli/integration_template/integration_template/retrievers.py
+++ b/libs/cli/langchain_cli/integration_template/integration_template/retrievers.py
@@ -65,7 +65,7 @@ class __ModuleName__Retriever(BaseRetriever):
         Question: {question}\"\"\"
         )
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125")
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125")
 
         def format_docs(docs):
             return "\\n\\n".join(doc.page_content for doc in docs)
@@ -73,7 +73,7 @@ class __ModuleName__Retriever(BaseRetriever):
         chain = (
             {"context": retriever | format_docs, "question": RunnablePassthrough()}
             | prompt
-            | llm
+            | model
             | StrOutputParser()
         )
 
diff --git a/libs/core/langchain_core/language_models/chat_models.py b/libs/core/langchain_core/language_models/chat_models.py
index d13a081520c..67ec50e8207 100644
--- a/libs/core/langchain_core/language_models/chat_models.py
+++ b/libs/core/langchain_core/language_models/chat_models.py
@@ -1555,10 +1555,10 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
                 justification: str
 
 
-            llm = ChatModel(model="model-name", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatModel(model="model-name", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
 
@@ -1580,12 +1580,12 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
                 justification: str
 
 
-            llm = ChatModel(model="model-name", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatModel(model="model-name", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -1609,10 +1609,10 @@ class BaseChatModel(BaseLanguageModel[AIMessage], ABC):
 
 
             dict_schema = convert_to_openai_tool(AnswerWithJustification)
-            llm = ChatModel(model="model-name", temperature=0)
-            structured_llm = llm.with_structured_output(dict_schema)
+            model = ChatModel(model="model-name", temperature=0)
+            structured_model = model.with_structured_output(dict_schema)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
diff --git a/libs/core/langchain_core/runnables/base.py b/libs/core/langchain_core/runnables/base.py
index 842ed35f824..91b6ef1c5f4 100644
--- a/libs/core/langchain_core/runnables/base.py
+++ b/libs/core/langchain_core/runnables/base.py
@@ -776,11 +776,11 @@ class Runnable(ABC, Generic[Input, Output]):
             SystemMessagePromptTemplate.from_template("You are a nice assistant.")
             + "{question}"
         )
-        llm = FakeStreamingListLLM(responses=["foo-lish"])
+        model = FakeStreamingListLLM(responses=["foo-lish"])
 
-        chain: Runnable = prompt | llm | {"str": StrOutputParser()}
+        chain: Runnable = prompt | model | {"str": StrOutputParser()}
 
-        chain_with_assign = chain.assign(hello=itemgetter("str") | llm)
+        chain_with_assign = chain.assign(hello=itemgetter("str") | model)
 
         print(chain_with_assign.input_schema.model_json_schema())
         # {'title': 'PromptInput', 'type': 'object', 'properties':
@@ -1598,16 +1598,16 @@ class Runnable(ABC, Generic[Input, Output]):
             from langchain_ollama import ChatOllama
             from langchain_core.output_parsers import StrOutputParser
 
-            llm = ChatOllama(model="llama3.1")
+            model = ChatOllama(model="llama3.1")
 
             # Without bind
-            chain = llm | StrOutputParser()
+            chain = model | StrOutputParser()
 
             chain.invoke("Repeat quoted words exactly: 'One two three four five.'")
             # Output is 'One two three four five.'
 
             # With bind
-            chain = llm.bind(stop=["three"]) | StrOutputParser()
+            chain = model.bind(stop=["three"]) | StrOutputParser()
 
             chain.invoke("Repeat quoted words exactly: 'One two three four five.'")
             # Output is 'One two'
@@ -6056,10 +6056,10 @@ def chain(
         @chain
         def my_func(fields):
             prompt = PromptTemplate("Hello, {name}!")
-            llm = OpenAI()
+            model = OpenAI()
             formatted = prompt.invoke(**fields)
 
-            for chunk in llm.stream(formatted):
+            for chunk in model.stream(formatted):
                 yield chunk
         ```
     """
diff --git a/libs/core/langchain_core/runnables/fallbacks.py b/libs/core/langchain_core/runnables/fallbacks.py
index 61f1753d8dd..a3794d8ebcb 100644
--- a/libs/core/langchain_core/runnables/fallbacks.py
+++ b/libs/core/langchain_core/runnables/fallbacks.py
@@ -594,7 +594,7 @@ class RunnableWithFallbacks(RunnableSerializable[Input, Output]):
         Returns:
             If the attribute is anything other than a method that outputs a Runnable,
             returns getattr(self.runnable, name). If the attribute is a method that
-            does return a new Runnable (e.g. llm.bind_tools([...]) outputs a new
+            does return a new Runnable (e.g. model.bind_tools([...]) outputs a new
             RunnableBinding) then self.runnable and each of the runnables in
             self.fallbacks is replaced with getattr(x, name).
 
@@ -605,15 +605,15 @@ class RunnableWithFallbacks(RunnableSerializable[Input, Output]):
 
             gpt_4o = ChatOpenAI(model="gpt-4o")
             claude_3_sonnet = ChatAnthropic(model="claude-3-7-sonnet-20250219")
-            llm = gpt_4o.with_fallbacks([claude_3_sonnet])
+            model = gpt_4o.with_fallbacks([claude_3_sonnet])
 
-            llm.model_name
+            model.model_name
             # -> "gpt-4o"
 
             # .bind_tools() is called on both ChatOpenAI and ChatAnthropic
             # Equivalent to:
             # gpt_4o.bind_tools([...]).with_fallbacks([claude_3_sonnet.bind_tools([...])])
-            llm.bind_tools([...])
+            model.bind_tools([...])
             # -> RunnableWithFallbacks(
                 runnable=RunnableBinding(bound=ChatOpenAI(...), kwargs={"tools": [...]}),
                 fallbacks=[RunnableBinding(bound=ChatAnthropic(...), kwargs={"tools": [...]})],
diff --git a/libs/core/tests/unit_tests/tracers/test_run_collector.py b/libs/core/tests/unit_tests/tracers/test_run_collector.py
index 95c0052cf21..17f6a973fce 100644
--- a/libs/core/tests/unit_tests/tracers/test_run_collector.py
+++ b/libs/core/tests/unit_tests/tracers/test_run_collector.py
@@ -7,9 +7,9 @@ from langchain_core.tracers.context import collect_runs
 
 
 def test_collect_runs() -> None:
-    llm = FakeListLLM(responses=["hello"])
+    model = FakeListLLM(responses=["hello"])
     with collect_runs() as cb:
-        llm.invoke("hi")
+        model.invoke("hi")
         assert cb.traced_runs
         assert len(cb.traced_runs) == 1
         assert isinstance(cb.traced_runs[0].id, uuid.UUID)
diff --git a/libs/langchain/langchain_classic/agents/agent_toolkits/vectorstore/base.py b/libs/langchain/langchain_classic/agents/agent_toolkits/vectorstore/base.py
index a8d02d4f03e..d59458e761f 100644
--- a/libs/langchain/langchain_classic/agents/agent_toolkits/vectorstore/base.py
+++ b/libs/langchain/langchain_classic/agents/agent_toolkits/vectorstore/base.py
@@ -58,7 +58,7 @@ def create_vectorstore_agent(
         from langchain_openai import ChatOpenAI, OpenAIEmbeddings
         from langgraph.prebuilt import create_react_agent
 
-        llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+        model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
 
         vector_store = InMemoryVectorStore.from_texts(
             [
@@ -74,7 +74,7 @@ def create_vectorstore_agent(
             "Fetches information about pets.",
         )
 
-        agent = create_react_agent(llm, [tool])
+        agent = create_react_agent(model, [tool])
 
         for step in agent.stream(
             {"messages": [("human", "What are dogs known for?")]},
@@ -156,7 +156,7 @@ def create_vectorstore_router_agent(
         from langchain_openai import ChatOpenAI, OpenAIEmbeddings
         from langgraph.prebuilt import create_react_agent
 
-        llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+        model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
 
         pet_vector_store = InMemoryVectorStore.from_texts(
             [
@@ -187,7 +187,7 @@ def create_vectorstore_router_agent(
             ),
         ]
 
-        agent = create_react_agent(llm, tools)
+        agent = create_react_agent(model, tools)
 
         for step in agent.stream(
             {"messages": [("human", "Tell me about carrots.")]},
diff --git a/libs/langchain/langchain_classic/chains/api/base.py b/libs/langchain/langchain_classic/chains/api/base.py
index ee2e13b2312..830211bf21f 100644
--- a/libs/langchain/langchain_classic/chains/api/base.py
+++ b/libs/langchain/langchain_classic/chains/api/base.py
@@ -143,7 +143,7 @@ try:
                   description: Limit the number of results
         \"\"\"
 
-        llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+        model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
         toolkit = RequestsToolkit(
             requests_wrapper=TextRequestsWrapper(headers={}),  # no auth required
             allow_dangerous_requests=ALLOW_DANGEROUS_REQUESTS,
@@ -152,7 +152,7 @@ try:
 
         api_request_chain = (
             API_URL_PROMPT.partial(api_docs=api_spec)
-            | llm.bind_tools(tools, tool_choice="any")
+            | model.bind_tools(tools, tool_choice="any")
         )
 
         class ChainState(TypedDict):
@@ -169,7 +169,7 @@ try:
             return {"messages": [response]}
 
         async def acall_model(state: ChainState, config: RunnableConfig):
-            response = await llm.ainvoke(state["messages"], config)
+            response = await model.ainvoke(state["messages"], config)
             return {"messages": [response]}
 
         graph_builder = StateGraph(ChainState)
diff --git a/libs/langchain/langchain_classic/chains/combine_documents/map_reduce.py b/libs/langchain/langchain_classic/chains/combine_documents/map_reduce.py
index 99fdf7bc1be..16cd4b9f372 100644
--- a/libs/langchain/langchain_classic/chains/combine_documents/map_reduce.py
+++ b/libs/langchain/langchain_classic/chains/combine_documents/map_reduce.py
@@ -53,16 +53,16 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
             input_variables=["page_content"], template="{page_content}"
         )
         document_variable_name = "context"
-        llm = OpenAI()
+        model = OpenAI()
         # The prompt here should take as an input variable the
         # `document_variable_name`
         prompt = PromptTemplate.from_template("Summarize this content: {context}")
-        llm_chain = LLMChain(llm=llm, prompt=prompt)
+        llm_chain = LLMChain(llm=model, prompt=prompt)
         # We now define how to combine these summaries
         reduce_prompt = PromptTemplate.from_template(
             "Combine these summaries: {context}"
         )
-        reduce_llm_chain = LLMChain(llm=llm, prompt=reduce_prompt)
+        reduce_llm_chain = LLMChain(llm=model, prompt=reduce_prompt)
         combine_documents_chain = StuffDocumentsChain(
             llm_chain=reduce_llm_chain,
             document_prompt=document_prompt,
@@ -79,7 +79,7 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
         # which is specifically aimed at collapsing documents BEFORE
         # the final call.
         prompt = PromptTemplate.from_template("Collapse this content: {context}")
-        llm_chain = LLMChain(llm=llm, prompt=prompt)
+        llm_chain = LLMChain(llm=model, prompt=prompt)
         collapse_documents_chain = StuffDocumentsChain(
             llm_chain=llm_chain,
             document_prompt=document_prompt,
diff --git a/libs/langchain/langchain_classic/chains/combine_documents/map_rerank.py b/libs/langchain/langchain_classic/chains/combine_documents/map_rerank.py
index a712ab6f06b..8d6f3ac5992 100644
--- a/libs/langchain/langchain_classic/chains/combine_documents/map_rerank.py
+++ b/libs/langchain/langchain_classic/chains/combine_documents/map_rerank.py
@@ -42,7 +42,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
         from langchain_classic.output_parsers.regex import RegexParser
 
         document_variable_name = "context"
-        llm = OpenAI()
+        model = OpenAI()
         # The prompt here should take as an input variable the
         # `document_variable_name`
         # The actual prompt will need to be a lot more complex, this is just
@@ -61,7 +61,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
             input_variables=["context"],
             output_parser=output_parser,
         )
-        llm_chain = LLMChain(llm=llm, prompt=prompt)
+        llm_chain = LLMChain(llm=model, prompt=prompt)
         chain = MapRerankDocumentsChain(
             llm_chain=llm_chain,
             document_variable_name=document_variable_name,
diff --git a/libs/langchain/langchain_classic/chains/combine_documents/reduce.py b/libs/langchain/langchain_classic/chains/combine_documents/reduce.py
index 0f86c389ff0..6f546702dae 100644
--- a/libs/langchain/langchain_classic/chains/combine_documents/reduce.py
+++ b/libs/langchain/langchain_classic/chains/combine_documents/reduce.py
@@ -171,11 +171,11 @@ class ReduceDocumentsChain(BaseCombineDocumentsChain):
             input_variables=["page_content"], template="{page_content}"
         )
         document_variable_name = "context"
-        llm = OpenAI()
+        model = OpenAI()
         # The prompt here should take as an input variable the
         # `document_variable_name`
         prompt = PromptTemplate.from_template("Summarize this content: {context}")
-        llm_chain = LLMChain(llm=llm, prompt=prompt)
+        llm_chain = LLMChain(llm=model, prompt=prompt)
         combine_documents_chain = StuffDocumentsChain(
             llm_chain=llm_chain,
             document_prompt=document_prompt,
@@ -188,7 +188,7 @@ class ReduceDocumentsChain(BaseCombineDocumentsChain):
         # which is specifically aimed at collapsing documents BEFORE
         # the final call.
         prompt = PromptTemplate.from_template("Collapse this content: {context}")
-        llm_chain = LLMChain(llm=llm, prompt=prompt)
+        llm_chain = LLMChain(llm=model, prompt=prompt)
         collapse_documents_chain = StuffDocumentsChain(
             llm_chain=llm_chain,
             document_prompt=document_prompt,
diff --git a/libs/langchain/langchain_classic/chains/combine_documents/refine.py b/libs/langchain/langchain_classic/chains/combine_documents/refine.py
index a6d694c63d1..528e86a7e84 100644
--- a/libs/langchain/langchain_classic/chains/combine_documents/refine.py
+++ b/libs/langchain/langchain_classic/chains/combine_documents/refine.py
@@ -55,11 +55,11 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
             input_variables=["page_content"], template="{page_content}"
         )
         document_variable_name = "context"
-        llm = OpenAI()
+        model = OpenAI()
         # The prompt here should take as an input variable the
         # `document_variable_name`
         prompt = PromptTemplate.from_template("Summarize this content: {context}")
-        initial_llm_chain = LLMChain(llm=llm, prompt=prompt)
+        initial_llm_chain = LLMChain(llm=model, prompt=prompt)
         initial_response_name = "prev_response"
         # The prompt here should take as an input variable the
         # `document_variable_name` as well as `initial_response_name`
@@ -67,7 +67,7 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
             "Here's your first summary: {prev_response}. "
             "Now add to it based on the following context: {context}"
         )
-        refine_llm_chain = LLMChain(llm=llm, prompt=prompt_refine)
+        refine_llm_chain = LLMChain(llm=model, prompt=prompt_refine)
         chain = RefineDocumentsChain(
             initial_llm_chain=initial_llm_chain,
             refine_llm_chain=refine_llm_chain,
diff --git a/libs/langchain/langchain_classic/chains/combine_documents/stuff.py b/libs/langchain/langchain_classic/chains/combine_documents/stuff.py
index 5e05d01114e..363d74dcb6f 100644
--- a/libs/langchain/langchain_classic/chains/combine_documents/stuff.py
+++ b/libs/langchain/langchain_classic/chains/combine_documents/stuff.py
@@ -68,8 +68,8 @@ def create_stuff_documents_chain(
         prompt = ChatPromptTemplate.from_messages(
             [("system", "What are everyone's favorite colors:\n\n{context}")]
         )
-        llm = ChatOpenAI(model="gpt-3.5-turbo")
-        chain = create_stuff_documents_chain(llm, prompt)
+        model = ChatOpenAI(model="gpt-3.5-turbo")
+        chain = create_stuff_documents_chain(model, prompt)
 
         docs = [
             Document(page_content="Jesse loves red but not yellow"),
@@ -132,11 +132,11 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
             input_variables=["page_content"], template="{page_content}"
         )
         document_variable_name = "context"
-        llm = OpenAI()
+        model = OpenAI()
         # The prompt here should take as an input variable the
         # `document_variable_name`
         prompt = PromptTemplate.from_template("Summarize this content: {context}")
-        llm_chain = LLMChain(llm=llm, prompt=prompt)
+        llm_chain = LLMChain(llm=model, prompt=prompt)
         chain = StuffDocumentsChain(
             llm_chain=llm_chain,
             document_prompt=document_prompt,
diff --git a/libs/langchain/langchain_classic/chains/constitutional_ai/base.py b/libs/langchain/langchain_classic/chains/constitutional_ai/base.py
index 72bbcbb9323..af8302b34a7 100644
--- a/libs/langchain/langchain_classic/chains/constitutional_ai/base.py
+++ b/libs/langchain/langchain_classic/chains/constitutional_ai/base.py
@@ -58,7 +58,7 @@ class ConstitutionalChain(Chain):
         from langgraph.graph import END, START, StateGraph
         from typing_extensions import Annotated, TypedDict
 
