This guide provides a quick overview for getting started with Anthropic chat models. For detailed documentation of all ChatAnthropic features and configurations head to the API reference.Anthropic has several chat models. You can find information about their latest models and their costs, context windows, and supported input types in the Anthropic docs.
AWS Bedrock and Google VertexAINote that certain Anthropic models can also be accessed via AWS Bedrock and Google VertexAI. See the ChatBedrock and ChatVertexAI integrations to use Anthropic models via these services.
messages = [ ( "system", "You are a helpful assistant that translates English to French. Translate the user sentence.", ), ("human", "I love programming."),]ai_msg = llm.invoke(messages)ai_msg
When using tools, extended thinking, and other features, content from a single Anthropic AI message can either be a single string or a list of content blocks. For example, when an Anthropic model invokes a tool, the tool invocation is part of the message content (as well as being exposed in the standardized AIMessage.tool_calls):
Copy
from langchain_anthropic import ChatAnthropicfrom typing_extensions import Annotatedllm = ChatAnthropic(model="claude-3-5-haiku-latest")def get_weather( location: Annotated[str, ..., "Location as city and state."]) -> str: """Get the weather at a location.""" return "It's sunny."llm_with_tools = llm.bind_tools([get_weather])response = llm_with_tools.invoke("Which city is hotter today: LA or NY?")response.content
Copy
[{'text': "I'll help you compare the temperatures of Los Angeles and New York by checking their current weather. I'll retrieve the weather for both cities.", 'type': 'text'}, {'id': 'toolu_01CkMaXrgmsNjTso7so94RJq', 'input': {'location': 'Los Angeles, CA'}, 'name': 'get_weather', 'type': 'tool_use'}, {'id': 'toolu_01SKaTBk9wHjsBTw5mrPVSQf', 'input': {'location': 'New York, NY'}, 'name': 'get_weather', 'type': 'tool_use'}]
Using .content_blocks will render the content in a standard format that is
consistent across providers:
Copy
response.content_blocks
Copy
[{'type': 'text', 'text': "I'll help you compare the temperatures of Los Angeles and New York by checking their current weather. I'll retrieve the weather for both cities."}, {'type': 'tool_call', 'name': 'get_weather', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_01CkMaXrgmsNjTso7so94RJq'}, {'type': 'tool_call', 'name': 'get_weather', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01SKaTBk9wHjsBTw5mrPVSQf'}]
You can also access tool calls specifically in a standard format using the
.tool_calls attribute:
Claude supports image and PDF inputs as content blocks, both in Anthropic’s native format (see docs for vision and PDF support) as well as LangChain’s standard format.
Claude also supports interactions with files through its managed Files API. See examples below.The Files API can also be used to upload files to a container for use with Claude’s built-in code-execution tools. See the code execution section below, for details.
Some Claude models support an extended thinking feature, which will output the step-by-step reasoning process that led to its final answer.See applicable models in the Anthropic guide here.To use extended thinking, specify the thinking parameter when initializing ChatAnthropic. It can also be passed in as a kwarg during invocation.You will need to specify a token budget to use this feature. See usage example below:
Copy
import jsonfrom langchain_anthropic import ChatAnthropicllm = 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?")print(json.dumps(response.content_blocks, indent=2))
Copy
[ { "type": "reasoning", "reasoning": "To find the cube root of 50.653, I need to find the value of $x$ such that $x^3 = 50.653$.\n\nI can try to estimate this first. \n$3^3 = 27$\n$4^3 = 64$\n\nSo the cube root of 50.653 will be somewhere between 3 and 4, but closer to 4.\n\nLet me try to compute this more precisely. I can use the cube root function:\n\ncube root of 50.653 = 50.653^(1/3)\n\nLet me calculate this:\n50.653^(1/3) \u2248 3.6998\n\nLet me verify:\n3.6998^3 \u2248 50.6533\n\nThat's very close to 50.653, so I'm confident that the cube root of 50.653 is approximately 3.6998.\n\nActually, let me compute this more precisely:\n50.653^(1/3) \u2248 3.69981\n\nLet me verify once more:\n3.69981^3 \u2248 50.652998\n\nThat's extremely close to 50.653, so I'll say that the cube root of 50.653 is approximately 3.69981.", "extras": {"signature": "ErUBCkYIBxgCIkB0UjV..."} }, { "text": "The cube root of 50.653 is approximately 3.6998.\n\nTo verify: 3.6998\u00b3 = 50.6530, which is very close to our original number.", "type": "text" }]
