chore: use latest chat model names

src/langsmith/define-target-function.mdx

@@ -87,7 +87,7 @@ const target = async(inputs) => {
 ```python Python (LangChain)
 from langchain.chat_models import init_chat_model
 
-model = init_chat_model("openai:gpt-4o-mini")
+model = init_chat_model("gpt-4o-mini")
 
 def target(inputs: dict) -> dict:
   # This assumes your dataset has inputs with a `messages` key

src/langsmith/evaluate-complex-agent.mdx

@@ -322,7 +322,7 @@ def lookup_album( ...
 def lookup_artist( ...
 
 # Agent model
-qa_llm = init_chat_model("claude-3-5-sonnet-latest")
+qa_llm = init_chat_model("claude-sonnet-4-5-20250929")
 # The prebuilt ReACT agent only expects State to have a 'messages' key, so the
 # state we defined for the refund agent can also be passed to our lookup agent.
 qa_graph = create_agent(qa_llm, tools=[lookup_track, lookup_artist, lookup_album])
@@ -1260,7 +1260,7 @@ def lookup_artist(
 
 
 # Agent model
-qa_llm = init_chat_model("claude-3-5-sonnet-latest")
+qa_llm = init_chat_model("claude-sonnet-4-5-20250929")
 # The prebuilt ReACT agent only expects State to have a 'messages' key, so the
 # state we defined for the refund agent can also be passed to our lookup agent.
 qa_graph = create_agent(qa_llm, [lookup_track, lookup_artist, lookup_album])

src/langsmith/evaluate-graph.mdx

@@ -42,7 +42,7 @@ def search(query: str) -> str:
 
 tools = [search]
 tool_node = ToolNode(tools)
-model = init_chat_model("claude-3-5-sonnet-latest").bind_tools(tools)
+model = init_chat_model("claude-sonnet-4-5-20250929").bind_tools(tools)
 
 # Define the function that determines whether to continue or not
 def should_continue(state: State) -> Literal["tools", END]:
@@ -282,7 +282,7 @@ def search(query: str) -> str:
 
 tools = [search]
 tool_node = ToolNode(tools)
-model = init_chat_model("claude-3-5-sonnet-latest").bind_tools(tools)
+model = init_chat_model("claude-sonnet-4-5-20250929").bind_tools(tools)
 
 # Define the function that determines whether to continue or not
 def should_continue(state: State) -> Literal["tools", END]:

src/langsmith/generative-ui-react.mdx

@@ -367,7 +367,7 @@ Then you can push updates to the UI component by calling `ui.push()` / `push_ui_
 
 
     async def writer_node(state: AgentState):
-        model = ChatAnthropic(model="claude-3-5-sonnet-latest")
+        model = ChatAnthropic(model="claude-sonnet-4-5-20250929")
         message: AIMessage = await model.bind_tools(
             tools=[CreateTextDocument],
             tool_choice={"type": "tool", "name": "CreateTextDocument"},
@@ -432,7 +432,7 @@ Then you can push updates to the UI component by calling `ui.push()` / `push_ui_
     ): Promise<typeof AgentState.Update> {
       const ui = typedUi<typeof ComponentMap>(config);
 
-      const model = new ChatAnthropic({ model: "claude-3-5-sonnet-latest" });
+      const model = new ChatAnthropic({ model: "claude-sonnet-4-5-20250929" });
       const message = await model
         .bindTools(
           [

src/langsmith/human-in-the-loop-time-travel.mdx

@@ -27,7 +27,7 @@ To time travel using the LangGraph Server API (via the LangGraph SDK):
         joke: NotRequired[str]
 
     model = init_chat_model(
-        "anthropic:claude-sonnet-4-5",
+        "claude-sonnet-4-5-20250929",
         temperature=0,
     )
 

src/langsmith/log-llm-trace.mdx

@@ -397,7 +397,7 @@ def chat_model(inputs: dict) -> dict:
 When using a custom model, it is recommended to also provide the following `metadata` fields to identify the model when viewing traces and when filtering.