-        llm = ChatOpenAI(model="gpt-4o-mini")
+        model = ChatOpenAI(model="gpt-4o-mini")
 
         class Critique(TypedDict):
             """Generate a critique, if needed."""
@@ -86,9 +86,9 @@ class ConstitutionalChain(Chain):
             "Revision Request: {revision_request}"
         )
 
-        chain = llm | StrOutputParser()
-        critique_chain = critique_prompt | llm.with_structured_output(Critique)
-        revision_chain = revision_prompt | llm | StrOutputParser()
+        chain = model | StrOutputParser()
+        critique_chain = critique_prompt | model.with_structured_output(Critique)
+        revision_chain = revision_prompt | model | StrOutputParser()
 
 
         class State(TypedDict):
@@ -170,16 +170,16 @@ class ConstitutionalChain(Chain):
         from langchain_classic.chains.constitutional_ai.models \
             import ConstitutionalPrinciple
 
-        llm = OpenAI()
+        llmodelm = OpenAI()
 
         qa_prompt = PromptTemplate(
             template="Q: {question} A:",
             input_variables=["question"],
         )
-        qa_chain = LLMChain(llm=llm, prompt=qa_prompt)
+        qa_chain = LLMChain(llm=model, prompt=qa_prompt)
 
         constitutional_chain = ConstitutionalChain.from_llm(
-            llm=llm,
+            llm=model,
             chain=qa_chain,
             constitutional_principles=[
                 ConstitutionalPrinciple(
diff --git a/libs/langchain/langchain_classic/chains/conversation/base.py b/libs/langchain/langchain_classic/chains/conversation/base.py
index 07c1c98ee08..f1c403787de 100644
--- a/libs/langchain/langchain_classic/chains/conversation/base.py
+++ b/libs/langchain/langchain_classic/chains/conversation/base.py
@@ -47,9 +47,9 @@ class ConversationChain(LLMChain):
             return store[session_id]
 
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125")
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125")
 
-        chain = RunnableWithMessageHistory(llm, get_session_history)
+        chain = RunnableWithMessageHistory(model, get_session_history)
         chain.invoke(
             "Hi I'm Bob.",
             config={"configurable": {"session_id": "1"}},
@@ -85,9 +85,9 @@ class ConversationChain(LLMChain):
             return store[session_id]
 
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125")
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125")
 
-        chain = RunnableWithMessageHistory(llm, get_session_history)
+        chain = RunnableWithMessageHistory(model, get_session_history)
         chain.invoke(
             "Hi I'm Bob.",
             config={"configurable": {"session_id": "1"}},
diff --git a/libs/langchain/langchain_classic/chains/conversational_retrieval/base.py b/libs/langchain/langchain_classic/chains/conversational_retrieval/base.py
index d1424619ec4..f327a9d407a 100644
--- a/libs/langchain/langchain_classic/chains/conversational_retrieval/base.py
+++ b/libs/langchain/langchain_classic/chains/conversational_retrieval/base.py
@@ -283,7 +283,7 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
 
     retriever = ...  # Your retriever
 
-    llm = ChatOpenAI()
+    model = ChatOpenAI()
 
     # Contextualize question
     contextualize_q_system_prompt = (
@@ -301,7 +301,7 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
         ]
     )
     history_aware_retriever = create_history_aware_retriever(
-        llm, retriever, contextualize_q_prompt
+        model, retriever, contextualize_q_prompt
     )
 
     # Answer question
@@ -324,7 +324,7 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
     # Below we use create_stuff_documents_chain to feed all retrieved context
     # into the LLM. Note that we can also use StuffDocumentsChain and other
     # instances of BaseCombineDocumentsChain.
-    question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)
+    question_answer_chain = create_stuff_documents_chain(model, qa_prompt)
     rag_chain = create_retrieval_chain(history_aware_retriever, question_answer_chain)
 
     # Usage:
@@ -371,8 +371,8 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
             "Follow up question: {question}"
         )
         prompt = PromptTemplate.from_template(template)
-        llm = OpenAI()
-        question_generator_chain = LLMChain(llm=llm, prompt=prompt)
+        model = OpenAI()
+        question_generator_chain = LLMChain(llm=model, prompt=prompt)
         chain = ConversationalRetrievalChain(
             combine_docs_chain=combine_docs_chain,
             retriever=retriever,
diff --git a/libs/langchain/langchain_classic/chains/history_aware_retriever.py b/libs/langchain/langchain_classic/chains/history_aware_retriever.py
index ed16c85560b..9d193adf52e 100644
--- a/libs/langchain/langchain_classic/chains/history_aware_retriever.py
+++ b/libs/langchain/langchain_classic/chains/history_aware_retriever.py
@@ -38,10 +38,10 @@ def create_history_aware_retriever(
         from langchain_classic import hub
 
         rephrase_prompt = hub.pull("langchain-ai/chat-langchain-rephrase")
-        llm = ChatOpenAI()
+        model = ChatOpenAI()
         retriever = ...
         chat_retriever_chain = create_history_aware_retriever(
-            llm, retriever, rephrase_prompt
+            model, retriever, rephrase_prompt
         )
 
         chain.invoke({"input": "...", "chat_history": })
diff --git a/libs/langchain/langchain_classic/chains/llm.py b/libs/langchain/langchain_classic/chains/llm.py
index 534cd97794c..fae99da5d53 100644
--- a/libs/langchain/langchain_classic/chains/llm.py
+++ b/libs/langchain/langchain_classic/chains/llm.py
@@ -55,8 +55,8 @@ class LLMChain(Chain):
 
         prompt_template = "Tell me a {adjective} joke"
         prompt = PromptTemplate(input_variables=["adjective"], template=prompt_template)
-        llm = OpenAI()
-        chain = prompt | llm | StrOutputParser()
+        model = OpenAI()
+        chain = prompt | model | StrOutputParser()
 
         chain.invoke("your adjective here")
         ```
@@ -69,7 +69,7 @@ class LLMChain(Chain):
 
         prompt_template = "Tell me a {adjective} joke"
         prompt = PromptTemplate(input_variables=["adjective"], template=prompt_template)
-        llm = LLMChain(llm=OpenAI(), prompt=prompt)
+        model = LLMChain(llm=OpenAI(), prompt=prompt)
         ```
     """
 
diff --git a/libs/langchain/langchain_classic/chains/llm_checker/base.py b/libs/langchain/langchain_classic/chains/llm_checker/base.py
index 5bd53322e9c..ec630178d5b 100644
--- a/libs/langchain/langchain_classic/chains/llm_checker/base.py
+++ b/libs/langchain/langchain_classic/chains/llm_checker/base.py
@@ -80,8 +80,8 @@ class LLMCheckerChain(Chain):
         from langchain_community.llms import OpenAI
         from langchain_classic.chains import LLMCheckerChain
 
-        llm = OpenAI(temperature=0.7)
-        checker_chain = LLMCheckerChain.from_llm(llm)
+        model = OpenAI(temperature=0.7)
+        checker_chain = LLMCheckerChain.from_llm(model)
         ```
     """
 
diff --git a/libs/langchain/langchain_classic/chains/llm_math/base.py b/libs/langchain/langchain_classic/chains/llm_math/base.py
index 86eea13e1b7..0d1306c6925 100644
--- a/libs/langchain/langchain_classic/chains/llm_math/base.py
+++ b/libs/langchain/langchain_classic/chains/llm_math/base.py
@@ -84,9 +84,9 @@ class LLMMathChain(Chain):
                     )
                 )
 
-            llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+            model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
             tools = [calculator]
-            llm_with_tools = llm.bind_tools(tools, tool_choice="any")
+            model_with_tools = model.bind_tools(tools, tool_choice="any")
 
             class ChainState(TypedDict):
                 \"\"\"LangGraph state.\"\"\"
@@ -95,11 +95,11 @@ class LLMMathChain(Chain):
 
             async def acall_chain(state: ChainState, config: RunnableConfig):
                 last_message = state["messages"][-1]
-                response = await llm_with_tools.ainvoke(state["messages"], config)
+                response = await model_with_tools.ainvoke(state["messages"], config)
                 return {"messages": [response]}
 
             async def acall_model(state: ChainState, config: RunnableConfig):
-                response = await llm.ainvoke(state["messages"], config)
+                response = await model.ainvoke(state["messages"], config)
                 return {"messages": [response]}
 
             graph_builder = StateGraph(ChainState)
diff --git a/libs/langchain/langchain_classic/chains/llm_summarization_checker/base.py b/libs/langchain/langchain_classic/chains/llm_summarization_checker/base.py
index 28e745772a7..7eb3a12d0ba 100644
--- a/libs/langchain/langchain_classic/chains/llm_summarization_checker/base.py
+++ b/libs/langchain/langchain_classic/chains/llm_summarization_checker/base.py
@@ -83,8 +83,8 @@ class LLMSummarizationCheckerChain(Chain):
         from langchain_community.llms import OpenAI
         from langchain_classic.chains import LLMSummarizationCheckerChain
 
-        llm = OpenAI(temperature=0.0)
-        checker_chain = LLMSummarizationCheckerChain.from_llm(llm)
+        model = OpenAI(temperature=0.0)
+        checker_chain = LLMSummarizationCheckerChain.from_llm(model)
         ```
     """
 
diff --git a/libs/langchain/langchain_classic/chains/natbot/base.py b/libs/langchain/langchain_classic/chains/natbot/base.py
index 6c482bccd86..c93969bf61a 100644
--- a/libs/langchain/langchain_classic/chains/natbot/base.py
+++ b/libs/langchain/langchain_classic/chains/natbot/base.py
@@ -84,8 +84,8 @@ class NatBotChain(Chain):
         """Load with default LLMChain."""
         msg = (
             "This method is no longer implemented. Please use from_llm."
-            "llm = OpenAI(temperature=0.5, best_of=10, n=3, max_tokens=50)"
-            "For example, NatBotChain.from_llm(llm, objective)"
+            "model = OpenAI(temperature=0.5, best_of=10, n=3, max_tokens=50)"
+            "For example, NatBotChain.from_llm(model, objective)"
         )
         raise NotImplementedError(msg)
 
diff --git a/libs/langchain/langchain_classic/chains/openai_functions/base.py b/libs/langchain/langchain_classic/chains/openai_functions/base.py
index 417ae1e2a64..f7cdce9c021 100644
--- a/libs/langchain/langchain_classic/chains/openai_functions/base.py
+++ b/libs/langchain/langchain_classic/chains/openai_functions/base.py
@@ -107,7 +107,7 @@ def create_openai_fn_chain(
             fav_food: str | None = Field(None, description="The dog's favorite food")
 
 
-        llm = ChatOpenAI(model="gpt-4", temperature=0)
+        model = ChatOpenAI(model="gpt-4", temperature=0)
         prompt = ChatPromptTemplate.from_messages(
             [
                 ("system", "You are a world class algorithm for recording entities."),
@@ -115,7 +115,7 @@ def create_openai_fn_chain(
                 ("human", "Tip: Make sure to answer in the correct format"),
             ]
         )
-        chain = create_openai_fn_chain([RecordPerson, RecordDog], llm, prompt)
+        chain = create_openai_fn_chain([RecordPerson, RecordDog], model, prompt)
         chain.run("Harry was a chubby brown beagle who loved chicken")
         # -> RecordDog(name="Harry", color="brown", fav_food="chicken")
 
@@ -191,7 +191,7 @@ def create_structured_output_chain(
             color: str = Field(..., description="The dog's color")
             fav_food: str | None = Field(None, description="The dog's favorite food")
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0613", temperature=0)
+        model = ChatOpenAI(model="gpt-3.5-turbo-0613", temperature=0)
         prompt = ChatPromptTemplate.from_messages(
             [
                 ("system", "You are a world class algorithm for extracting information in structured formats."),
@@ -199,7 +199,7 @@ def create_structured_output_chain(
                 ("human", "Tip: Make sure to answer in the correct format"),
             ]
         )
-        chain = create_structured_output_chain(Dog, llm, prompt)
+        chain = create_structured_output_chain(Dog, model, prompt)
         chain.run("Harry was a chubby brown beagle who loved chicken")
         # -> Dog(name="Harry", color="brown", fav_food="chicken")
 
diff --git a/libs/langchain/langchain_classic/chains/openai_functions/citation_fuzzy_match.py b/libs/langchain/langchain_classic/chains/openai_functions/citation_fuzzy_match.py
index 0a8cc3bed02..4b3fd369d39 100644
--- a/libs/langchain/langchain_classic/chains/openai_functions/citation_fuzzy_match.py
+++ b/libs/langchain/langchain_classic/chains/openai_functions/citation_fuzzy_match.py
@@ -83,12 +83,12 @@ def create_citation_fuzzy_match_runnable(llm: BaseChatModel) -> Runnable:
         from langchain_classic.chains import create_citation_fuzzy_match_runnable
         from langchain_openai import ChatOpenAI
 
-        llm = ChatOpenAI(model="gpt-4o-mini")
+        model = ChatOpenAI(model="gpt-4o-mini")
 
         context = "Alice has blue eyes. Bob has brown eyes. Charlie has green eyes."
         question = "What color are Bob's eyes?"
 
-        chain = create_citation_fuzzy_match_runnable(llm)
+        chain = create_citation_fuzzy_match_runnable(model)
         chain.invoke({"question": question, "context": context})
         ```
 
diff --git a/libs/langchain/langchain_classic/chains/openai_functions/extraction.py b/libs/langchain/langchain_classic/chains/openai_functions/extraction.py
index 3075bf93eaf..8d1dd05ce62 100644
--- a/libs/langchain/langchain_classic/chains/openai_functions/extraction.py
+++ b/libs/langchain/langchain_classic/chains/openai_functions/extraction.py
@@ -73,8 +73,8 @@ Passage:
             # to see an up to date list of which models support
             # with_structured_output.
             model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
-            structured_llm = model.with_structured_output(Joke)
-            structured_llm.invoke("Tell me a joke about cats.
+            structured_model = model.with_structured_output(Joke)
+            structured_model.invoke("Tell me a joke about cats.
                 Make sure to call the Joke function.")
             """
     ),
@@ -143,8 +143,8 @@ def create_extraction_chain(
             # to see an up to date list of which models support
             # with_structured_output.
             model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
-            structured_llm = model.with_structured_output(Joke)
-            structured_llm.invoke("Tell me a joke about cats.
+            structured_model = model.with_structured_output(Joke)
+            structured_model.invoke("Tell me a joke about cats.
                 Make sure to call the Joke function.")
             """
     ),
diff --git a/libs/langchain/langchain_classic/chains/openai_functions/openapi.py b/libs/langchain/langchain_classic/chains/openai_functions/openapi.py
index 2cfbfc31522..c29c111e388 100644
--- a/libs/langchain/langchain_classic/chains/openai_functions/openapi.py
+++ b/libs/langchain/langchain_classic/chains/openai_functions/openapi.py
@@ -330,7 +330,7 @@ def get_openapi_chain(
         prompt = ChatPromptTemplate.from_template(
             "Use the provided APIs to respond to this user query:\\n\\n{query}"
         )
-        llm = ChatOpenAI(model="gpt-4o-mini", temperature=0).bind_tools(tools)
+        model = ChatOpenAI(model="gpt-4o-mini", temperature=0).bind_tools(tools)
 
         def _execute_tool(message) -> Any:
             if tool_calls := message.tool_calls:
@@ -341,7 +341,7 @@ def get_openapi_chain(
             else:
                 return message.content
 
-        chain = prompt | llm | _execute_tool
+        chain = prompt | model | _execute_tool
         ```
 