Anthropic supports caching of elements of your prompts, including messages, tool definitions, tool results, images and documents. This allows you to re-use large documents, instructions, few-shot documents, and other data to reduce latency and costs.To enable caching on an element of a prompt, mark its associated content block using the cache_control key. See examples below:
First invocation:{'cache_read': 0, 'cache_creation': 1458}Second:{'cache_read': 1458, 'cache_creation': 0}
Extended cachingThe cache lifetime is 5 minutes by default. If this is too short, you can apply one hour caching by enabling the "extended-cache-ttl-2025-04-11" beta header:
and specifying "cache_control": {"type": "ephemeral", "ttl": "1h"}.Details of cached token counts will be included on the InputTokenDetails of response’s usage_metadata:
from langchain_anthropic import convert_to_anthropic_toolfrom langchain_core.tools import tool# For demonstration purposes, we artificially expand the# tool description.description = ( f"Get the weather at a location. By the way, check out this readme: {readme}")@tool(description=description)def get_weather(location: str) -> str: return "It's sunny."# Enable caching on the toolweather_tool = convert_to_anthropic_tool(get_weather)weather_tool["cache_control"] = {"type": "ephemeral"}llm = ChatAnthropic(model="claude-3-7-sonnet-20250219")llm_with_tools = llm.bind_tools([weather_tool])query = "What's the weather in San Francisco?"response_1 = llm_with_tools.invoke(query)response_2 = llm_with_tools.invoke(query)usage_1 = response_1.usage_metadata["input_token_details"]usage_2 = response_2.usage_metadata["input_token_details"]print(f"First invocation:\n{usage_1}")print(f"\nSecond:\n{usage_2}")
Copy
First invocation:{'cache_read': 0, 'cache_creation': 1809}Second:{'cache_read': 1809, 'cache_creation': 0}
Incremental caching in conversational applications
Prompt caching can be used in multi-turn conversations to maintain context from earlier messages without redundant processing.We can enable incremental caching by marking the final message with cache_control. Claude will automatically use the longest previously-cached prefix for follow-up messages.Below, we implement a simple chatbot that incorporates this feature. We follow the LangChain chatbot tutorial, but add a custom reducer that automatically marks the last content block in each user message with cache_control. See below:
Copy
import requestsfrom langchain_anthropic import ChatAnthropicfrom langgraph.checkpoint.memory import MemorySaverfrom langgraph.graph import START, StateGraph, add_messagesfrom typing_extensions import Annotated, TypedDictllm = ChatAnthropic(model="claude-3-7-sonnet-20250219")# Pull LangChain readmeget_response = requests.get( "https://raw.githubusercontent.com/langchain-ai/langchain/master/README.md")readme = get_response.textdef messages_reducer(left: list, right: list) -> list: # Update last user message for i in range(len(right) - 1, -1, -1): if right[i].type == "human": right[i].content[-1]["cache_control"] = {"type": "ephemeral"} break return add_messages(left, right)class State(TypedDict): messages: Annotated[list, messages_reducer]workflow = StateGraph(state_schema=State)# Define the function that calls the modeldef call_model(state: State): response = llm.invoke(state["messages"]) return {"messages": [response]}# Define the (single) node in the graphworkflow.add_edge(START, "model")workflow.add_node("model", call_model)# Add memorymemory = MemorySaver()app = workflow.compile(checkpointer=memory)
================================== Ai Message ==================================Hello, Bob! It's nice to meet you. How are you doing today? Is there something I can help you with?{'cache_read': 0, 'cache_creation': 0}
Copy
query = f"Check out this readme: {readme}"input_message = HumanMessage([{"type": "text", "text": query}])output = app.invoke({"messages": [input_message]}, config)output["messages"][-1].pretty_print()print(f"\n{output['messages'][-1].usage_metadata['input_token_details']}")
Copy
