update to gemini

src/langsmith/evaluate-graph.mdx

@@ -187,7 +187,7 @@ async def main():
         max_concurrency=4,  # optional
         experiment_prefix="claude-sonnet-4-6-baseline",  # optional
         metadata={  # optional, used to populate model/prompt/tool columns in UI
-            "models": "anthropic:claude-sonnet-4-6",
+            "models": "google_genai:gemini-3.1-pro-preview",
             "tools": [{"name": "search", "description": "Call to surf the web."}],
         },
     )
@@ -215,7 +215,7 @@ async def main():
         max_concurrency=4,  # optional
         experiment_prefix="claude-sonnet-4-6-baseline",  # optional
         metadata={  # optional, used to populate model/prompt/tool columns in UI
-            "models": "anthropic:claude-sonnet-4-6",
+            "models": "google_genai:gemini-3.1-pro-preview",
             "tools": [{"name": "search", "description": "Call to surf the web."}],
         },
     )
@@ -246,7 +246,7 @@ async def main():
         max_concurrency=4,  # optional
         experiment_prefix="claude-sonnet-4-6-baseline",  # optional
         metadata={  # optional, used to populate model/prompt/tool columns in UI
-            "models": "anthropic:claude-sonnet-4-6",
+            "models": "google_genai:gemini-3.1-pro-preview",
             "tools": [{"name": "search", "description": "Call to surf the web."}],
         },
     )
@@ -268,7 +268,7 @@ async def main():
         max_concurrency=4,  # optional
         experiment_prefix="claude-sonnet-4-6-model-node",  # optional
         metadata={  # optional, used to populate model/prompt/tool columns in UI
-            "models": "anthropic:claude-sonnet-4-6",
+            "models": "google_genai:gemini-3.1-pro-preview",
             "tools": [{"name": "search", "description": "Call to surf the web."}],
         },
     )
@@ -432,7 +432,7 @@ async def main():
         max_concurrency=4,  # optional
         experiment_prefix="claude-sonnet-4-6-baseline",  # optional
         metadata={  # optional, used to populate model/prompt/tool columns in UI
-            "models": "anthropic:claude-sonnet-4-6",
+            "models": "google_genai:gemini-3.1-pro-preview",
             "tools": [{"name": "search", "description": "Call to surf the web."}],
         },
     )

src/oss/concepts/providers-and-models.mdx

@@ -150,17 +150,17 @@ To find available model names for a provider, refer to the provider's own docume
 
 ## Use new models immediately
 
-Because LangChain provider packages pass model names directly to the provider's API, you can use new models the moment a provider releases them — no LangChain update required. Simply pass the new model name:
+Because LangChain provider packages pass model names directly to the provider's API, you can use new models the moment a provider releases them—no LangChain update required. Simply pass the new model name:
 
 :::python
 ```python
-model = init_chat_model("anthropic:claude-mythos")
+model = init_chat_model("google_genai:gemini-mythos")
 ```
 :::
 
 :::js
 ```typescript
-const model = await initChatModel("anthropic:claude-mythos");
+const model = await initChatModel("google_genai:gemini-mythos");
 ```
 :::
 

src/oss/deepagents/cli/configuration.mdx

@@ -70,7 +70,7 @@ Then override per-project where needed by placing a `.env` in the project direct
 ```toml
 [models]
 default = "ollama:qwen3:4b"             # your intentional long-term preference
-recent = "anthropic:claude-sonnet-4-5"   # last /model switch (written automatically)
+recent = "google_genai:gemini-3.1-pro-preview"   # last /model switch (written automatically)
 ```
 
 `[models].default` always takes priority over `[models].recent`. The `/model` command only writes to `[models].recent`, so your configured default is never overwritten by mid-session switches. To remove the default, use `/model --default --clear` or delete the `default` key from the config file.
@@ -223,7 +223,7 @@ To override model profile fields at runtime without editing the config file, pas
 deepagents --profile-override '{"max_input_tokens": 4096}'
 