         ```python
@@ -394,7 +394,7 @@ def get_openapi_chain(
         msg = (
             "Must provide an LLM for this chain.For example,\n"
             "from langchain_openai import ChatOpenAI\n"
-            "llm = ChatOpenAI()\n"
+            "model = ChatOpenAI()\n"
         )
         raise ValueError(msg)
     prompt = prompt or ChatPromptTemplate.from_template(
diff --git a/libs/langchain/langchain_classic/chains/openai_functions/tagging.py b/libs/langchain/langchain_classic/chains/openai_functions/tagging.py
index bbb21f9cb5a..2f70394b0e5 100644
--- a/libs/langchain/langchain_classic/chains/openai_functions/tagging.py
+++ b/libs/langchain/langchain_classic/chains/openai_functions/tagging.py
@@ -77,8 +77,8 @@ def create_tagging_chain(
     # to see an up to date list of which models support
     # with_structured_output.
     model = ChatAnthropic(model="claude-3-haiku-20240307", temperature=0)
-    structured_llm = model.with_structured_output(Joke)
-    structured_llm.invoke(
+    structured_model = model.with_structured_output(Joke)
+    structured_model.invoke(
         "Why did the cat cross the road? To get to the other "
         "side... and then lay down in the middle of it!"
     )
@@ -153,8 +153,8 @@ def create_tagging_chain_pydantic(
     # to see an up to date list of which models support
     # with_structured_output.
     model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
-    structured_llm = model.with_structured_output(Joke)
-    structured_llm.invoke(
+    structured_model = model.with_structured_output(Joke)
+    structured_model.invoke(
         "Why did the cat cross the road? To get to the other "
         "side... and then lay down in the middle of it!"
     )
diff --git a/libs/langchain/langchain_classic/chains/openai_tools/extraction.py b/libs/langchain/langchain_classic/chains/openai_tools/extraction.py
index 36c5729cdbc..276a0548e4d 100644
--- a/libs/langchain/langchain_classic/chains/openai_tools/extraction.py
+++ b/libs/langchain/langchain_classic/chains/openai_tools/extraction.py
@@ -42,8 +42,8 @@ If a property is not present and is not required in the function parameters, do
             # to see an up to date list of which models support
             # with_structured_output.
             model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
-            structured_llm = model.with_structured_output(Joke)
-            structured_llm.invoke("Tell me a joke about cats.
+            structured_model = model.with_structured_output(Joke)
+            structured_model.invoke("Tell me a joke about cats.
                 Make sure to call the Joke function.")
             """
     ),
diff --git a/libs/langchain/langchain_classic/chains/qa_generation/base.py b/libs/langchain/langchain_classic/chains/qa_generation/base.py
index df74669d045..fc2ca8824b8 100644
--- a/libs/langchain/langchain_classic/chains/qa_generation/base.py
+++ b/libs/langchain/langchain_classic/chains/qa_generation/base.py
@@ -34,7 +34,7 @@ class QAGenerationChain(Chain):
     - Supports async and streaming;
     - Surfaces prompt and text splitter for easier customization;
     - Use of JsonOutputParser supports JSONPatch operations in streaming mode,
-      as well as robustness to markdown.
+        as well as robustness to markdown.
 
         ```python
         from langchain_classic.chains.qa_generation.prompt import (
@@ -52,14 +52,14 @@ class QAGenerationChain(Chain):
         from langchain_openai import ChatOpenAI
         from langchain_text_splitters import RecursiveCharacterTextSplitter
 
-        llm = ChatOpenAI()
+        model = ChatOpenAI()
         text_splitter = RecursiveCharacterTextSplitter(chunk_overlap=500)
         split_text = RunnableLambda(lambda x: text_splitter.create_documents([x]))
 
         chain = RunnableParallel(
             text=RunnablePassthrough(),
             questions=(
-                split_text | RunnableEach(bound=prompt | llm | JsonOutputParser())
+                split_text | RunnableEach(bound=prompt | model | JsonOutputParser())
             ),
         )
         ```
diff --git a/libs/langchain/langchain_classic/chains/retrieval.py b/libs/langchain/langchain_classic/chains/retrieval.py
index 8eb4ff47768..f181953689b 100644
--- a/libs/langchain/langchain_classic/chains/retrieval.py
+++ b/libs/langchain/langchain_classic/chains/retrieval.py
@@ -46,9 +46,11 @@ def create_retrieval_chain(
         from langchain_classic import hub
 
         retrieval_qa_chat_prompt = hub.pull("langchain-ai/retrieval-qa-chat")
-        llm = ChatOpenAI()
+        model = ChatOpenAI()
         retriever = ...
-        combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)
+        combine_docs_chain = create_stuff_documents_chain(
+            model, retrieval_qa_chat_prompt
+        )
         retrieval_chain = create_retrieval_chain(retriever, combine_docs_chain)
 
         retrieval_chain.invoke({"input": "..."})
diff --git a/libs/langchain/langchain_classic/chains/retrieval_qa/base.py b/libs/langchain/langchain_classic/chains/retrieval_qa/base.py
index 39fdf46ff60..5a6bc65af88 100644
--- a/libs/langchain/langchain_classic/chains/retrieval_qa/base.py
+++ b/libs/langchain/langchain_classic/chains/retrieval_qa/base.py
@@ -237,7 +237,7 @@ class RetrievalQA(BaseRetrievalQA):
 
 
         retriever = ...  # Your retriever
-        llm = ChatOpenAI()
+        model = ChatOpenAI()
 
         system_prompt = (
             "Use the given context to answer the question. "
@@ -251,7 +251,7 @@ class RetrievalQA(BaseRetrievalQA):
                 ("human", "{input}"),
             ]
         )
-        question_answer_chain = create_stuff_documents_chain(llm, prompt)
+        question_answer_chain = create_stuff_documents_chain(model, prompt)
         chain = create_retrieval_chain(retriever, question_answer_chain)
 
         chain.invoke({"input": query})
diff --git a/libs/langchain/langchain_classic/chains/router/llm_router.py b/libs/langchain/langchain_classic/chains/router/llm_router.py
index 6fa390a2f12..c90685e6b5d 100644
--- a/libs/langchain/langchain_classic/chains/router/llm_router.py
+++ b/libs/langchain/langchain_classic/chains/router/llm_router.py
@@ -48,7 +48,7 @@ class LLMRouterChain(RouterChain):
         from langchain_core.runnables import RunnableLambda, RunnablePassthrough
         from langchain_openai import ChatOpenAI
 
-        llm = ChatOpenAI(model="gpt-4o-mini")
+        model = ChatOpenAI(model="gpt-4o-mini")
 
         prompt_1 = ChatPromptTemplate.from_messages(
             [
@@ -63,8 +63,8 @@ class LLMRouterChain(RouterChain):
             ]
         )
 
-        chain_1 = prompt_1 | llm | StrOutputParser()
-        chain_2 = prompt_2 | llm | StrOutputParser()
+        chain_1 = prompt_1 | model | StrOutputParser()
+        chain_2 = prompt_2 | model | StrOutputParser()
 
         route_system = "Route the user's query to either the animal "
         "or vegetable expert."
@@ -83,7 +83,7 @@ class LLMRouterChain(RouterChain):
 
         route_chain = (
             route_prompt
-            | llm.with_structured_output(RouteQuery)
+            | model.with_structured_output(RouteQuery)
             | itemgetter("destination")
         )
 
diff --git a/libs/langchain/langchain_classic/chains/router/multi_prompt.py b/libs/langchain/langchain_classic/chains/router/multi_prompt.py
index 2c13ec476d4..52c3eac6a1e 100644
--- a/libs/langchain/langchain_classic/chains/router/multi_prompt.py
+++ b/libs/langchain/langchain_classic/chains/router/multi_prompt.py
@@ -49,7 +49,7 @@ class MultiPromptChain(MultiRouteChain):
         from langgraph.graph import END, START, StateGraph
         from typing_extensions import TypedDict
 
-        llm = ChatOpenAI(model="gpt-4o-mini")
+        model = ChatOpenAI(model="gpt-4o-mini")
 
         # Define the prompts we will route to
         prompt_1 = ChatPromptTemplate.from_messages(
@@ -68,8 +68,8 @@ class MultiPromptChain(MultiRouteChain):
         # Construct the chains we will route to. These format the input query
         # into the respective prompt, run it through a chat model, and cast
         # the result to a string.
-        chain_1 = prompt_1 | llm | StrOutputParser()
-        chain_2 = prompt_2 | llm | StrOutputParser()
+        chain_1 = prompt_1 | model | StrOutputParser()
+        chain_2 = prompt_2 | model | StrOutputParser()
 
 
         # Next: define the chain that selects which branch to route to.
@@ -92,7 +92,7 @@ class MultiPromptChain(MultiRouteChain):
             destination: Literal["animal", "vegetable"]
 
 
-        route_chain = route_prompt | llm.with_structured_output(RouteQuery)
+        route_chain = route_prompt | model.with_structured_output(RouteQuery)
 
 
         # For LangGraph, we will define the state of the graph to hold the query,
diff --git a/libs/langchain/langchain_classic/chains/router/multi_retrieval_qa.py b/libs/langchain/langchain_classic/chains/router/multi_retrieval_qa.py
index bf710cd8040..7f9d743f0f8 100644
--- a/libs/langchain/langchain_classic/chains/router/multi_retrieval_qa.py
+++ b/libs/langchain/langchain_classic/chains/router/multi_retrieval_qa.py
@@ -117,7 +117,7 @@ class MultiRetrievalQAChain(MultiRouteChain):
                     "default LLMs on behalf of users."
                     "You can provide a conversation LLM like so:\n"
                     "from langchain_openai import ChatOpenAI\n"
-                    "llm = ChatOpenAI()"
+                    "model = ChatOpenAI()"
                 )
                 raise NotImplementedError(msg)
             _default_chain = ConversationChain(
diff --git a/libs/langchain/langchain_classic/chains/sql_database/query.py b/libs/langchain/langchain_classic/chains/sql_database/query.py
index f14b9672205..aa26b6bae21 100644
--- a/libs/langchain/langchain_classic/chains/sql_database/query.py
+++ b/libs/langchain/langchain_classic/chains/sql_database/query.py
@@ -76,8 +76,8 @@ def create_sql_query_chain(
         from langchain_community.utilities import SQLDatabase
 
         db = SQLDatabase.from_uri("sqlite:///Chinook.db")
-        llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
-        chain = create_sql_query_chain(llm, db)
+        model = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+        chain = create_sql_query_chain(model, db)
         response = chain.invoke({"question": "How many employees are there"})
         ```
 
diff --git a/libs/langchain/langchain_classic/chains/structured_output/base.py b/libs/langchain/langchain_classic/chains/structured_output/base.py
index 9d99cb33f9c..e7e18f51efe 100644
--- a/libs/langchain/langchain_classic/chains/structured_output/base.py
+++ b/libs/langchain/langchain_classic/chains/structured_output/base.py
@@ -57,8 +57,8 @@ from pydantic import BaseModel
             # to see an up to date list of which models support
             # with_structured_output.
             model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
-            structured_llm = model.with_structured_output(Joke)
-            structured_llm.invoke("Tell me a joke about cats.
+            structured_model = model.with_structured_output(Joke)
+            structured_model.invoke("Tell me a joke about cats.
                 Make sure to call the Joke function.")
             """
     ),
@@ -127,9 +127,9 @@ def create_openai_fn_runnable(
             fav_food: str | None = Field(None, description="The dog's favorite food")
 
 
-        llm = ChatOpenAI(model="gpt-4", temperature=0)
-        structured_llm = create_openai_fn_runnable([RecordPerson, RecordDog], llm)
-        structured_llm.invoke("Harry was a chubby brown beagle who loved chicken)
+        model = ChatOpenAI(model="gpt-4", temperature=0)
+        structured_model = create_openai_fn_runnable([RecordPerson, RecordDog], model)
+        structured_model.invoke("Harry was a chubby brown beagle who loved chicken)
         # -> RecordDog(name="Harry", color="brown", fav_food="chicken")
 
         ```
@@ -176,8 +176,8 @@ def create_openai_fn_runnable(
             # to see an up to date list of which models support
             # with_structured_output.
             model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
-            structured_llm = model.with_structured_output(Joke)
-            structured_llm.invoke("Tell me a joke about cats.
+            structured_model = model.with_structured_output(Joke)
+            structured_model.invoke("Tell me a joke about cats.
                 Make sure to call the Joke function.")
             """
     ),
@@ -250,21 +250,21 @@ def create_structured_output_runnable(
             color: str = Field(..., description="The dog's color")
             fav_food: str | None = Field(None, description="The dog's favorite food")
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
         prompt = ChatPromptTemplate.from_messages(
             [
                 ("system", "You are an extraction algorithm. Please extract every possible instance"),
                 ('human', '{input}')
             ]
         )
-        structured_llm = create_structured_output_runnable(
+        structured_model = create_structured_output_runnable(
             RecordDog,
-            llm,
+            model,
             mode="openai-tools",
             enforce_function_usage=True,
             return_single=True
         )
-        structured_llm.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
+        structured_model.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
         # -> RecordDog(name="Harry", color="brown", fav_food="chicken")
         ```
 
@@ -303,15 +303,15 @@ def create_structured_output_runnable(
         }
 
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
-        structured_llm = create_structured_output_runnable(
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
+        structured_model = create_structured_output_runnable(
             dog_schema,
-            llm,
+            model,
             mode="openai-tools",
             enforce_function_usage=True,
             return_single=True
         )
-        structured_llm.invoke("Harry was a chubby brown beagle who loved chicken")
+        structured_model.invoke("Harry was a chubby brown beagle who loved chicken")
         # -> {'name': 'Harry', 'color': 'brown', 'fav_food': 'chicken'}
         ```
 
@@ -330,9 +330,9 @@ def create_structured_output_runnable(
             color: str = Field(..., description="The dog's color")
             fav_food: str | None = Field(None, description="The dog's favorite food")
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
-        structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-functions")
-        structured_llm.invoke("Harry was a chubby brown beagle who loved chicken")
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
+        structured_model = create_structured_output_runnable(Dog, model, mode="openai-functions")
+        structured_model.invoke("Harry was a chubby brown beagle who loved chicken")
         # -> Dog(name="Harry", color="brown", fav_food="chicken")
         ```
 
@@ -352,13 +352,13 @@ def create_structured_output_runnable(
             color: str = Field(..., description="The dog's color")
             fav_food: str | None = Field(None, description="The dog's favorite food")
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
-        structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-functions")
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
+        structured_model = create_structured_output_runnable(Dog, model, mode="openai-functions")
         system = '''Extract information about any dogs mentioned in the user input.'''
         prompt = ChatPromptTemplate.from_messages(
             [("system", system), ("human", "{input}"),]
         )
-        chain = prompt | structured_llm
+        chain = prompt | structured_model
         chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
         # -> Dog(name="Harry", color="brown", fav_food="chicken")
         ```
@@ -379,8 +379,8 @@ def create_structured_output_runnable(
             color: str = Field(..., description="The dog's color")
             fav_food: str | None = Field(None, description="The dog's favorite food")
 
-        llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
-        structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-json")
+        model = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
+        structured_model = create_structured_output_runnable(Dog, model, mode="openai-json")
         system = '''You are a world class assistant for extracting information in structured JSON formats. \
 
         Extract a valid JSON blob from the user input that matches the following JSON Schema:
@@ -389,7 +389,7 @@ def create_structured_output_runnable(
         prompt = ChatPromptTemplate.from_messages(
             [("system", system), ("human", "{input}"),]
         )
-        chain = prompt | structured_llm
+        chain = prompt | structured_model
         chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})
 
         ```
diff --git a/libs/langchain/langchain_classic/evaluation/agents/trajectory_eval_chain.py b/libs/langchain/langchain_classic/evaluation/agents/trajectory_eval_chain.py
index a8b364028c3..644a3902186 100644
--- a/libs/langchain/langchain_classic/evaluation/agents/trajectory_eval_chain.py
+++ b/libs/langchain/langchain_classic/evaluation/agents/trajectory_eval_chain.py
@@ -113,10 +113,10 @@ class TrajectoryEvalChain(AgentTrajectoryEvaluator, LLMEvalChain):
         \"\"\"Very helpful answers to geography questions.\"\"\"
         return f"{country}? IDK - We may never know {question}."
 