================================== Ai Message ==================================I can see you've shared the README from the LangChain GitHub repository. This is the documentation for LangChain, which is a popular framework for building applications powered by Large Language Models (LLMs). Here's a summary of what the README contains:LangChain is:- A framework for developing LLM-powered applications- Helps chain together components and integrations to simplify AI application development- Provides a standard interface for models, embeddings, vector stores, etc.Key features/benefits:- Real-time data augmentation (connect LLMs to diverse data sources)- Model interoperability (swap models easily as needed)- Large ecosystem of integrationsThe LangChain ecosystem includes:- LangSmith - For evaluations and observability- LangGraph - For building complex agents with customizable architecture- LangGraph Platform - For deployment and scaling of agentsThe README also mentions installation instructions (`pip install -U langchain`) and links to various resources including tutorials, how-to guides, conceptual guides, and API references.Is there anything specific about LangChain you'd like to know more about, Bob?{'cache_read': 0, 'cache_creation': 1498}
Copy
query = "What was my name again?"input_message = HumanMessage([{"type": "text", "text": query}])output = app.invoke({"messages": [input_message]}, config)output["messages"][-1].pretty_print()print(f"\n{output['messages'][-1].usage_metadata['input_token_details']}")
Copy
================================== Ai Message ==================================Your name is Bob. You introduced yourself at the beginning of our conversation.{'cache_read': 1498, 'cache_creation': 269}
In the LangSmith trace, toggling “raw output” will show exactly what messages are sent to the chat model, including cache_control keys.
Anthropic supports a (beta) token-efficient tool use feature. To use it, specify the relevant beta-headers when instantiating the model.
Copy
from langchain_anthropic import ChatAnthropicfrom langchain_core.tools import toolllm = ChatAnthropic( model="claude-3-7-sonnet-20250219", betas=["token-efficient-tools-2025-02-19"],)@tooldef get_weather(location: str) -> str: """Get the weather at a location.""" return "It's sunny."llm_with_tools = llm.bind_tools([get_weather])response = llm_with_tools.invoke("What's the weather in San Francisco?")print(response.tool_calls)print(f"\nTotal tokens: {response.usage_metadata['total_tokens']}")
Anthropic supports a citations feature that lets Claude attach context to its answers based on source documents supplied by the user. When document or search result content blocks with "citations": {"enabled": True} are included in a query, Claude may generate citations in its response.
In this example we pass a plain text document. In the background, Claude automatically chunks the input text into sentences, which are used when generating citations.
Copy
from langchain_anthropic import ChatAnthropicllm = ChatAnthropic(model="claude-3-5-haiku-latest")messages = [ { "role": "user", "content": [ { "type": "document", "source": { "type": "text", "media_type": "text/plain", "data": "The grass is green. The sky is blue.", }, "title": "My Document", "context": "This is a trustworthy document.", "citations": {"enabled": True}, }, {"type": "text", "text": "What color is the grass and sky?"}, ], }]response = llm.invoke(messages)response.content
Copy
[{'text': 'Based on the document, ', 'type': 'text'}, {'text': 'the grass is green', 'type': 'text', 'citations': [{'type': 'char_location', 'cited_text': 'The grass is green. ', 'document_index': 0, 'document_title': 'My Document', 'start_char_index': 0, 'end_char_index': 20}]}, {'text': ', and ', 'type': 'text'}, {'text': 'the sky is blue', 'type': 'text', 'citations': [{'type': 'char_location', 'cited_text': 'The sky is blue.', 'document_index': 0, 'document_title': 'My Document', 'start_char_index': 20, 'end_char_index': 36}]}, {'text': '.', 'type': 'text'}]
Claude supports a search_result content block representing citable results from queries against a knowledge base or other custom source. These content blocks can be passed to claude both top-line (as in the above example) and within a tool result. This allows Claude to cite elements of its response using the result of a tool call.To pass search results in response to tool calls, define a tool that returns a list of search_result content blocks in Anthropic’s native format. For example:
Copy
def retrieval_tool(query: str) -> list[dict]: """Access my knowledge base.""" # Run a search (e.g., with a LangChain vector store) results = vector_store.similarity_search(query=query, k=2) # Package results into search_result blocks return [ { "type": "search_result", # Customize fields as desired, using document metadata or otherwise "title": "My Document Title", "source": "Source description or provenance", "citations": {"enabled": True}, "content": [{"type": "text", "text": doc.page_content}], } for doc in results ]
End to end example with LangGraph
Here we demonstrate an end-to-end example in which we populate a LangChain vector store with sample documents and equip Claude with a tool that queries those documents.