 
 * `ls_provider`: The provider of the model, eg "openai", "anthropic", etc.
-* `ls_model_name`: The name of the model, eg "gpt-4o-mini", "claude-3-opus-20240307", etc.
+* `ls_model_name`: The name of the model, eg "gpt-4o-mini", "claude-3-opus-20240229", etc.
 
 <CodeGroup>
 

src/langsmith/manage-prompts-programmatically.mdx

@@ -349,7 +349,7 @@ const { messages, system } = convertPromptToAnthropic(formattedPrompt);
 
 const anthropicClient = new Anthropic();
 const anthropicResponse = await anthropicClient.messages.create({
-  model: "claude-3-haiku-20240307",
+  model: "claude-haiku-4-5-20251001",
   system,
   messages,
   max_tokens: 1024,

src/langsmith/observability-studio.mdx

@@ -78,8 +78,8 @@ class Configuration(BaseModel):
 
     model: Annotated[
         Literal[
-            "anthropic/claude-sonnet-4-5",
-            "anthropic/claude-3-5-haiku-latest",
+            "anthropic/claude-sonnet-4-5-20250929",
+            "anthropic/claude-haiku-4-5-20251001",
             "openai/o1",
             "openai/gpt-4o-mini",
             "openai/o1-mini",

src/langsmith/server-mcp.mdx

@@ -154,7 +154,7 @@ Use an MCP-compliant client to connect to the LangGraph server. The following ex
                 tools = await load_mcp_tools(session)
 
                 # Create and run a react agent with the tools
-                agent = create_agent("openai:gpt-4.1", tools)
+                agent = create_agent("gpt-4.1", tools)
 
                 # Invoke the agent with a message
                 agent_response = await agent.ainvoke({"messages": "What can the finance agent do for me?"})

src/langsmith/streaming.mdx

@@ -649,7 +649,7 @@ The streamed output from [`messages-tuple` mode](#supported-stream-modes) is a t
         topic: str
         joke: str = ""
 
-    model = init_chat_model(model="openai:gpt-4o-mini")
+    model = init_chat_model(model="gpt-4o-mini")
 
     def call_model(state: MyState):
         """Call the LLM to generate a joke about a topic"""

src/langsmith/test-react-agent-pytest.mdx

@@ -194,7 +194,7 @@ class AgentOutputFormat(TypedDict):
     reasoning: Annotated[str, ..., "The reasoning behind the answer"]
 
 agent = create_agent(
-    model="openai:gpt-4o-mini",
+    model="gpt-4o-mini",
     tools=[code_tool, search_tool, polygon_aggregates],
     response_format=AgentOutputFormat,
     system_prompt="You are a financial expert. Respond to the users query accurately",
@@ -766,7 +766,7 @@ Remember to also add the config files for [Vitest](#config-files-for-vitestjest)
         reasoning: Annotated[str, ..., "The reasoning behind the answer"]
 
     agent = create_agent(
-        model="openai:gpt-4o-mini",
+        model="gpt-4o-mini",
         tools=[code_tool, search_tool, polygon_aggregates],
         response_format=AgentOutputFormat,
         system_prompt="You are a financial expert. Respond to the users query accurately",

src/langsmith/trace-claude-agent-sdk.mdx

@@ -70,7 +70,7 @@ async def main():
     )
 
     options = ClaudeAgentOptions(
-        model="claude-sonnet-4-5",
+        model="claude-sonnet-4-5-20250929",
         system_prompt="You are a friendly travel assistant who helps with weather information.",
         mcp_servers={"weather": weather_server},
         allowed_tools=["mcp__weather__get_weather"],

src/langsmith/trajectory-evals.mdx

@@ -70,7 +70,7 @@ def get_weather(city: str):
     """Get weather information for a city."""
     return f"It's 75 degrees and sunny in {city}."