-    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+    model = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
     agent = initialize_agent(
         tools=[geography_answers],
-        llm=llm,
+        llm=model,
         agent=AgentType.OPENAI_FUNCTIONS,
         return_intermediate_steps=True,
     )
@@ -125,7 +125,7 @@ class TrajectoryEvalChain(AgentTrajectoryEvaluator, LLMEvalChain):
     response = agent(question)
 
     eval_chain = TrajectoryEvalChain.from_llm(
-        llm=llm, agent_tools=[geography_answers], return_reasoning=True
+        llm=model, agent_tools=[geography_answers], return_reasoning=True
     )
 
     result = eval_chain.evaluate_agent_trajectory(
diff --git a/libs/langchain/langchain_classic/evaluation/comparison/eval_chain.py b/libs/langchain/langchain_classic/evaluation/comparison/eval_chain.py
index ab83aa46c4a..01b9c6afd3d 100644
--- a/libs/langchain/langchain_classic/evaluation/comparison/eval_chain.py
+++ b/libs/langchain/langchain_classic/evaluation/comparison/eval_chain.py
@@ -165,10 +165,10 @@ class PairwiseStringEvalChain(PairwiseStringEvaluator, LLMEvalChain, LLMChain):
     Example:
         >>> from langchain_community.chat_models import ChatOpenAI
         >>> from langchain_classic.evaluation.comparison import PairwiseStringEvalChain
-        >>> llm = ChatOpenAI(
+        >>> model = ChatOpenAI(
         ...     temperature=0, model_name="gpt-4", model_kwargs={"random_seed": 42}
         ... )
-        >>> chain = PairwiseStringEvalChain.from_llm(llm=llm)
+        >>> chain = PairwiseStringEvalChain.from_llm(llm=model)
         >>> result = chain.evaluate_string_pairs(
         ...     input = "What is the chemical formula for water?",
         ...     prediction = "H2O",
diff --git a/libs/langchain/langchain_classic/evaluation/criteria/__init__.py b/libs/langchain/langchain_classic/evaluation/criteria/__init__.py
index c275541a06c..fce15234e2b 100644
--- a/libs/langchain/langchain_classic/evaluation/criteria/__init__.py
+++ b/libs/langchain/langchain_classic/evaluation/criteria/__init__.py
@@ -15,9 +15,9 @@ Using a predefined criterion:
 >>> from langchain_community.llms import OpenAI
 >>> from langchain_classic.evaluation.criteria import CriteriaEvalChain
 
->>> llm = OpenAI()
+>>> model = OpenAI()
 >>> criteria = "conciseness"
->>> chain = CriteriaEvalChain.from_llm(llm=llm, criteria=criteria)
+>>> chain = CriteriaEvalChain.from_llm(llm=model, criteria=criteria)
 >>> chain.evaluate_strings(
         prediction="The answer is 42.",
         reference="42",
@@ -29,7 +29,7 @@ Using a custom criterion:
 >>> from langchain_community.llms import OpenAI
 >>> from langchain_classic.evaluation.criteria import LabeledCriteriaEvalChain
 
->>> llm = OpenAI()
+>>> model = OpenAI()
 >>> criteria = {
        "hallucination": (
             "Does this submission contain information"
@@ -37,7 +37,7 @@ Using a custom criterion:
         ),
     }
 >>> chain = LabeledCriteriaEvalChain.from_llm(
-        llm=llm,
+        llm=model,
         criteria=criteria,
         )
 >>> chain.evaluate_strings(
diff --git a/libs/langchain/langchain_classic/evaluation/criteria/eval_chain.py b/libs/langchain/langchain_classic/evaluation/criteria/eval_chain.py
index 80d964c451f..64c2cc0d6cf 100644
--- a/libs/langchain/langchain_classic/evaluation/criteria/eval_chain.py
+++ b/libs/langchain/langchain_classic/evaluation/criteria/eval_chain.py
@@ -190,9 +190,9 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
     --------
     >>> from langchain_anthropic import ChatAnthropic
     >>> from langchain_classic.evaluation.criteria import CriteriaEvalChain
-    >>> llm = ChatAnthropic(temperature=0)
+    >>> model = ChatAnthropic(temperature=0)
     >>> criteria = {"my-custom-criterion": "Is the submission the most amazing ever?"}
-    >>> evaluator = CriteriaEvalChain.from_llm(llm=llm, criteria=criteria)
+    >>> evaluator = CriteriaEvalChain.from_llm(llm=model, criteria=criteria)
     >>> evaluator.evaluate_strings(
     ...     prediction="Imagine an ice cream flavor for the color aquamarine",
     ...     input="Tell me an idea",
@@ -205,10 +205,10 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
 
     >>> from langchain_openai import ChatOpenAI
     >>> from langchain_classic.evaluation.criteria import LabeledCriteriaEvalChain
-    >>> llm = ChatOpenAI(model="gpt-4", temperature=0)
+    >>> model = ChatOpenAI(model="gpt-4", temperature=0)
     >>> criteria = "correctness"
     >>> evaluator = LabeledCriteriaEvalChain.from_llm(
-    ...     llm=llm,
+    ...     llm=model,
     ...     criteria=criteria,
     ... )
     >>> evaluator.evaluate_strings(
@@ -347,7 +347,7 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
         --------
         >>> from langchain_openai import OpenAI
         >>> from langchain_classic.evaluation.criteria import LabeledCriteriaEvalChain
-        >>> llm = OpenAI()
+        >>> model = OpenAI()
         >>> criteria = {
                 "hallucination": (
                     "Does this submission contain information"
@@ -355,7 +355,7 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
                 ),
             }
         >>> chain = LabeledCriteriaEvalChain.from_llm(
-                llm=llm,
+                llm=model,
                 criteria=criteria,
             )
         """
@@ -433,9 +433,9 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
         Examples:
             >>> from langchain_openai import OpenAI
             >>> from langchain_classic.evaluation.criteria import CriteriaEvalChain
-            >>> llm = OpenAI()
+            >>> model = OpenAI()
             >>> criteria = "conciseness"
-            >>> chain = CriteriaEvalChain.from_llm(llm=llm, criteria=criteria)
+            >>> chain = CriteriaEvalChain.from_llm(llm=model, criteria=criteria)
             >>> chain.evaluate_strings(
                     prediction="The answer is 42.",
                     reference="42",
@@ -485,9 +485,9 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
         Examples:
             >>> from langchain_openai import OpenAI
             >>> from langchain_classic.evaluation.criteria import CriteriaEvalChain
-            >>> llm = OpenAI()
+            >>> model = OpenAI()
             >>> criteria = "conciseness"
-            >>> chain = CriteriaEvalChain.from_llm(llm=llm, criteria=criteria)
+            >>> chain = CriteriaEvalChain.from_llm(llm=model, criteria=criteria)
             >>> await chain.aevaluate_strings(
                     prediction="The answer is 42.",
                     reference="42",
@@ -569,7 +569,7 @@ class LabeledCriteriaEvalChain(CriteriaEvalChain):
         --------
         >>> from langchain_openai import OpenAI
         >>> from langchain_classic.evaluation.criteria import LabeledCriteriaEvalChain
-        >>> llm = OpenAI()
+        >>> model = OpenAI()
         >>> criteria = {
                 "hallucination": (
                     "Does this submission contain information"
@@ -577,7 +577,7 @@ class LabeledCriteriaEvalChain(CriteriaEvalChain):
                 ),
             }
         >>> chain = LabeledCriteriaEvalChain.from_llm(
-                llm=llm,
+                llm=model,
                 criteria=criteria,
             )
         """
diff --git a/libs/langchain/langchain_classic/evaluation/scoring/__init__.py b/libs/langchain/langchain_classic/evaluation/scoring/__init__.py
index 4faaefb278a..c5c08722f25 100644
--- a/libs/langchain/langchain_classic/evaluation/scoring/__init__.py
+++ b/libs/langchain/langchain_classic/evaluation/scoring/__init__.py
@@ -7,8 +7,8 @@ criteria and or a reference answer.
 Example:
     >>> from langchain_community.chat_models import ChatOpenAI
     >>> from langchain_classic.evaluation.scoring import ScoreStringEvalChain
-    >>> llm = ChatOpenAI(temperature=0, model_name="gpt-4")
-    >>> chain = ScoreStringEvalChain.from_llm(llm=llm)
+    >>> model = ChatOpenAI(temperature=0, model_name="gpt-4")
+    >>> chain = ScoreStringEvalChain.from_llm(llm=model)
     >>> result = chain.evaluate_strings(
     ...     input="What is the chemical formula for water?",
     ...     prediction="H2O",
diff --git a/libs/langchain/langchain_classic/evaluation/scoring/eval_chain.py b/libs/langchain/langchain_classic/evaluation/scoring/eval_chain.py
index 93c412af61c..fefa2041936 100644
--- a/libs/langchain/langchain_classic/evaluation/scoring/eval_chain.py
+++ b/libs/langchain/langchain_classic/evaluation/scoring/eval_chain.py
@@ -156,8 +156,8 @@ class ScoreStringEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
     Example:
         >>> from langchain_community.chat_models import ChatOpenAI
         >>> from langchain_classic.evaluation.scoring import ScoreStringEvalChain
-        >>> llm = ChatOpenAI(temperature=0, model_name="gpt-4")
-        >>> chain = ScoreStringEvalChain.from_llm(llm=llm)
+        >>> model = ChatOpenAI(temperature=0, model_name="gpt-4")
+        >>> chain = ScoreStringEvalChain.from_llm(llm=model)
         >>> result = chain.evaluate_strings(
         ...     input="What is the chemical formula for water?",
         ...     prediction="H2O",
diff --git a/libs/langchain/langchain_classic/indexes/vectorstore.py b/libs/langchain/langchain_classic/indexes/vectorstore.py
index d23951d0daf..0680241739c 100644
--- a/libs/langchain/langchain_classic/indexes/vectorstore.py
+++ b/libs/langchain/langchain_classic/indexes/vectorstore.py
@@ -55,7 +55,7 @@ class VectorStoreIndexWrapper(BaseModel):
                 "Please provide an llm to use for querying the vectorstore.\n"
                 "For example,\n"
                 "from langchain_openai import OpenAI\n"
-                "llm = OpenAI(temperature=0)"
+                "model = OpenAI(temperature=0)"
             )
             raise NotImplementedError(msg)
         retriever_kwargs = retriever_kwargs or {}
@@ -90,7 +90,7 @@ class VectorStoreIndexWrapper(BaseModel):
                 "Please provide an llm to use for querying the vectorstore.\n"
                 "For example,\n"
                 "from langchain_openai import OpenAI\n"
-                "llm = OpenAI(temperature=0)"
+                "model = OpenAI(temperature=0)"
             )
             raise NotImplementedError(msg)
         retriever_kwargs = retriever_kwargs or {}
@@ -125,7 +125,7 @@ class VectorStoreIndexWrapper(BaseModel):
                 "Please provide an llm to use for querying the vectorstore.\n"
                 "For example,\n"
                 "from langchain_openai import OpenAI\n"
-                "llm = OpenAI(temperature=0)"
+                "model = OpenAI(temperature=0)"
             )
             raise NotImplementedError(msg)
         retriever_kwargs = retriever_kwargs or {}
@@ -160,7 +160,7 @@ class VectorStoreIndexWrapper(BaseModel):
                 "Please provide an llm to use for querying the vectorstore.\n"
                 "For example,\n"
                 "from langchain_openai import OpenAI\n"
-                "llm = OpenAI(temperature=0)"
+                "model = OpenAI(temperature=0)"
             )
             raise NotImplementedError(msg)
         retriever_kwargs = retriever_kwargs or {}
diff --git a/libs/langchain/langchain_classic/smith/__init__.py b/libs/langchain/langchain_classic/smith/__init__.py
index 4f06ae3af34..24a75f48dae 100644
--- a/libs/langchain/langchain_classic/smith/__init__.py
+++ b/libs/langchain/langchain_classic/smith/__init__.py
@@ -22,8 +22,8 @@ from langchain_classic.smith import RunEvalConfig, run_on_dataset
 # Chains may have memory. Passing in a constructor function lets the
 # evaluation framework avoid cross-contamination between runs.
 def construct_chain():
-    llm = ChatOpenAI(temperature=0)
-    chain = LLMChain.from_string(llm, "What's the answer to {your_input_key}")
+    model = ChatOpenAI(temperature=0)
+    chain = LLMChain.from_string(model, "What's the answer to {your_input_key}")
     return chain
 
 
diff --git a/libs/langchain/langchain_classic/smith/evaluation/__init__.py b/libs/langchain/langchain_classic/smith/evaluation/__init__.py
index 78e7fc70ab5..d10d6ef03b6 100644
--- a/libs/langchain/langchain_classic/smith/evaluation/__init__.py
+++ b/libs/langchain/langchain_classic/smith/evaluation/__init__.py
@@ -16,8 +16,8 @@ from langchain_classic.smith import EvaluatorType, RunEvalConfig, run_on_dataset
 
 
 def construct_chain():
-    llm = ChatOpenAI(temperature=0)
-    chain = LLMChain.from_string(llm, "What's the answer to {your_input_key}")
+    model = ChatOpenAI(temperature=0)
+    chain = LLMChain.from_string(model, "What's the answer to {your_input_key}")
     return chain
 
 
diff --git a/libs/langchain/langchain_classic/smith/evaluation/runner_utils.py b/libs/langchain/langchain_classic/smith/evaluation/runner_utils.py
index 51fb2d776af..8db9f6fa971 100644
--- a/libs/langchain/langchain_classic/smith/evaluation/runner_utils.py
+++ b/libs/langchain/langchain_classic/smith/evaluation/runner_utils.py
@@ -1395,9 +1395,9 @@ async def arun_on_dataset(
     # Chains may have memory. Passing in a constructor function lets the
     # evaluation framework avoid cross-contamination between runs.
     def construct_chain():
-        llm = ChatOpenAI(temperature=0)
+        model = ChatOpenAI(temperature=0)
         chain = LLMChain.from_string(
-            llm,
+            model,
             "What's the answer to {your_input_key}"
         )
         return chain
@@ -1570,9 +1570,9 @@ def run_on_dataset(
     # Chains may have memory. Passing in a constructor function lets the
     # evaluation framework avoid cross-contamination between runs.
     def construct_chain():
-        llm = ChatOpenAI(temperature=0)
+        model = ChatOpenAI(temperature=0)
         chain = LLMChain.from_string(
-            llm,
+            model,
             "What's the answer to {your_input_key}"
         )
         return chain
diff --git a/libs/partners/anthropic/langchain_anthropic/chat_models.py b/libs/partners/anthropic/langchain_anthropic/chat_models.py
index fb494fffcab..ee8aba6225f 100644
--- a/libs/partners/anthropic/langchain_anthropic/chat_models.py
+++ b/libs/partners/anthropic/langchain_anthropic/chat_models.py
@@ -609,7 +609,7 @@ class ChatAnthropic(BaseChatModel):
         ```python
         from langchain_anthropic import ChatAnthropic
 
-        llm = ChatAnthropic(
+        model = ChatAnthropic(
             model="claude-3-7-sonnet-20250219",
             temperature=0,
             max_tokens=1024,
@@ -650,7 +650,7 @@ class ChatAnthropic(BaseChatModel):
             ),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
         ```python
@@ -674,7 +674,7 @@ class ChatAnthropic(BaseChatModel):
 
     Stream:
         ```python
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.text, end="")
         ```
 
@@ -690,7 +690,7 @@ class ChatAnthropic(BaseChatModel):
         ```
 
         ```python
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -703,13 +703,13 @@ class ChatAnthropic(BaseChatModel):
 
     Async:
         ```python
-        await llm.ainvoke(messages)
+        await model.ainvoke(messages)
 
         # stream:
-        # async for chunk in (await llm.astream(messages))
+        # async for chunk in (await model.astream(messages))
 
         # batch:
-        # await llm.abatch([messages])
+        # await model.abatch([messages])
         ```
 
         ```python
@@ -748,8 +748,8 @@ class ChatAnthropic(BaseChatModel):
             location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
 
 
-        llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
-        ai_msg = llm_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
+        model_with_tools = model.bind_tools([GetWeather, GetPopulation])
+        ai_msg = model_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
         ai_msg.tool_calls
         ```
 
@@ -795,8 +795,8 @@ class ChatAnthropic(BaseChatModel):
             rating: int | None = Field(description="How funny the joke is, from 1 to 10")
 
 
-        structured_llm = llm.with_structured_output(Joke)
-        structured_llm.invoke("Tell me a joke about cats")
+        structured_model = model.with_structured_output(Joke)
+        structured_model.invoke("Tell me a joke about cats")
         ```
 
         ```python
@@ -823,7 +823,7 @@ class ChatAnthropic(BaseChatModel):
         image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
         image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
 