 # Combine with --model
-deepagents --model anthropic:claude-sonnet-4-5 --profile-override '{"max_input_tokens": 4096}'
+deepagents --model google_genai:gemini-3.1-pro-preview --profile-override '{"max_input_tokens": 4096}'
 
 # In non-interactive mode
 deepagents -n "Summarize this repo" --profile-override '{"max_input_tokens": 4096}'

src/oss/deepagents/cli/overview.mdx

@@ -334,7 +334,7 @@ For full details on switching models, setting a default, and adding custom model
         Pass extra model constructor parameters when switching mid-session using `--model-params`:
 
         ```txt
-        > /model --model-params '{"temperature": 0.7}' anthropic:claude-sonnet-4-5
+        > /model --model-params '{"temperature": 0.7}' anthropic:claude-opus-4-7
         > /model --model-params '{"temperature": 0.7}'  # opens selector, applies params to chosen model
         ```
 
@@ -842,8 +842,8 @@ When configured, the CLI displays a status line with a link to the LangSmith pro
 deepagents --agent mybot
 
 # Use a specific model (provider:model format or auto-detect)
-deepagents --model anthropic:claude-sonnet-4-5
-deepagents --model gpt-4o
+deepagents --model anthropic:claude-opus-4-7
+deepagents --model gpt-5.4
 
 # Auto-approve tool usage (skip human-in-the-loop prompts)
 deepagents -y

src/oss/deepagents/customization.mdx

@@ -86,10 +86,10 @@ For the full parameter list, see the [`createDeepAgent`](https://reference.langc
 
 ## Model
 
-Pass a `model` string in `provider:model` format, or an initialized model instance. Defaults to `anthropic:claude-sonnet-4-6`. See [supported models](/oss/deepagents/models#supported-models) for all providers and [suggested models](/oss/deepagents/models#suggested-models) for tested recommendations.
+Pass a `model` string in `provider:model` format, or an initialized model instance. See [supported models](/oss/deepagents/models#supported-models) for all providers and [suggested models](/oss/deepagents/models#suggested-models) for tested recommendations.
 
 <Tip>
-    Use the `provider:model` format (for example `openai:gpt-5`) to quickly switch between models.
+    Use the `provider:model` format (for example `openai:gpt-5.4`) to quickly switch between models.
 </Tip>
 
 :::python

src/oss/deepagents/deploy.mdx

@@ -145,7 +145,7 @@ Core agent identity. For more on model selection and provider configuration, see
     Name for the deployed agent. Used as the assistant identifier in LangSmith.
 </ResponseField>
 
-<ResponseField name="model" type="string" default="anthropic:claude-sonnet-4-6">
+<ResponseField name="model" type="string">
     Model identifier in `provider:model` format. See [supported models](/oss/deepagents/models#supported-models).
 </ResponseField>
 
@@ -373,7 +373,7 @@ Each subagent subdirectory **may** contain:
 [agent]
 name = "researcher"
 description = "Researches market trends, competitors, and target audiences"
-model = "anthropic:claude-haiku-4-5-20251001"
+model = "google_genai:gemini-3.1-pro-preview"
 ```
 
 ### Inheritance
@@ -404,14 +404,14 @@ A go-to-market agent that delegates research to a specialized subagent:
 ```toml deepagents.toml
 [agent]
 name = "gtm-strategist"
-model = "anthropic:claude-sonnet-4-6"
+model = "google_genai:gemini-3.1-pro-preview"
 ```
 
 ```toml subagents/researcher/deepagents.toml
 [agent]
 name = "researcher"
 description = "Researches market trends, competitors, and target audiences to inform GTM strategy"
-model = "anthropic:claude-haiku-4-5-20251001"
+model = "google_genai:gemini-3.1-pro-preview"
 ```
 
 ```markdown subagents/researcher/AGENTS.md

src/oss/deepagents/quickstart.mdx

@@ -14,7 +14,7 @@ This guide walks you through creating your first deep agent with planning, file
 
 ## Prerequisites
 
-Before you begin, make sure you have an API key from a model provider (e.g., Anthropic, OpenAI).
+Before you begin, make sure you have an API key from a model provider (e.g., Gemini, Anthropic, OpenAI).
 