 
-agent = create_agent("openai:gpt-4o", tools=[get_weather])
+agent = create_agent("gpt-4o", tools=[get_weather])
 
 evaluator = create_trajectory_match_evaluator(  # [!code highlight]
     trajectory_match_mode="strict",  # [!code highlight]
@@ -121,7 +121,7 @@ const getWeather = tool(
 );
 
 const agent = createAgent({
-  model: "openai:gpt-4o",
+  model: "gpt-4o",
   tools: [getWeather]
 });
 
@@ -187,7 +187,7 @@ def get_events(city: str):
     """Get events happening in a city."""
     return f"Concert at the park in {city} tonight."
 
-agent = create_agent("openai:gpt-4o", tools=[get_weather, get_events])
+agent = create_agent("gpt-4o", tools=[get_weather, get_events])
 
 evaluator = create_trajectory_match_evaluator(  # [!code highlight]
     trajectory_match_mode="unordered",  # [!code highlight]
@@ -249,7 +249,7 @@ const getEvents = tool(
 );
 
 const agent = createAgent({
-  model: "openai:gpt-4o",
+  model: "gpt-4o",
   tools: [getWeather, getEvents]
 });
 
@@ -325,7 +325,7 @@ def get_detailed_forecast(city: str):
     """Get detailed weather forecast for a city."""
     return f"Detailed forecast for {city}: sunny all week."
 
-agent = create_agent("openai:gpt-4o", tools=[get_weather, get_detailed_forecast])
+agent = create_agent("gpt-4o", tools=[get_weather, get_detailed_forecast])
 
 evaluator = create_trajectory_match_evaluator(  # [!code highlight]
     trajectory_match_mode="superset",  # [!code highlight]
@@ -388,7 +388,7 @@ const getDetailedForecast = tool(
 );
 
 const agent = createAgent({
-  model: "openai:gpt-4o",
+  model: "gpt-4o",
   tools: [getWeather, getDetailedForecast]
 });
 
@@ -460,7 +460,7 @@ def get_weather(city: str):
     """Get weather information for a city."""
     return f"It's 75 degrees and sunny in {city}."
 
-agent = create_agent("openai:gpt-4o", tools=[get_weather])
+agent = create_agent("gpt-4o", tools=[get_weather])
 
 evaluator = create_trajectory_llm_as_judge(  # [!code highlight]
     model="openai:o3-mini",  # [!code highlight]
@@ -502,7 +502,7 @@ const getWeather = tool(
 );
 
 const agent = createAgent({
-  model: "openai:gpt-4o",
+  model: "gpt-4o",
   tools: [getWeather]
 });
 

src/oss/concepts/context.mdx

@@ -64,7 +64,7 @@ graph.invoke(
         return f"You are a helpful assistant. Address the user as {user_name}."
 
     agent = create_agent(
-        model="anthropic:claude-sonnet-4-5",
+        model="claude-sonnet-4-5-20250929",
         tools=[get_weather],
         middleware=[personalized_prompt],
         context_schema=ContextSchema
@@ -145,6 +145,7 @@ await graph.invoke(
     State can also be accessed by the agent's **tools**, which can read or update the state as needed. See [tool calling guide](/oss/langchain/tools#short-term-memory) for details.