-        llm = ChatAnthropic(model="claude-3-5-sonnet-latest")
+        model = ChatAnthropic(model="claude-3-5-sonnet-latest")
         message = HumanMessage(
             content=[
                 {
@@ -841,7 +841,7 @@ class ChatAnthropic(BaseChatModel):
                 },
             ],
         )
-        ai_msg = llm.invoke([message])
+        ai_msg = model.invoke([message])
         ai_msg.content
         ```
 
@@ -857,7 +857,7 @@ class ChatAnthropic(BaseChatModel):
             ```python
             from langchain_anthropic import ChatAnthropic
 
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-sonnet-4-20250514",
                 betas=["files-api-2025-04-14"],
             )
@@ -874,7 +874,7 @@ class ChatAnthropic(BaseChatModel):
                     },
                 ],
             }
-            llm.invoke([input_message])
+            model.invoke([input_message])
             ```
 
     PDF input:
@@ -890,8 +890,8 @@ class ChatAnthropic(BaseChatModel):
         url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
         data = b64encode(requests.get(url).content).decode()
 
-        llm = ChatAnthropic(model="claude-3-5-sonnet-latest")
-        ai_msg = llm.invoke(
+        model = ChatAnthropic(model="claude-3-5-sonnet-latest")
+        ai_msg = model.invoke(
             [
                 HumanMessage(
                     [
@@ -920,7 +920,7 @@ class ChatAnthropic(BaseChatModel):
             ```python
             from langchain_anthropic import ChatAnthropic
 
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-sonnet-4-20250514",
                 betas=["files-api-2025-04-14"],
             )
@@ -937,7 +937,7 @@ class ChatAnthropic(BaseChatModel):
                     },
                 ],
             }
-            llm.invoke([input_message])
+            model.invoke([input_message])
             ```
 
     Extended thinking:
@@ -954,13 +954,13 @@ class ChatAnthropic(BaseChatModel):
         ```python
         from langchain_anthropic import ChatAnthropic
 
-        llm = ChatAnthropic(
+        model = ChatAnthropic(
             model="claude-3-7-sonnet-latest",
             max_tokens=5000,
             thinking={"type": "enabled", "budget_tokens": 2000},
         )
 
-        response = llm.invoke("What is the cube root of 50.653?")
+        response = model.invoke("What is the cube root of 50.653?")
         response.content
         ```
 
@@ -987,7 +987,7 @@ class ChatAnthropic(BaseChatModel):
         ```python
         from langchain_anthropic import ChatAnthropic
 
-        llm = ChatAnthropic(model="claude-3-5-haiku-latest")
+        model = ChatAnthropic(model="claude-3-5-haiku-latest")
 
         messages = [
             {
@@ -1008,7 +1008,7 @@ class ChatAnthropic(BaseChatModel):
                 ],
             }
         ]
-        response = llm.invoke(messages)
+        response = model.invoke(messages)
         response.content
         ```
 
@@ -1050,7 +1050,7 @@ class ChatAnthropic(BaseChatModel):
 
     Token usage:
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.usage_metadata
         ```
 
@@ -1062,7 +1062,7 @@ class ChatAnthropic(BaseChatModel):
         default:
 
         ```python
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -1088,7 +1088,7 @@ class ChatAnthropic(BaseChatModel):
         ```python
         from langchain_anthropic import ChatAnthropic
 
-        llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")
+        model = ChatAnthropic(model="claude-3-7-sonnet-20250219")
 
         messages = [
             {
@@ -1111,7 +1111,7 @@ class ChatAnthropic(BaseChatModel):
             },
         ]
 
-        response = llm.invoke(messages)
+        response = model.invoke(messages)
         response.usage_metadata["input_token_details"]
         ```
 
@@ -1125,7 +1125,7 @@ class ChatAnthropic(BaseChatModel):
         cache.
 
         ```python
-        response = llm.invoke(
+        response = model.invoke(
             messages,
             cache_control={"type": "ephemeral"},
         )
@@ -1137,7 +1137,7 @@ class ChatAnthropic(BaseChatModel):
             apply one hour caching by setting `ttl` to `'1h'`.
 
             ```python
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-3-7-sonnet-20250219",
             )
 
@@ -1154,14 +1154,14 @@ class ChatAnthropic(BaseChatModel):
                 }
             ]
 
-            response = llm.invoke(messages)
+            response = model.invoke(messages)
             ```
 
             Details of cached token counts will be included on the `InputTokenDetails`
             of response's `usage_metadata`:
 
             ```python
-            response = llm.invoke(messages)
+            response = model.invoke(messages)
             response.usage_metadata
             ```
 
@@ -1189,7 +1189,7 @@ class ChatAnthropic(BaseChatModel):
         ```python
         from langchain_anthropic import ChatAnthropic
 
-        llm = ChatAnthropic(
+        model = ChatAnthropic(
             model="claude-sonnet-4-20250514",
             betas=["context-1m-2025-08-07"],  # Enable 1M context beta
         )
@@ -1210,7 +1210,7 @@ class ChatAnthropic(BaseChatModel):
         \"\"\")
         ]
 
-        response = llm.invoke(messages)
+        response = model.invoke(messages)
         ```
 
         See [Claude documentation](https://docs.anthropic.com/en/docs/build-with-claude/context-windows#1m-token-context-window)
@@ -1225,7 +1225,7 @@ class ChatAnthropic(BaseChatModel):
         from langchain_anthropic import ChatAnthropic
         from langchain_core.tools import tool
 
-        llm = ChatAnthropic(
+        model = ChatAnthropic(
             model="claude-3-7-sonnet-20250219",
             temperature=0,
             model_kwargs={
@@ -1240,8 +1240,8 @@ class ChatAnthropic(BaseChatModel):
             \"\"\"Get the weather at a location.\"\"\"
             return "It's sunny."
 
-        llm_with_tools = llm.bind_tools([get_weather])
-        response = llm_with_tools.invoke(
+        model_with_tools = model.bind_tools([get_weather])
+        response = model_with_tools.invoke(
             "What's the weather in San Francisco?"
         )
         print(response.tool_calls)
@@ -1263,13 +1263,13 @@ class ChatAnthropic(BaseChatModel):
         ```python
         from langchain_anthropic import ChatAnthropic
 
-        llm = ChatAnthropic(
+        model = ChatAnthropic(
             model="claude-sonnet-4-5-20250929",
             betas=["context-management-2025-06-27"],
             context_management={"edits": [{"type": "clear_tool_uses_20250919"}]},
         )
-        llm_with_tools = llm.bind_tools([{"type": "web_search_20250305", "name": "web_search"}])
-        response = llm_with_tools.invoke("Search for recent developments in AI")
+        model_with_tools = model.bind_tools([{"type": "web_search_20250305", "name": "web_search"}])
+        response = model_with_tools.invoke("Search for recent developments in AI")
         ```
 
     Built-in tools:
@@ -1281,16 +1281,16 @@ class ChatAnthropic(BaseChatModel):
             ```python
             from langchain_anthropic import ChatAnthropic
 
-            llm = ChatAnthropic(model="claude-3-5-haiku-latest")
+            model = ChatAnthropic(model="claude-3-5-haiku-latest")
 
             tool = {
                 "type": "web_search_20250305",
                 "name": "web_search",
                 "max_uses": 3,
             }
-            llm_with_tools = llm.bind_tools([tool])
+            model_with_tools = model.bind_tools([tool])
 
-            response = llm_with_tools.invoke("How do I update a web app to TypeScript 5.5?")
+            response = model_with_tools.invoke("How do I update a web app to TypeScript 5.5?")
             ```
 
         ??? note "Web fetch (beta)"
@@ -1298,7 +1298,7 @@ class ChatAnthropic(BaseChatModel):
             ```python
             from langchain_anthropic import ChatAnthropic
 
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-3-5-haiku-latest",
                 betas=["web-fetch-2025-09-10"],  # Enable web fetch beta
             )
@@ -1308,23 +1308,23 @@ class ChatAnthropic(BaseChatModel):
                 "name": "web_fetch",
                 "max_uses": 3,
             }
-            llm_with_tools = llm.bind_tools([tool])
+            model_with_tools = model.bind_tools([tool])
 
-            response = llm_with_tools.invoke("Please analyze the content at https://example.com/article")
+            response = model_with_tools.invoke("Please analyze the content at https://example.com/article")
             ```
 
         ??? note "Code execution"
 
             ```python
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-sonnet-4-20250514",
                 betas=["code-execution-2025-05-22"],
             )
 
             tool = {"type": "code_execution_20250522", "name": "code_execution"}
-            llm_with_tools = llm.bind_tools([tool])
+            model_with_tools = model.bind_tools([tool])
 
-            response = llm_with_tools.invoke(
+            response = model_with_tools.invoke(
                 "Calculate the mean and standard deviation of [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]"
             )
             ```
@@ -1347,13 +1347,13 @@ class ChatAnthropic(BaseChatModel):
                 }
             ]
 
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-sonnet-4-20250514",
                 betas=["mcp-client-2025-04-04"],
                 mcp_servers=mcp_servers,
             )
 
-            response = llm.invoke(
+            response = model.invoke(
                 "What transport protocols does the 2025-03-26 version of the MCP "
                 "spec (modelcontextprotocol/modelcontextprotocol) support?"
             )
@@ -1364,12 +1364,12 @@ class ChatAnthropic(BaseChatModel):
             ```python
             from langchain_anthropic import ChatAnthropic
 
-            llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")
+            model = ChatAnthropic(model="claude-3-7-sonnet-20250219")
 
             tool = {"type": "text_editor_20250124", "name": "str_replace_editor"}
-            llm_with_tools = llm.bind_tools([tool])
+            model_with_tools = model.bind_tools([tool])
 
-            response = llm_with_tools.invoke(
+            response = model_with_tools.invoke(
                 "There's a syntax error in my primes.py file. Can you help me fix it?"
             )
             print(response.text)
@@ -1390,18 +1390,18 @@ class ChatAnthropic(BaseChatModel):
             ```python
             from langchain_anthropic import ChatAnthropic
 
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-sonnet-4-5-20250929",
                 betas=["context-management-2025-06-27"],
             )
-            llm_with_tools = llm.bind_tools([{"type": "memory_20250818", "name": "memory"}])
-            response = llm_with_tools.invoke("What are my interests?")
+            model_with_tools = model.bind_tools([{"type": "memory_20250818", "name": "memory"}])
+            response = model_with_tools.invoke("What are my interests?")
             ```
 
     Response metadata
 
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.response_metadata
         ```
 
@@ -1939,9 +1939,9 @@ class ChatAnthropic(BaseChatModel):
                 product: str = Field(..., description="The product to look up.")
 
 
-            llm = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
-            llm_with_tools = llm.bind_tools([GetWeather, GetPrice])
-            llm_with_tools.invoke(
+            model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
+            model_with_tools = model.bind_tools([GetWeather, GetPrice])
+            model_with_tools.invoke(
                 "What is the weather like in San Francisco",
             )
             # -> AIMessage(
@@ -1973,9 +1973,9 @@ class ChatAnthropic(BaseChatModel):
                 product: str = Field(..., description="The product to look up.")
 
 
-            llm = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
-            llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="any")
-            llm_with_tools.invoke(
+            model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
+            model_with_tools = model.bind_tools([GetWeather, GetPrice], tool_choice="any")
+            model_with_tools.invoke(
                 "what is the weather like in San Francisco",
             )
             ```
@@ -1999,9 +1999,9 @@ class ChatAnthropic(BaseChatModel):
                 product: str = Field(..., description="The product to look up.")
 
 
-            llm = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
-            llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="GetWeather")
-            llm_with_tools.invoke("What is the weather like in San Francisco")
+            model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
+            model_with_tools = model.bind_tools([GetWeather, GetPrice], tool_choice="GetWeather")
+            model_with_tools.invoke("What is the weather like in San Francisco")
             ```
 
         Example — cache specific tools:
@@ -2033,12 +2033,12 @@ class ChatAnthropic(BaseChatModel):
 
             # We need to pass in extra headers to enable use of the beta cache
             # control API.
-            llm = ChatAnthropic(
+            model = ChatAnthropic(
                 model="claude-3-5-sonnet-latest",
                 temperature=0,
             )
-            llm_with_tools = llm.bind_tools([GetWeather, cached_price_tool])
-            llm_with_tools.invoke("What is the weather like in San Francisco")
+            model_with_tools = model.bind_tools([GetWeather, cached_price_tool])
+            model_with_tools.invoke("What is the weather like in San Francisco")
             ```
 
             This outputs:
@@ -2227,10 +2227,10 @@ class ChatAnthropic(BaseChatModel):
                 justification: str
 
 
-            llm = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
 
             # -> AnswerWithJustification(
             #     answer='They weigh the same',
@@ -2252,10 +2252,10 @@ class ChatAnthropic(BaseChatModel):
                 justification: str
 
 
-            llm = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification, include_raw=True)
+            model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification, include_raw=True)
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
             # -> {
             #     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
             #     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
@@ -2280,10 +2280,10 @@ class ChatAnthropic(BaseChatModel):
                     "required": ["answer", "justification"],
                 },
             }
-            llm = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
-            structured_llm = llm.with_structured_output(schema)
+            model = ChatAnthropic(model="claude-3-5-sonnet-latest", temperature=0)
+            structured_model = model.with_structured_output(schema)
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
             # -> {
             #     'answer': 'They weigh the same',
             #     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
@@ -2356,13 +2356,13 @@ class ChatAnthropic(BaseChatModel):
             from langchain_anthropic import ChatAnthropic
             from langchain_core.messages import HumanMessage, SystemMessage
 
-            llm = ChatAnthropic(model="claude-3-5-sonnet-20241022")
+            model = ChatAnthropic(model="claude-3-5-sonnet-20241022")
 
             messages = [
                 SystemMessage(content="You are a scientist"),
                 HumanMessage(content="Hello, Claude"),
             ]
-            llm.get_num_tokens_from_messages(messages)
+            model.get_num_tokens_from_messages(messages)
             ```
 
             ```txt
@@ -2376,7 +2376,7 @@ class ChatAnthropic(BaseChatModel):
             from langchain_core.messages import HumanMessage
             from langchain_core.tools import tool
 
-            llm = ChatAnthropic(model="claude-3-5-sonnet-20241022")
+            model = ChatAnthropic(model="claude-3-5-sonnet-20241022")
 
             @tool(parse_docstring=True)
             def get_weather(location: str) -> str:
@@ -2390,7 +2390,7 @@ class ChatAnthropic(BaseChatModel):
             messages = [
                 HumanMessage(content="What's the weather like in San Francisco?"),
             ]
-            llm.get_num_tokens_from_messages(messages, tools=[get_weather])
+            model.get_num_tokens_from_messages(messages, tools=[get_weather])
             ```
 
             ```txt
diff --git a/libs/partners/deepseek/langchain_deepseek/chat_models.py b/libs/partners/deepseek/langchain_deepseek/chat_models.py
index 7abfd3ebd63..bc185d366fc 100644
--- a/libs/partners/deepseek/langchain_deepseek/chat_models.py
+++ b/libs/partners/deepseek/langchain_deepseek/chat_models.py
@@ -59,7 +59,7 @@ class ChatDeepSeek(BaseChatOpenAI):
         ```python
         from langchain_deepseek import ChatDeepSeek
 
-        llm = ChatDeepSeek(
+        model = ChatDeepSeek(
             model="...",
             temperature=0,
             max_tokens=None,
@@ -76,16 +76,16 @@ class ChatDeepSeek(BaseChatOpenAI):
             ("system", "You are a helpful translator. Translate the user sentence to French."),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
     Stream:
         ```python
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.text, end="")
         ```
         ```python
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -94,13 +94,13 @@ class ChatDeepSeek(BaseChatOpenAI):
 
     Async:
         ```python
-        await llm.ainvoke(messages)
+        await model.ainvoke(messages)
 
         # stream:
-        # async for chunk in (await llm.astream(messages))
+        # async for chunk in (await model.astream(messages))
 
         # batch:
-        # await llm.abatch([messages])
+        # await model.abatch([messages])
         ```
 
     Tool calling:
@@ -120,8 +120,8 @@ class ChatDeepSeek(BaseChatOpenAI):
             location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
 
 
-        llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
-        ai_msg = llm_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
+        model_with_tools = model.bind_tools([GetWeather, GetPopulation])
+        ai_msg = model_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
         ai_msg.tool_calls
         ```
 
@@ -142,15 +142,15 @@ class ChatDeepSeek(BaseChatOpenAI):
             rating: int | None = Field(description="How funny the joke is, from 1 to 10")
 
 
-        structured_llm = llm.with_structured_output(Joke)
-        structured_llm.invoke("Tell me a joke about cats")
+        structured_model = model.with_structured_output(Joke)
+        structured_model.invoke("Tell me a joke about cats")
         ```
 
         See `ChatDeepSeek.with_structured_output()` for more.
 