 <Note>
     Deep Agents require a model that supports [tool calling](/oss/langchain/models#tool-calling). See [customization](/oss/deepagents/customization#model) for how to configure your model.
@@ -208,7 +208,7 @@ Use this to run an internet search for a given query. You can specify the max nu
 """
 ```
 
-Pass a `model` string in `provider:model` format, or an initialized model instance. Defaults to `anthropic:claude-sonnet-4-6`. See [supported models](/oss/deepagents/models#supported-models) for all providers and [suggested models](/oss/deepagents/models#suggested-models) for tested recommendations.
+Pass a `model` string in `provider:model` format, or an initialized model instance. See [supported models](/oss/deepagents/models#supported-models) for all providers and [suggested models](/oss/deepagents/models#suggested-models) for tested recommendations.
 
 <Tabs>
     <Tab title="Google">

src/oss/langchain/agents.mdx

@@ -895,7 +895,7 @@ from langchain.agents import create_agent
 from langchain.messages import SystemMessage, HumanMessage
 
 literary_agent = create_agent(
-    model="anthropic:claude-sonnet-4-5",
+    model="google_genai:gemini-3.1-pro-preview",
     system_prompt=SystemMessage(
         content=[
             {
@@ -929,7 +929,7 @@ import { createAgent } from "langchain";
 import { SystemMessage, HumanMessage } from "@langchain/core/messages";
 
 const literaryAgent = createAgent({
-  model: "anthropic:claude-sonnet-4-5",
+  model: "google_genai:gemini-3.1-pro-preview",
   systemPrompt: new SystemMessage({
     content: [
       {

src/oss/langchain/frontend/integrations/copilotkit.mdx

@@ -290,7 +290,7 @@ const structuredOutputMiddleware = createMiddleware({
 });
 
 export const agent = createAgent({
-  model: process.env.COPILOTKIT_MODEL ?? "anthropic:claude-haiku-4-5",
+  model: process.env.COPILOTKIT_MODEL ?? "google_genai:gemini-3.1-pro-preview",
   contextSchema,
   middleware: [structuredOutputMiddleware],
   tools: [searchWebTool, deepSearchTool],

src/oss/langchain/mcp.mdx

@@ -527,7 +527,7 @@ async with client.session("server_name") as session:  # [!code highlight]
     # Pass the session to load tools, resources, or prompts
     tools = await load_mcp_tools(session)  # [!code highlight]
     agent = create_agent(
-        "anthropic:claude-3-7-sonnet-latest",
+        "google_genai:gemini-3.1-pro-preview",
         tools
     )
 ```

src/oss/langchain/middleware/built-in.mdx

@@ -1833,7 +1833,7 @@ const agent = createAgent({
 </ParamField>
 
 <ParamField body="model" type="string | BaseChatModel">
-    Model to use for generating emulated tool responses. Can be a model identifier string (e.g., `'anthropic:claude-sonnet-4-6'`) or a `BaseChatModel` instance. Defaults to the agent's model if not specified. See @[`init_chat_model`][init_chat_model(model)] for more information.
+    Model to use for generating emulated tool responses. Can be a model identifier string (e.g., `'google_genai:gemini-3.1-pro-preview'`) or a `BaseChatModel` instance. Defaults to the agent's model if not specified. See @[`init_chat_model`][init_chat_model(model)] for more information.
 </ParamField>
 :::
 
@@ -1843,7 +1843,7 @@ const agent = createAgent({
 </ParamField>
 
 <ParamField body="model" type="string | BaseChatModel">
-    Model to use for generating emulated tool responses. Can be a model identifier string (e.g., `'anthropic:claude-sonnet-4-6'`) or a `BaseChatModel` instance. Defaults to the agent's model if not specified.
+    Model to use for generating emulated tool responses. Can be a model identifier string (e.g., `'google_genai:gemini-3.1-pro-preview'`) or a `BaseChatModel` instance. Defaults to the agent's model if not specified.
 </ParamField>
 :::
 