 
     :::python
+
     ```python
     from langchain.agents import create_agent
     from langchain.agents.middleware import dynamic_prompt, ModelRequest
@@ -160,7 +161,7 @@ await graph.invoke(
         return f"You are a helpful assistant. User's name is {user_name}"
 
     agent = create_agent(
-        model="anthropic:claude-sonnet-4-5",
+        model="claude-sonnet-4-5-20250929",
         tools=[...],
         state_schema=CustomState,  # [!code highlight]
         middleware=[personalized_prompt],  # [!code highlight]
@@ -174,6 +175,7 @@ await graph.invoke(
     :::
 
     :::js
+
     ```typescript
     import { createAgent, createMiddleware } from "langchain";
     import type { AgentState } from "langchain";
@@ -194,7 +196,7 @@ await graph.invoke(
     });
 
     const agent = createAgent({  // [!code highlight]
-      model: "anthropic:claude-sonnet-4-5",
+      model: "claude-sonnet-4-5-20250929",
       tools: [/* your tools here */],
       middleware: [personalizedPrompt] as const, // [!code highlight]
     });

src/oss/deepagents/customization.mdx

@@ -14,7 +14,7 @@ from langchain.chat_models import init_chat_model
 from deepagents import create_deep_agent
 
 model = init_chat_model(
-    model="openai:gpt-5",
+    model="gpt-5",
 )
 agent = create_deep_agent(
     model=model,

src/oss/deepagents/human-in-the-loop.mdx

@@ -38,7 +38,7 @@ def send_email(to: str, subject: str, body: str) -> str:
 checkpointer = MemorySaver()
 
 agent = create_deep_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     tools=[delete_file, read_file, send_email],
     interrupt_on={
         "delete_file": True,  # Default: approve, edit, reject

src/oss/deepagents/middleware.mdx

@@ -30,7 +30,7 @@ from langchain.agents.middleware import TodoListMiddleware
 # TodoListMiddleware is included by default in create_deep_agent
 # You can customize it if building a custom agent
 agent = create_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     # Custom planning instructions can be added via middleware
     middleware=[
         TodoListMiddleware(
@@ -65,7 +65,7 @@ from deepagents.middleware.filesystem import FilesystemMiddleware
 # FilesystemMiddleware is included by default in create_deep_agent
 # You can customize it if building a custom agent
 agent = create_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     middleware=[
         FilesystemMiddleware(
             long_term_memory=False,  # Enables access to long-term memory, defaults to False. You must attach a store to use long-term memory.
@@ -92,7 +92,7 @@ from langgraph.store.memory import InMemoryStore
 store = InMemoryStore()
 
 agent = create_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     store=store,
     middleware=[
         FilesystemMiddleware(
@@ -133,10 +133,10 @@ def get_weather(city: str) -> str:
     return f"The weather in {city} is sunny."
 
 agent = create_agent(
-    model="claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     middleware=[
         SubAgentMiddleware(
-            default_model="claude-sonnet-4-20250514",
+            default_model="claude-sonnet-4-5-20250929",
             default_tools=[],
             subagents=[
                 {
@@ -180,10 +180,10 @@ weather_subagent = CompiledSubAgent(
 )
 
 agent = create_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     middleware=[
         SubAgentMiddleware(
-            default_model="claude-sonnet-4-20250514",
+            default_model="claude-sonnet-4-5-20250929",
             default_tools=[],
             subagents=[weather_subagent],
         )

src/oss/deepagents/subagents.mdx

@@ -82,7 +82,7 @@ research_subagent = {
 subagents = [research_subagent]
 
 agent = create_deep_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     subagents=subagents
 )
 ```
@@ -113,7 +113,7 @@ custom_subagent = CompiledSubAgent(
 subagents = [custom_subagent]
 
 agent = create_deep_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     tools=[internet_search],
     system_prompt=research_instructions,
     subagents=subagents
@@ -223,7 +223,7 @@ subagents = [
         "description": "Reviews legal documents and contracts",
         "system_prompt": "You are an expert legal reviewer...",
         "tools": [read_document, analyze_contract],
-        "model": "anthropic:claude-sonnet-4-20250514",  # Large context for long documents
+        "model": "claude-sonnet-4-5-20250929",  # Large context for long documents
     },
     {
         "name": "financial-analyst",
@@ -302,7 +302,7 @@ subagents = [
 ]
 
 agent = create_deep_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="claude-sonnet-4-5-20250929",
     system_prompt="You coordinate data analysis and reporting. Use subagents for specialized tasks.",
     subagents=subagents
 )