     Token usage:
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.usage_metadata
         ```
         ```python
@@ -158,7 +158,7 @@ class ChatDeepSeek(BaseChatOpenAI):
         ```
     Response metadata
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.response_metadata
         ```
     """  # noqa: E501
diff --git a/libs/partners/fireworks/langchain_fireworks/chat_models.py b/libs/partners/fireworks/langchain_fireworks/chat_models.py
index 52be161d902..9c242b1eaf5 100644
--- a/libs/partners/fireworks/langchain_fireworks/chat_models.py
+++ b/libs/partners/fireworks/langchain_fireworks/chat_models.py
@@ -748,13 +748,13 @@ class ChatFireworks(BaseChatModel):
                 )
 
 
-            llm = ChatFireworks(
+            model = ChatFireworks(
                 model="accounts/fireworks/models/firefunction-v1",
                 temperature=0,
             )
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
 
@@ -778,15 +778,15 @@ class ChatFireworks(BaseChatModel):
                 justification: str
 
 
-            llm = ChatFireworks(
+            model = ChatFireworks(
                 model="accounts/fireworks/models/firefunction-v1",
                 temperature=0,
             )
-            structured_llm = llm.with_structured_output(
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -813,13 +813,13 @@ class ChatFireworks(BaseChatModel):
                 ]
 
 
-            llm = ChatFireworks(
+            model = ChatFireworks(
                 model="accounts/fireworks/models/firefunction-v1",
                 temperature=0,
             )
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -849,13 +849,13 @@ class ChatFireworks(BaseChatModel):
                 },
             }
 
-            llm = ChatFireworks(
+            model = ChatFireworks(
                 model="accounts/fireworks/models/firefunction-v1",
                 temperature=0,
             )
-            structured_llm = llm.with_structured_output(oai_schema)
+            structured_model = model.with_structured_output(oai_schema)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -876,14 +876,14 @@ class ChatFireworks(BaseChatModel):
                 justification: str
 
 
-            llm = ChatFireworks(
+            model = ChatFireworks(
                 model="accounts/fireworks/models/firefunction-v1", temperature=0
             )
-            structured_llm = llm.with_structured_output(
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'. "
                 "What's heavier a pound of bricks or a pound of feathers?"
@@ -898,11 +898,11 @@ class ChatFireworks(BaseChatModel):
         Example: schema=None, method="json_mode", include_raw=True:
 
             ```python
-            structured_llm = llm.with_structured_output(
+            structured_model = model.with_structured_output(
                 method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'. "
                 "What's heavier a pound of bricks or a pound of feathers?"
diff --git a/libs/partners/groq/langchain_groq/chat_models.py b/libs/partners/groq/langchain_groq/chat_models.py
index 7f4bb628638..64c72fbdd8d 100644
--- a/libs/partners/groq/langchain_groq/chat_models.py
+++ b/libs/partners/groq/langchain_groq/chat_models.py
@@ -124,7 +124,7 @@ class ChatGroq(BaseChatModel):
         ```python
         from langchain_groq import ChatGroq
 
-        llm = ChatGroq(
+        model = ChatGroq(
             model="llama-3.1-8b-instant",
             temperature=0.0,
             max_retries=2,
@@ -138,7 +138,7 @@ class ChatGroq(BaseChatModel):
             ("system", "You are a helpful translator. Translate the user sentence to French."),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
         ```python
         AIMessage(content='The English sentence "I love programming" can
@@ -155,7 +155,7 @@ class ChatGroq(BaseChatModel):
     Stream:
         ```python
         # Streaming `text` for each content chunk received
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.text, end="")
         ```
 
@@ -173,7 +173,7 @@ class ChatGroq(BaseChatModel):
 
         ```python
         # Reconstructing a full response
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -195,7 +195,7 @@ class ChatGroq(BaseChatModel):
 
     Async:
         ```python
-        await llm.ainvoke(messages)
+        await model.ainvoke(messages)
         ```
 
         ```python
@@ -228,7 +228,7 @@ class ChatGroq(BaseChatModel):
             location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
 
 
-        model_with_tools = llm.bind_tools([GetWeather, GetPopulation])
+        model_with_tools = model.bind_tools([GetWeather, GetPopulation])
         ai_msg = model_with_tools.invoke("What is the population of NY?")
         ai_msg.tool_calls
         ```
@@ -260,7 +260,7 @@ class ChatGroq(BaseChatModel):
             rating: int | None = Field(description="How funny the joke is, from 1 to 10")
 
 
-        structured_model = llm.with_structured_output(Joke)
+        structured_model = model.with_structured_output(Joke)
         structured_model.invoke("Tell me a joke about cats")
         ```
 
@@ -276,7 +276,7 @@ class ChatGroq(BaseChatModel):
 
     Response metadata:
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.response_metadata
         ```
 
@@ -921,10 +921,10 @@ class ChatGroq(BaseChatModel):
                 justification: str | None = Field(default=None, description="A justification for the answer.")
 
 
-            llm = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
 
             # -> AnswerWithJustification(
             #     answer='They weigh the same',
@@ -945,13 +945,13 @@ class ChatGroq(BaseChatModel):
                 justification: str
 
 
-            llm = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification,
                 include_raw=True,
             )
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
             # -> {
             #     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
             #     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
@@ -973,10 +973,10 @@ class ChatGroq(BaseChatModel):
                 justification: Annotated[str | None, None, "A justification for the answer."]
 
 
-            llm = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
             # -> {
             #     'answer': 'They weigh the same',
             #     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
@@ -999,10 +999,10 @@ class ChatGroq(BaseChatModel):
                     'required': ['answer']
                 }
 
-                llm = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
-                structured_llm = llm.with_structured_output(oai_schema)
+                model = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
+                structured_model = model.with_structured_output(oai_schema)
 
-                structured_llm.invoke(
+                structured_model.invoke(
                     "What weighs more a pound of bricks or a pound of feathers"
                 )
                 # -> {
@@ -1029,13 +1029,13 @@ class ChatGroq(BaseChatModel):
                 justification: str | None = Field(default=None, description="A justification for the answer.")
 
 
-            llm = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification,
                 method="json_schema",
             )
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
 
             # -> AnswerWithJustification(
             #     answer='They weigh the same',
@@ -1054,12 +1054,12 @@ class ChatGroq(BaseChatModel):
                 justification: str
 
 
-            llm = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatGroq(model="openai/gpt-oss-120b", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\n\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
diff --git a/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py b/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
index 2f65ee79c53..fe9f2111855 100644
--- a/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
+++ b/libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py
@@ -352,7 +352,7 @@ class ChatHuggingFace(BaseChatModel):
         from langchain_huggingface import HuggingFaceEndpoint,
         ChatHuggingFace
 
-        llm = HuggingFaceEndpoint(
+        model = HuggingFaceEndpoint(
             repo_id="microsoft/Phi-3-mini-4k-instruct",
             task="text-generation",
             max_new_tokens=512,
@@ -360,7 +360,7 @@ class ChatHuggingFace(BaseChatModel):
             repetition_penalty=1.03,
         )
 
-        chat = ChatHuggingFace(llm=llm, verbose=True)
+        chat = ChatHuggingFace(llm=model, verbose=True)
         ```
 
     Invoke:
diff --git a/libs/partners/huggingface/langchain_huggingface/llms/huggingface_endpoint.py b/libs/partners/huggingface/langchain_huggingface/llms/huggingface_endpoint.py
index 4ee76521c36..1fa41ffed3d 100644
--- a/libs/partners/huggingface/langchain_huggingface/llms/huggingface_endpoint.py
+++ b/libs/partners/huggingface/langchain_huggingface/llms/huggingface_endpoint.py
@@ -36,7 +36,7 @@ class HuggingFaceEndpoint(LLM):
     Example:
         ```python
         # Basic Example (no streaming)
-        llm = HuggingFaceEndpoint(
+        model = HuggingFaceEndpoint(
             endpoint_url="http://localhost:8010/",
             max_new_tokens=512,
             top_k=10,
@@ -46,13 +46,13 @@ class HuggingFaceEndpoint(LLM):
             repetition_penalty=1.03,
             huggingfacehub_api_token="my-api-key",
         )
-        print(llm.invoke("What is Deep Learning?"))
+        print(model.invoke("What is Deep Learning?"))
 
         # Streaming response example
         from langchain_core.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
         callbacks = [StreamingStdOutCallbackHandler()]
-        llm = HuggingFaceEndpoint(
+        model = HuggingFaceEndpoint(
             endpoint_url="http://localhost:8010/",
             max_new_tokens=512,
             top_k=10,
@@ -64,17 +64,17 @@ class HuggingFaceEndpoint(LLM):
             streaming=True,
             huggingfacehub_api_token="my-api-key",
         )
-        print(llm.invoke("What is Deep Learning?"))
+        print(model.invoke("What is Deep Learning?"))
 
         # Basic Example (no streaming) with Mistral-Nemo-Base-2407 model using a third-party provider (Novita).
-        llm = HuggingFaceEndpoint(
+        model = HuggingFaceEndpoint(
             repo_id="mistralai/Mistral-Nemo-Base-2407",
             provider="novita",
             max_new_tokens=100,
             do_sample=False,
             huggingfacehub_api_token="my-api-key",
         )
-        print(llm.invoke("What is Deep Learning?"))
+        print(model.invoke("What is Deep Learning?"))
         ```
     """  # noqa: E501
 
diff --git a/libs/partners/mistralai/langchain_mistralai/chat_models.py b/libs/partners/mistralai/langchain_mistralai/chat_models.py
index 88e999db270..578f0acdaa5 100644
--- a/libs/partners/mistralai/langchain_mistralai/chat_models.py
+++ b/libs/partners/mistralai/langchain_mistralai/chat_models.py
@@ -827,10 +827,10 @@ class ChatMistralAI(BaseChatModel):
                 )
 
 
-            llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatMistralAI(model="mistral-large-latest", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
 
@@ -853,12 +853,12 @@ class ChatMistralAI(BaseChatModel):
                 justification: str
 
 
-            llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatMistralAI(model="mistral-large-latest", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -884,10 +884,10 @@ class ChatMistralAI(BaseChatModel):
                 ]
 
 
-            llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatMistralAI(model="mistral-large-latest", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -912,10 +912,10 @@ class ChatMistralAI(BaseChatModel):
                     'required': ['answer']
                 }
 
-                llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
-                structured_llm = llm.with_structured_output(oai_schema)
+                model = ChatMistralAI(model="mistral-large-latest", temperature=0)
+                structured_model = model.with_structured_output(oai_schema)
 
-                structured_llm.invoke(
+                structured_model.invoke(
                     "What weighs more a pound of bricks or a pound of feathers"
                 )
                 # -> {
@@ -935,12 +935,12 @@ class ChatMistralAI(BaseChatModel):
                 justification: str
 
 
-            llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatMistralAI(model="mistral-large-latest", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\\n\\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
@@ -954,11 +954,11 @@ class ChatMistralAI(BaseChatModel):
 
         Example: schema=None, method="json_mode", include_raw=True:
             ```python
-            structured_llm = llm.with_structured_output(
+            structured_model = model.with_structured_output(
                 method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\\n\\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
diff --git a/libs/partners/ollama/langchain_ollama/chat_models.py b/libs/partners/ollama/langchain_ollama/chat_models.py
index 2e63b51d310..9eefcb04e3d 100644
--- a/libs/partners/ollama/langchain_ollama/chat_models.py
+++ b/libs/partners/ollama/langchain_ollama/chat_models.py
@@ -294,7 +294,7 @@ class ChatOllama(BaseChatModel):
         ```python
         from langchain_ollama import ChatOllama
 
-        llm = ChatOllama(
+        model = ChatOllama(
             model="gpt-oss:20b",
             validate_model_on_init=True,
             temperature=0.8,
@@ -309,7 +309,7 @@ class ChatOllama(BaseChatModel):
             ("system", "You are a helpful translator. Translate the user sentence to French."),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
         ```python
@@ -318,7 +318,7 @@ class ChatOllama(BaseChatModel):
 
     Stream:
         ```python
-        for chunk in llm.stream("Return the words Hello World!"):
+        for chunk in model.stream("Return the words Hello World!"):
             print(chunk.text, end="")
         ```
 
@@ -331,7 +331,7 @@ class ChatOllama(BaseChatModel):
         ```
 
         ```python
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -359,7 +359,7 @@ class ChatOllama(BaseChatModel):
 
     Async:
         ```python
-        await llm.ainvoke("Hello how are you!")
+        await model.ainvoke("Hello how are you!")
         ```
 
         ```python
@@ -383,7 +383,7 @@ class ChatOllama(BaseChatModel):
         ```
 
         ```python
-        async for chunk in llm.astream("Say hello world!"):
+        async for chunk in model.astream("Say hello world!"):
             print(chunk.content)
         ```
 
@@ -396,7 +396,7 @@ class ChatOllama(BaseChatModel):
 
         ```python
         messages = [("human", "Say hello world!"), ("human", "Say goodbye world!")]
-        await llm.abatch(messages)
+        await model.abatch(messages)
         ```
 
         ```python
@@ -440,8 +440,8 @@ class ChatOllama(BaseChatModel):
 
     JSON mode:
         ```python
-        json_llm = ChatOllama(format="json")
-        llm.invoke(
+        json_model = ChatOllama(format="json")
+        json_model.invoke(
             "Return a query for the weather in a random location and time of day with two keys: location and time_of_day. "
             "Respond using JSON only."
         ).content
@@ -495,18 +495,18 @@ class ChatOllama(BaseChatModel):
         ```python
         from langchain_ollama import ChatOllama
 
-        llm = ChatOllama(
+        model = ChatOllama(
             model="deepseek-r1:8b",
             validate_model_on_init=True,
             reasoning=True,
         )
 
-        llm.invoke("how many r in the word strawberry?")
+        model.invoke("how many r in the word strawberry?")
 
         # or, on an invocation basis:
 
-        llm.invoke("how many r in the word strawberry?", reasoning=True)
-        # or llm.stream("how many r in the word strawberry?", reasoning=True)
+        model.invoke("how many r in the word strawberry?", reasoning=True)
+        # or model.stream("how many r in the word strawberry?", reasoning=True)
 
         # If not provided, the invocation will default to the ChatOllama reasoning
         # param provided (None by default).
@@ -1327,10 +1327,10 @@ class ChatOllama(BaseChatModel):
                 )
 
 
-            llm = ChatOllama(model="llama3.1", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatOllama(model="llama3.1", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
 
             # -> AnswerWithJustification(
             #     answer='They weigh the same',
@@ -1352,13 +1352,13 @@ class ChatOllama(BaseChatModel):
                 justification: str
 
 
-            llm = ChatOllama(model="llama3.1", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatOllama(model="llama3.1", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification,
                 include_raw=True,
             )
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
             # -> {
             #     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
             #     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
@@ -1385,13 +1385,13 @@ class ChatOllama(BaseChatModel):
                 )
 
 
-            llm = ChatOllama(model="llama3.1", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatOllama(model="llama3.1", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification,
                 method="function_calling",
             )
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
 
             # -> AnswerWithJustification(
             #     answer='They weigh the same',
@@ -1414,10 +1414,10 @@ class ChatOllama(BaseChatModel):
                 justification: Annotated[str | None, None, "A justification for the answer."]
 