src/oss/langchain/middleware/custom.mdx

@@ -1414,7 +1414,7 @@ const myOtherMiddleware = createMiddleware({
 });
 
 const agent = createAgent({
-  model: "anthropic:claude-3-5-sonnet",
+  model: "google_genai:gemini-3.1-pro-preview",
   systemPrompt: "You are a helpful assistant.",
   middleware: [myMiddleware, myOtherMiddleware],
 });

src/oss/langchain/multi-agent/handoffs-customer-support.mdx

@@ -1035,7 +1035,7 @@ from langchain.chat_models import init_chat_model
 from langchain.messages import HumanMessage, ToolMessage
 from langchain.tools import tool, ToolRuntime
 
-model = init_chat_model("anthropic:claude-3-5-sonnet-latest")
+model = init_chat_model("google_genai:gemini-3.1-pro-preview")
 
 
 # Define the possible workflow steps

src/oss/langchain/multi-agent/handoffs.mdx

@@ -478,13 +478,13 @@ def transfer_to_support(
 
 # 3. Create agents with handoff tools
 sales_agent = create_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="google_genai:gemini-3.1-pro-preview",
     tools=[transfer_to_support],
     system_prompt="You are a sales agent. Help with sales inquiries. If asked about technical issues or support, transfer to the support agent.",
 )
 
 support_agent = create_agent(
-    model="anthropic:claude-sonnet-4-20250514",
+    model="google_genai:gemini-3.1-pro-preview",
     tools=[transfer_to_sales],
     system_prompt="You are a support agent. Help with technical issues. If asked about pricing or purchasing, transfer to the sales agent.",
 )
@@ -636,14 +636,14 @@ const transferToSupport = tool(
 
 // 3. Create agents with handoff tools
 const salesAgent = createAgent({
-  model: "anthropic:claude-sonnet-4-20250514",
+  model: "google_genai:gemini-3.1-pro-preview",
   tools: [transferToSupport],
   systemPrompt:
     "You are a sales agent. Help with sales inquiries. If asked about technical issues or support, transfer to the support agent.",
 });
 
 const supportAgent = createAgent({
-  model: "anthropic:claude-sonnet-4-20250514",
+  model: "google_genai:gemini-3.1-pro-preview",
   tools: [transferToSales],
   systemPrompt:
     "You are a support agent. Help with technical issues. If asked about pricing or purchasing, transfer to the sales agent.",

src/oss/langchain/multi-agent/subagents.mdx

@@ -51,7 +51,7 @@ from langchain.tools import tool
 from langchain.agents import create_agent
 
 # Create a subagent
-subagent = create_agent(model="anthropic:claude-sonnet-4-20250514", tools=[...])
+subagent = create_agent(model="google_genai:gemini-3.1-pro-preview", tools=[...])
 
 # Wrap it as a tool
 @tool("research", description="Research a topic and return findings")
@@ -60,7 +60,7 @@ def call_research_agent(query: str):
     return result["messages"][-1].content
 
 # Main agent with subagent as a tool
-main_agent = create_agent(model="anthropic:claude-sonnet-4-20250514", tools=[call_research_agent])
+main_agent = create_agent(model="google_genai:gemini-3.1-pro-preview", tools=[call_research_agent])
 ```
 :::
 :::js
@@ -69,7 +69,7 @@ import { createAgent, tool } from "langchain";
 import { z } from "zod";
 
 // Create a subagent
-const subagent = createAgent({ model: "anthropic:claude-sonnet-4-20250514", tools: [...] });
+const subagent = createAgent({ model: "google_genai:gemini-3.1-pro-preview", tools: [...] });
 
 // Wrap it as a tool
 const callResearchAgent = tool(
@@ -87,7 +87,7 @@ const callResearchAgent = tool(
 );
 
 // Main agent with subagent as a tool
-const mainAgent = createAgent({ model: "anthropic:claude-sonnet-4-20250514", tools: [callResearchAgent] });
+const mainAgent = createAgent({ model: "google_genai:gemini-3.1-pro-preview", tools: [callResearchAgent] });
 ```
 :::