 
-            llm = ChatOllama(model="llama3.1", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatOllama(model="llama3.1", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+            structured_model.invoke("What weighs more a pound of bricks or a pound of feathers")
             # -> {
             #     'answer': 'They weigh the same',
             #     'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
@@ -1441,10 +1441,10 @@ class ChatOllama(BaseChatModel):
                     'required': ['answer']
                 }
 
-                llm = ChatOllama(model="llama3.1", temperature=0)
-                structured_llm = llm.with_structured_output(oai_schema)
+                model = ChatOllama(model="llama3.1", temperature=0)
+                structured_model = model.with_structured_output(oai_schema)
 
-                structured_llm.invoke(
+                structured_model.invoke(
                     "What weighs more a pound of bricks or a pound of feathers"
                 )
                 # -> {
@@ -1465,12 +1465,12 @@ class ChatOllama(BaseChatModel):
                 justification: str
 
 
-            llm = ChatOllama(model="llama3.1", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatOllama(model="llama3.1", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\\n\\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
diff --git a/libs/partners/ollama/langchain_ollama/llms.py b/libs/partners/ollama/langchain_ollama/llms.py
index 45a0a79fece..42b387a381c 100644
--- a/libs/partners/ollama/langchain_ollama/llms.py
+++ b/libs/partners/ollama/langchain_ollama/llms.py
@@ -66,7 +66,7 @@ class OllamaLLM(BaseLLM):
         ```python
         from langchain_ollama import OllamaLLM
 
-        llm = OllamaLLM(
+        model = OllamaLLM(
             model="llama3.1",
             temperature=0.7,
             num_predict=256,
@@ -78,7 +78,7 @@ class OllamaLLM(BaseLLM):
     Invoke:
         ```python
         input_text = "The meaning of life is "
-        response = llm.invoke(input_text)
+        response = model.invoke(input_text)
         print(response)
         ```
         ```txt
@@ -88,7 +88,7 @@ class OllamaLLM(BaseLLM):
 
     Stream:
         ```python
-        for chunk in llm.stream(input_text):
+        for chunk in model.stream(input_text):
             print(chunk, end="")
         ```
         ```txt
@@ -98,10 +98,10 @@ class OllamaLLM(BaseLLM):
 
     Async:
         ```python
-        response = await llm.ainvoke(input_text)
+        response = await model.ainvoke(input_text)
 
         # stream:
-        # async for chunk in llm.astream(input_text):
+        # async for chunk in model.astream(input_text):
         #     print(chunk, end="")
         ```
     """
diff --git a/libs/partners/openai/langchain_openai/chat_models/azure.py b/libs/partners/openai/langchain_openai/chat_models/azure.py
index 602b91f6980..215a4b691d8 100644
--- a/libs/partners/openai/langchain_openai/chat_models/azure.py
+++ b/libs/partners/openai/langchain_openai/chat_models/azure.py
@@ -82,7 +82,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
         ```python
         from langchain_openai import AzureChatOpenAI
 
-        llm = AzureChatOpenAI(
+        model = AzureChatOpenAI(
             azure_deployment="your-deployment",
             api_version="2024-05-01-preview",
             temperature=0,
@@ -127,7 +127,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
             ),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
         ```python
@@ -172,7 +172,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
 
     Stream:
         ```python
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.text, end="")
         ```
 
@@ -200,7 +200,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
         ```
 
         ```python
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -221,13 +221,13 @@ class AzureChatOpenAI(BaseChatOpenAI):
 
     Async:
         ```python
-        await llm.ainvoke(messages)
+        await model.ainvoke(messages)
 
         # stream:
-        # async for chunk in (await llm.astream(messages))
+        # async for chunk in (await model.astream(messages))
 
         # batch:
-        # await llm.abatch([messages])
+        # await model.abatch([messages])
         ```
 
     Tool calling:
@@ -251,8 +251,8 @@ class AzureChatOpenAI(BaseChatOpenAI):
             )
 
 
-        llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
-        ai_msg = llm_with_tools.invoke(
+        model_with_tools = model.bind_tools([GetWeather, GetPopulation])
+        ai_msg = model_with_tools.invoke(
             "Which city is hotter today and which is bigger: LA or NY?"
         )
         ai_msg.tool_calls
@@ -300,8 +300,8 @@ class AzureChatOpenAI(BaseChatOpenAI):
             )
 
 
-        structured_llm = llm.with_structured_output(Joke)
-        structured_llm.invoke("Tell me a joke about cats")
+        structured_model = model.with_structured_output(Joke)
+        structured_model.invoke("Tell me a joke about cats")
         ```
 
         ```python
@@ -316,8 +316,8 @@ class AzureChatOpenAI(BaseChatOpenAI):
 
     JSON mode:
         ```python
-        json_llm = llm.bind(response_format={"type": "json_object"})
-        ai_msg = json_llm.invoke(
+        json_model = model.bind(response_format={"type": "json_object"})
+        ai_msg = json_model.invoke(
             "Return a JSON object with key 'random_ints' and a value of 10 random ints in [0-99]"
         )
         ai_msg.content
@@ -344,7 +344,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
                 },
             ]
         )
-        ai_msg = llm.invoke([message])
+        ai_msg = model.invoke([message])
         ai_msg.content
         ```
 
@@ -354,7 +354,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
 
     Token usage:
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.usage_metadata
         ```
 
@@ -363,8 +363,8 @@ class AzureChatOpenAI(BaseChatOpenAI):
         ```
     Logprobs:
         ```python
-        logprobs_llm = llm.bind(logprobs=True)
-        ai_msg = logprobs_llm.invoke(messages)
+        logprobs_model = model.bind(logprobs=True)
+        ai_msg = logprobs_model.invoke(messages)
         ai_msg.response_metadata["logprobs"]
         ```
 
@@ -422,7 +422,7 @@ class AzureChatOpenAI(BaseChatOpenAI):
 
     Response metadata
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.response_metadata
         ```
 
@@ -911,16 +911,16 @@ class AzureChatOpenAI(BaseChatOpenAI):
                         \"\"\"Get weather at a location.\"\"\"
                         pass
 
-                    llm = init_chat_model("openai:gpt-4o-mini")
+                    model = init_chat_model("openai:gpt-4o-mini")
 
-                    structured_llm = llm.with_structured_output(
+                    structured_model = model.with_structured_output(
                         ResponseSchema,
                         tools=[get_weather],
                         strict=True,
                         include_raw=True,
                     )
 
-                    structured_llm.invoke("What's the weather in Boston?")
+                    structured_model.invoke("What's the weather in Boston?")
                     ```
 
                     ```python
@@ -986,10 +986,12 @@ class AzureChatOpenAI(BaseChatOpenAI):
                 )
 
 
-            llm = AzureChatOpenAI(azure_deployment="...", model="gpt-4o", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = AzureChatOpenAI(
+                azure_deployment="...", model="gpt-4o", temperature=0
+            )
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
 
@@ -1017,12 +1019,14 @@ class AzureChatOpenAI(BaseChatOpenAI):
                 )
 
 
-            llm = AzureChatOpenAI(azure_deployment="...", model="gpt-4o", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = AzureChatOpenAI(
+                azure_deployment="...", model="gpt-4o", temperature=0
+            )
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="function_calling"
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
 
@@ -1046,12 +1050,14 @@ class AzureChatOpenAI(BaseChatOpenAI):
                 justification: str
 
 
-            llm = AzureChatOpenAI(azure_deployment="...", model="gpt-4o", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = AzureChatOpenAI(
+                azure_deployment="...", model="gpt-4o", temperature=0
+            )
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -1078,10 +1084,12 @@ class AzureChatOpenAI(BaseChatOpenAI):
                 ]
 
 
-            llm = AzureChatOpenAI(azure_deployment="...", model="gpt-4o", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = AzureChatOpenAI(
+                azure_deployment="...", model="gpt-4o", temperature=0
+            )
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             # -> {
@@ -1107,14 +1115,14 @@ class AzureChatOpenAI(BaseChatOpenAI):
                     'required': ['answer']
                 }
 
-                llm = AzureChatOpenAI(
+                model = AzureChatOpenAI(
                     azure_deployment="...",
                     model="gpt-4o",
                     temperature=0,
                 )
-                structured_llm = llm.with_structured_output(oai_schema)
+                structured_model = model.with_structured_output(oai_schema)
 
-                structured_llm.invoke(
+                structured_model.invoke(
                     "What weighs more a pound of bricks or a pound of feathers"
                 )
                 # -> {
@@ -1135,16 +1143,16 @@ class AzureChatOpenAI(BaseChatOpenAI):
                 justification: str
 
 
-            llm = AzureChatOpenAI(
+            model = AzureChatOpenAI(
                 azure_deployment="...",
                 model="gpt-4o",
                 temperature=0,
             )
-            structured_llm = llm.with_structured_output(
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\\n\\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
@@ -1159,11 +1167,11 @@ class AzureChatOpenAI(BaseChatOpenAI):
         ??? note "Example: `schema=None`, `method='json_mode'`, `include_raw=True`"
 
             ```python
-            structured_llm = llm.with_structured_output(
+            structured_model = model.with_structured_output(
                 method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\\n\\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
diff --git a/libs/partners/openai/langchain_openai/chat_models/base.py b/libs/partners/openai/langchain_openai/chat_models/base.py
index 8fffd34e6ae..20bbeac10f5 100644
--- a/libs/partners/openai/langchain_openai/chat_models/base.py
+++ b/libs/partners/openai/langchain_openai/chat_models/base.py
@@ -654,11 +654,11 @@ class BaseChatOpenAI(BaseChatModel):
     For example, the following two are equivalent:
 
     ```python
-    llm = ChatOpenAI(
+    model = ChatOpenAI(
         model="...",
         use_previous_response_id=True,
     )
-    llm.invoke(
+    model.invoke(
         [
             HumanMessage("Hello"),
             AIMessage("Hi there!", response_metadata={"id": "resp_123"}),
@@ -668,8 +668,8 @@ class BaseChatOpenAI(BaseChatModel):
     ```
 
     ```python
-    llm = ChatOpenAI(model="...", use_responses_api=True)
-    llm.invoke([HumanMessage("How are you?")], previous_response_id="resp_123")
+    model = ChatOpenAI(model="...", use_responses_api=True)
+    model.invoke([HumanMessage("How are you?")], previous_response_id="resp_123")
     ```
 
     !!! version-added "Added in version 0.3.26"
@@ -1801,16 +1801,16 @@ class BaseChatOpenAI(BaseChatModel):
                         \"\"\"Get weather at a location.\"\"\"
                         pass
 
-                    llm = init_chat_model("openai:gpt-4o-mini")
+                    model = init_chat_model("openai:gpt-4o-mini")
 
-                    structured_llm = llm.with_structured_output(
+                    structured_model = model.with_structured_output(
                         ResponseSchema,
                         tools=[get_weather],
                         strict=True,
                         include_raw=True,
                     )
 
-                    structured_llm.invoke("What's the weather in Boston?")
+                    structured_model.invoke("What's the weather in Boston?")
                     ```
 
                     ```python
@@ -2057,7 +2057,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from langchain_openai import ChatOpenAI
 
-        llm = ChatOpenAI(
+        model = ChatOpenAI(
             model="...",
             temperature=0,
             max_tokens=None,
@@ -2104,7 +2104,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             ),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
         Results in an `AIMessage` response:
@@ -2133,7 +2133,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         Stream a response from the model:
 
         ```python
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.text, end="")
         ```
 
@@ -2158,7 +2158,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         To collect the full message, you can concatenate the chunks:
 
         ```python
-        stream = llm.stream(messages)
+        stream = model.stream(messages)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -2178,13 +2178,13 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
 
         ```python
         # Invoke
-        await llm.ainvoke(messages)
+        await model.ainvoke(messages)
 
         # Stream
-        async for chunk in (await llm.astream(messages))
+        async for chunk in (await model.astream(messages))
 
         # Batch
-        await llm.abatch([messages])
+        await model.abatch([messages])
         ```
 
         Results in an `AIMessage` response:
@@ -2236,11 +2236,11 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             )
 
 
-        llm_with_tools = llm.bind_tools(
+        model_with_tools = model.bind_tools(
             [GetWeather, GetPopulation]
             # strict = True  # Enforce tool args schema is respected
         )
-        ai_msg = llm_with_tools.invoke(
+        ai_msg = model_with_tools.invoke(
             "Which city is hotter today and which is bigger: LA or NY?"
         )
         ai_msg.tool_calls
@@ -2277,7 +2277,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             be set to `False` to disable parallel tool calls:
 
             ```python
-            ai_msg = llm_with_tools.invoke(
+            ai_msg = model_with_tools.invoke(
                 "What is the weather in LA and NY?", parallel_tool_calls=False
             )
             ai_msg.tool_calls
@@ -2294,7 +2294,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             ```
 
         Like other runtime parameters, `parallel_tool_calls` can be bound to a model
-        using `llm.bind(parallel_tool_calls=False)` or during instantiation by
+        using `model.bind(parallel_tool_calls=False)` or during instantiation by
         setting `model_kwargs`.
 
         See `bind_tools` for more.
@@ -2308,12 +2308,12 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from langchain_openai import ChatOpenAI
 
-        llm = ChatOpenAI(model="...", output_version="responses/v1")
+        model = ChatOpenAI(model="...", output_version="responses/v1")
 
         tool = {"type": "web_search"}
-        llm_with_tools = llm.bind_tools([tool])
+        model_with_tools = model.bind_tools([tool])
 
-        response = llm_with_tools.invoke("What was a positive news story from today?")
+        response = model_with_tools.invoke("What was a positive news story from today?")
         response.content
         ```
 
@@ -2354,12 +2354,12 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from langchain_openai import ChatOpenAI
 
-        llm = ChatOpenAI(
+        model = ChatOpenAI(
             model="...",
             use_responses_api=True,
             output_version="responses/v1",
         )
-        response = llm.invoke("Hi, I'm Bob.")
+        response = model.invoke("Hi, I'm Bob.")
         response.text
         ```
 
@@ -2368,7 +2368,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ```
 
         ```python
-        second_response = llm.invoke(
+        second_response = model.invoke(
             "What is my name?",
             previous_response_id=response.response_metadata["id"],
         )
@@ -2388,7 +2388,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             recent response.
 
             ```python
-            llm = ChatOpenAI(model="...", use_previous_response_id=True)
+            model = ChatOpenAI(model="...", use_previous_response_id=True)
             ```
 
     ??? info "Reasoning output"
@@ -2404,10 +2404,10 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             "summary": "auto",  # 'detailed', 'auto', or None
         }
 
-        llm = ChatOpenAI(
+        model = ChatOpenAI(
             model="...", reasoning=reasoning, output_version="responses/v1"
         )
-        response = llm.invoke("What is 3^3?")
+        response = model.invoke("What is 3^3?")
 
         # Response text
         print(f"Output: {response.text}")
@@ -2448,8 +2448,8 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             )
 
 
-        structured_llm = llm.with_structured_output(Joke)
-        structured_llm.invoke("Tell me a joke about cats")
+        structured_model = model.with_structured_output(Joke)
+        structured_model.invoke("Tell me a joke about cats")
         ```
 
         ```python
@@ -2465,8 +2465,8 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
     ??? info "JSON mode"
 
         ```python
-        json_llm = llm.bind(response_format={"type": "json_object"})
-        ai_msg = json_llm.invoke(
+        json_model = model.bind(response_format={"type": "json_object"})
+        ai_msg = json_model.invoke(
             "Return a JSON object with key 'random_ints' and a value of 10 random ints in [0-99]"
         )
         ai_msg.content
@@ -2495,7 +2495,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
             ]
         )
 
-        ai_msg = llm.invoke([message])
+        ai_msg = model.invoke([message])
         ai_msg.content
         ```
 
@@ -2506,7 +2506,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
     ??? info "Token usage"
 
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.usage_metadata
 
         ```txt
@@ -2516,7 +2516,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         When streaming, set the `stream_usage` kwarg:
 
         ```python
-        stream = llm.stream(messages, stream_usage=True)
+        stream = model.stream(messages, stream_usage=True)
         full = next(stream)
         for chunk in stream:
             full += chunk
@@ -2530,8 +2530,8 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
     ??? info "Logprobs"
 
         ```python
-        logprobs_llm = llm.bind(logprobs=True)
-        ai_msg = logprobs_llm.invoke(messages)
+        logprobs_model = model.bind(logprobs=True)
+        ai_msg = logprobs_model.invoke(messages)
         ai_msg.response_metadata["logprobs"]
         ```
 
@@ -2590,7 +2590,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
     ??? info "Response metadata"
 
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.response_metadata
         ```
 
@@ -2621,7 +2621,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from langchain_openai import ChatOpenAI
 
-        llm = ChatOpenAI(model="...", service_tier="flex")
+        model = ChatOpenAI(model="...", service_tier="flex")
         ```
 
         Note that this is a beta feature that is only available for a subset of models.
@@ -2639,7 +2639,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ```python title="LM Studio example with TTL (auto-eviction)"
         from langchain_openai import ChatOpenAI
 
-        llm = ChatOpenAI(
+        model = ChatOpenAI(
             base_url="http://localhost:1234/v1",
             api_key="lm-studio",  # Can be any string
             model="mlx-community/QwQ-32B-4bit",
@@ -2649,7 +2649,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ```
 
         ```python title="vLLM example with custom parameters"
-        llm = ChatOpenAI(
+        model = ChatOpenAI(
             base_url="http://localhost:8000/v1",
             api_key="EMPTY",
             model="meta-llama/Llama-2-7b-chat-hf",
@@ -2669,7 +2669,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
 
         ```python
         # Standard OpenAI parameters
-        llm = ChatOpenAI(
+        model = ChatOpenAI(
             model="...",
             model_kwargs={
                 "stream_options": {"include_usage": True},
@@ -2689,7 +2689,7 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
 
         ```python
         # Custom provider parameters
-        llm = ChatOpenAI(
+        model = ChatOpenAI(
             base_url="http://localhost:8000/v1",
             model="custom-model",
             extra_body={
@@ -2715,19 +2715,19 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         per-invocation to improve cache hit rates and reduce costs:
 
         ```python
-        llm = ChatOpenAI(model="...")
+        model = ChatOpenAI(model="...")
 
-        response = llm.invoke(
+        response = model.invoke(
             messages,
             prompt_cache_key="example-key-a",  # Routes to same machine for cache hits
         )
 
-        customer_response = llm.invoke(messages, prompt_cache_key="example-key-b")
-        support_response = llm.invoke(messages, prompt_cache_key="example-key-c")
+        customer_response = model.invoke(messages, prompt_cache_key="example-key-b")
+        support_response = model.invoke(messages, prompt_cache_key="example-key-c")
 
         # Dynamic cache keys based on context
         cache_key = f"example-key-{dynamic_suffix}"
-        response = llm.invoke(messages, prompt_cache_key=cache_key)
+        response = model.invoke(messages, prompt_cache_key=cache_key)
         ```
 
         Cache keys help ensure requests with the same prompt prefix are routed to
@@ -2905,16 +2905,16 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
                         \"\"\"Get weather at a location.\"\"\"
                         pass
 
-                    llm = init_chat_model("openai:gpt-4o-mini")
+                    model = init_chat_model("openai:gpt-4o-mini")
 
-                    structured_llm = llm.with_structured_output(
+                    structured_model = model.with_structured_output(
                         ResponseSchema,
                         tools=[get_weather],
                         strict=True,
                         include_raw=True,
                     )
 
-                    structured_llm.invoke("What's the weather in Boston?")
+                    structured_model.invoke("What's the weather in Boston?")
                     ```
 
                     ```python
@@ -2971,10 +2971,10 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
                 )
 
 
-            llm = ChatOpenAI(model="...", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatOpenAI(model="...", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             ```
@@ -3002,12 +3002,12 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
                 )
 
 
-            llm = ChatOpenAI(model="...", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatOpenAI(model="...", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="function_calling"
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             ```
@@ -3033,12 +3033,12 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
                 justification: str
 
 
-            llm = ChatOpenAI(model="...", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatOpenAI(model="...", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             ```
@@ -3085,10 +3085,10 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
                 ]
 
 
-            llm = ChatOpenAI(model="...", temperature=0)
-            structured_llm = llm.with_structured_output(AnswerWithJustification)
+            model = ChatOpenAI(model="...", temperature=0)
+            structured_model = model.with_structured_output(AnswerWithJustification)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             ```
@@ -3121,10 +3121,10 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
                 },
             }
 
-            llm = ChatOpenAI(model="...", temperature=0)
-            structured_llm = llm.with_structured_output(oai_schema)
+            model = ChatOpenAI(model="...", temperature=0)
+            structured_model = model.with_structured_output(oai_schema)
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "What weighs more a pound of bricks or a pound of feathers"
             )
             ```
@@ -3148,12 +3148,12 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
                 justification: str
 
 
-            llm = ChatOpenAI(model="...", temperature=0)
-            structured_llm = llm.with_structured_output(
+            model = ChatOpenAI(model="...", temperature=0)
+            structured_model = model.with_structured_output(
                 AnswerWithJustification, method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\\n\\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
@@ -3176,11 +3176,11 @@ class ChatOpenAI(BaseChatOpenAI):  # type: ignore[override]
         ??? note "Example: `schema=None`, `method='json_mode'`, `include_raw=True`"
 
             ```python
-            structured_llm = llm.with_structured_output(
+            structured_model = model.with_structured_output(
                 method="json_mode", include_raw=True
             )
 
-            structured_llm.invoke(
+            structured_model.invoke(
                 "Answer the following question. "
                 "Make sure to return a JSON blob with keys 'answer' and 'justification'.\\n\\n"
                 "What's heavier a pound of bricks or a pound of feathers?"
diff --git a/libs/partners/openai/langchain_openai/llms/base.py b/libs/partners/openai/langchain_openai/llms/base.py
index 1668854bba2..b835526552b 100644
--- a/libs/partners/openai/langchain_openai/llms/base.py
+++ b/libs/partners/openai/langchain_openai/llms/base.py
@@ -110,7 +110,7 @@ class BaseOpenAI(BaseLLM):
         ```python
         from langchain_openai.llms.base import BaseOpenAI
 
-        llm = BaseOpenAI(
+        model = BaseOpenAI(
             model_name="gpt-3.5-turbo-instruct",
             temperature=0.7,
             max_tokens=256,
@@ -127,7 +127,7 @@ class BaseOpenAI(BaseLLM):
     Invoke:
         ```python
         input_text = "The meaning of life is "
-        response = llm.invoke(input_text)
+        response = model.invoke(input_text)
         print(response)
         ```
 
@@ -138,7 +138,7 @@ class BaseOpenAI(BaseLLM):
 
     Stream:
         ```python
-        for chunk in llm.stream(input_text):
+        for chunk in model.stream(input_text):
             print(chunk, end="")
         ```
         ```txt
@@ -148,14 +148,14 @@ class BaseOpenAI(BaseLLM):
 
     Async:
         ```python
-        response = await llm.ainvoke(input_text)
+        response = await model.ainvoke(input_text)
 
         # stream:
-        # async for chunk in llm.astream(input_text):
+        # async for chunk in model.astream(input_text):
         #     print(chunk, end="")
 
         # batch:
-        # await llm.abatch([input_text])
+        # await model.abatch([input_text])
         ```
         ```
         "a philosophical question that has been debated by thinkers and
@@ -739,7 +739,7 @@ class OpenAI(BaseOpenAI):
         ```python
         from langchain_openai import OpenAI
 
-        llm = OpenAI(
+        model = OpenAI(
             model="gpt-3.5-turbo-instruct",
             temperature=0,
             max_retries=2,
@@ -753,7 +753,7 @@ class OpenAI(BaseOpenAI):
     Invoke:
         ```python
         input_text = "The meaning of life is "
-        llm.invoke(input_text)
+        model.invoke(input_text)
         ```
         ```txt
         "a philosophical question that has been debated by thinkers and scholars for centuries."
@@ -761,7 +761,7 @@ class OpenAI(BaseOpenAI):
 
     Stream:
         ```python
-        for chunk in llm.stream(input_text):
+        for chunk in model.stream(input_text):
             print(chunk, end="|")
         ```
         ```txt
@@ -769,7 +769,7 @@ class OpenAI(BaseOpenAI):
         ```
 
         ```python
-        "".join(llm.stream(input_text))
+        "".join(model.stream(input_text))
         ```
         ```txt
         "a philosophical question that has been debated by thinkers and scholars for centuries."
@@ -777,14 +777,14 @@ class OpenAI(BaseOpenAI):
 
     Async:
         ```python
-        await llm.ainvoke(input_text)
+        await model.ainvoke(input_text)
 
         # stream:
-        # async for chunk in (await llm.astream(input_text)):
+        # async for chunk in (await model.astream(input_text)):
         #    print(chunk)
 
         # batch:
-        # await llm.abatch([input_text])
+        # await model.abatch([input_text])
         ```
         ```txt
         "a philosophical question that has been debated by thinkers and scholars for centuries."
diff --git a/libs/partners/openai/langchain_openai/tools/custom_tool.py b/libs/partners/openai/langchain_openai/tools/custom_tool.py
index 0724d56277c..bf8b1ad1bcf 100644
--- a/libs/partners/openai/langchain_openai/tools/custom_tool.py
+++ b/libs/partners/openai/langchain_openai/tools/custom_tool.py
@@ -38,9 +38,9 @@ def custom_tool(*args: Any, **kwargs: Any) -> Any:
         return "27"
 
 
-    llm = ChatOpenAI(model="gpt-5", output_version="responses/v1")
+    model = ChatOpenAI(model="gpt-5", output_version="responses/v1")
 
-    agent = create_react_agent(llm, [execute_code])
+    agent = create_react_agent(model, [execute_code])
 
     input_message = {"role": "user", "content": "Use the tool to calculate 3^3."}
     for step in agent.stream(
@@ -79,9 +79,9 @@ def custom_tool(*args: Any, **kwargs: Any) -> Any:
         return "27"
 
 
-    llm = ChatOpenAI(model="gpt-5", output_version="responses/v1")
+    model = ChatOpenAI(model="gpt-5", output_version="responses/v1")
 
-    agent = create_react_agent(llm, [do_math])
+    agent = create_react_agent(model, [do_math])
 
     input_message = {"role": "user", "content": "Use the tool to calculate 3^3."}
     for step in agent.stream(
diff --git a/libs/partners/perplexity/langchain_perplexity/chat_models.py b/libs/partners/perplexity/langchain_perplexity/chat_models.py
index 3cd1b1a76d7..7566792fe9e 100644
--- a/libs/partners/perplexity/langchain_perplexity/chat_models.py
+++ b/libs/partners/perplexity/langchain_perplexity/chat_models.py
@@ -96,14 +96,14 @@ class ChatPerplexity(BaseChatModel):
         ```python
         from langchain_perplexity import ChatPerplexity
 
-        llm = ChatPerplexity(model="sonar", temperature=0.7)
+        model = ChatPerplexity(model="sonar", temperature=0.7)
         ```
 
         Invoke:
 
         ```python
         messages = [("system", "You are a chatbot."), ("user", "Hello!")]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
         Invoke with structured output:
@@ -117,31 +117,31 @@ class ChatPerplexity(BaseChatModel):
             content: str
 
 
-        llm.with_structured_output(StructuredOutput)
-        llm.invoke(messages)
+        model.with_structured_output(StructuredOutput)
+        model.invoke(messages)
         ```
 
         Invoke with perplexity-specific params:
 
         ```python
-        llm.invoke(messages, extra_body={"search_recency_filter": "week"})
+        model.invoke(messages, extra_body={"search_recency_filter": "week"})
         ```
 
         Stream:
         ```python
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.content)
         ```
 
         Token usage:
         ```python
-        response = llm.invoke(messages)
+        response = model.invoke(messages)
         response.usage_metadata
         ```
 
         Response metadata:
         ```python
-        response = llm.invoke(messages)
+        response = model.invoke(messages)
         response.response_metadata
         ```
     """  # noqa: E501
diff --git a/libs/partners/xai/langchain_xai/chat_models.py b/libs/partners/xai/langchain_xai/chat_models.py
index 2f0224bfa21..5bfd2fb62d7 100644
--- a/libs/partners/xai/langchain_xai/chat_models.py
+++ b/libs/partners/xai/langchain_xai/chat_models.py
@@ -62,7 +62,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from langchain_xai import ChatXAI
 
-        llm = ChatXAI(
+        model = ChatXAI(
             model="grok-4",
             temperature=0,
             max_tokens=None,
@@ -82,7 +82,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
             ),
             ("human", "I love programming."),
         ]
-        llm.invoke(messages)
+        model.invoke(messages)
         ```
 
         ```python
@@ -110,7 +110,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
 
     Stream:
         ```python
-        for chunk in llm.stream(messages):
+        for chunk in model.stream(messages):
             print(chunk.text, end="")
         ```
 
@@ -129,13 +129,13 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
 
     Async:
         ```python
-        await llm.ainvoke(messages)
+        await model.ainvoke(messages)
 
         # stream:
-        # async for chunk in (await llm.astream(messages))
+        # async for chunk in (await model.astream(messages))
 
         # batch:
-        # await llm.abatch([messages])
+        # await model.abatch([messages])
         ```
 
         ```python
@@ -192,7 +192,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from pydantic import BaseModel, Field
 
-        llm = ChatXAI(model="grok-4")
+        model = ChatXAI(model="grok-4")
 
 
         class GetWeather(BaseModel):
@@ -207,8 +207,8 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
             location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
 
 
-        llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
-        ai_msg = llm_with_tools.invoke("Which city is bigger: LA or NY?")
+        model_with_tools = model.bind_tools([GetWeather, GetPopulation])
+        ai_msg = model_with_tools.invoke("Which city is bigger: LA or NY?")
         ai_msg.tool_calls
         ```
 
@@ -237,12 +237,12 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
         constructor's `extra_body` argument. For example, to disable tool / function calling:
 
         ```python
-        llm = ChatXAI(model="grok-4", extra_body={"tool_choice": "none"})
+        model = ChatXAI(model="grok-4", extra_body={"tool_choice": "none"})
         ```
         To require that the model always calls a tool / function, set `tool_choice` to `'required'`:
 
         ```python
-        llm = ChatXAI(model="grok-4", extra_body={"tool_choice": "required"})
+        model = ChatXAI(model="grok-4", extra_body={"tool_choice": "required"})
         ```
 
         To specify a tool / function to call, set `tool_choice` to the name of the tool / function:
@@ -250,7 +250,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from pydantic import BaseModel, Field
 
-        llm = ChatXAI(
+        model = ChatXAI(
             model="grok-4",
             extra_body={
                 "tool_choice": {"type": "function", "function": {"name": "GetWeather"}}
@@ -269,8 +269,8 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
             location: str = Field(..., description='The city and state, e.g. San Francisco, CA')
 
 
-        llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
-        ai_msg = llm_with_tools.invoke(
+        model_with_tools = model.bind_tools([GetWeather, GetPopulation])
+        ai_msg = model_with_tools.invoke(
             "Which city is bigger: LA or NY?",
         )
         ai_msg.tool_calls
@@ -309,8 +309,8 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
             rating: int | None = Field(description="How funny the joke is, from 1 to 10")
 
 
-        structured_llm = llm.with_structured_output(Joke)
-        structured_llm.invoke("Tell me a joke about cats")
+        structured_model = model.with_structured_output(Joke)
+        structured_model.invoke("Tell me a joke about cats")
         ```
 
         ```python
@@ -328,7 +328,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
         ```python
         from langchain_xai import ChatXAI
 
-        llm = ChatXAI(
+        model = ChatXAI(
             model="grok-4",
             search_parameters={
                 "mode": "auto",
@@ -339,7 +339,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
             },
         )
 
-        llm.invoke("Provide me a digest of world news in the last 24 hours.")
+        model.invoke("Provide me a digest of world news in the last 24 hours.")
         ```
 
         !!! note
@@ -348,7 +348,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
 
     Token usage:
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.usage_metadata
         ```
 
@@ -358,9 +358,9 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
 
     Logprobs:
         ```python
-        logprobs_llm = llm.bind(logprobs=True)
+        logprobs_model = model.bind(logprobs=True)
         messages = [("human", "Say Hello World! Do not return anything else.")]
-        ai_msg = logprobs_llm.invoke(messages)
+        ai_msg = logprobs_model.invoke(messages)
         ai_msg.response_metadata["logprobs"]
         ```
 
@@ -375,7 +375,7 @@ class ChatXAI(BaseChatOpenAI):  # type: ignore[override]
 
     Response metadata
         ```python
-        ai_msg = llm.invoke(messages)
+        ai_msg = model.invoke(messages)
         ai_msg.response_metadata
         ```
 
diff --git a/libs/standard-tests/langchain_tests/integration_tests/chat_models.py b/libs/standard-tests/langchain_tests/integration_tests/chat_models.py
index e20085e1306..07303e5a61f 100644
--- a/libs/standard-tests/langchain_tests/integration_tests/chat_models.py
+++ b/libs/standard-tests/langchain_tests/integration_tests/chat_models.py
@@ -1498,8 +1498,8 @@ class ChatModelIntegrationTests(ChatModelTests):
         prompt = ChatPromptTemplate.from_messages(
             [("human", "Hello. Please respond in the style of {answer_style}.")]
         )
-        llm = GenericFakeChatModel(messages=iter(["hello matey"]))
-        chain = prompt | llm | StrOutputParser()
+        model = GenericFakeChatModel(messages=iter(["hello matey"]))
+        chain = prompt | model | StrOutputParser()
         tool_ = chain.as_tool(
             name="greeting_generator",
             description="Generate a greeting in a particular style of speaking.",