The tool here takes a search query and a category string literal, but any valid tool signature can be used.
Copy
from typing import Literalfrom langchain.chat_models import init_chat_modelfrom langchain.embeddings import init_embeddingsfrom langchain_core.documents import Documentfrom langchain_core.vectorstores import InMemoryVectorStorefrom langgraph.checkpoint.memory import InMemorySaverfrom langchain.agents import create_agent# Set up vector storeembeddings = init_embeddings("openai:text-embedding-3-small")vector_store = InMemoryVectorStore(embeddings)document_1 = Document( id="1", page_content=( "To request vacation days, submit a leave request form through the " "HR portal. Approval will be sent by email." ), metadata={ "category": "HR Policy", "doc_title": "Leave Policy", "provenance": "Leave Policy - page 1", },)document_2 = Document( id="2", page_content="Managers will review vacation requests within 3 business days.", metadata={ "category": "HR Policy", "doc_title": "Leave Policy", "provenance": "Leave Policy - page 2", },)document_3 = Document( id="3", page_content=( "Employees with over 6 months tenure are eligible for 20 paid vacation days " "per year." ), metadata={ "category": "Benefits Policy", "doc_title": "Benefits Guide 2025", "provenance": "Benefits Policy - page 1", },)documents = [document_1, document_2, document_3]vector_store.add_documents(documents=documents)# Define toolasync def retrieval_tool( query: str, category: Literal["HR Policy", "Benefits Policy"]) -> list[dict]: """Access my knowledge base.""" def _filter_function(doc: Document) -> bool: return doc.metadata.get("category") == category results = vector_store.similarity_search( query=query, k=2, filter=_filter_function ) return [ { "type": "search_result", "title": doc.metadata["doc_title"], "source": doc.metadata["provenance"], "citations": {"enabled": True}, "content": [{"type": "text", "text": doc.page_content}], } for doc in results ]# Create agentllm = init_chat_model("anthropic:claude-3-5-haiku-latest")checkpointer = InMemorySaver()agent = create_agent(llm, [retrieval_tool], checkpointer=checkpointer)# Invoke on a queryconfig = {"configurable": {"thread_id": "session_1"}}input_message = { "role": "user", "content": "How do I request vacation days?",}async for step in agent.astream( {"messages": [input_message]}, config, stream_mode="values",): step["messages"][-1].pretty_print()
Anthropic also lets you specify your own splits using custom document types. LangChain text splitters can be used to generate meaningful splits for this purpose. See the below example, where we split the LangChain README (a markdown document) and pass it to Claude as context:
[{'text': "You can find LangChain's tutorials at https://python.langchain.com/docs/tutorials/\n\nThe tutorials section is recommended for those looking to build something specific or who prefer a hands-on learning approach. It's considered the best place to get started with LangChain.", 'type': 'text', 'citations': [{'type': 'content_block_location', 'cited_text': "[Tutorials](https://python.langchain.com/docs/tutorials/):If you're looking to build something specific orare more of a hands-on learner, check out ourtutorials. This is the best place to get started.", 'document_index': 0, 'document_title': None, 'start_block_index': 243, 'end_block_index': 248}]}]
Anthropic supports a variety of built-in tools, which can be bound to the model in the usual way. Claude will generate tool calls adhering to its internal schema for the tool:
Claude can use a web search tool to run searches and ground its responses with citations.
Web search tool is supported since langchain-anthropic>=0.3.13
Copy
from langchain_anthropic import ChatAnthropicllm = ChatAnthropic(model="claude-3-5-sonnet-latest")tool = {"type": "web_search_20250305", "name": "web_search", "max_uses": 3}llm_with_tools = llm.bind_tools([tool])response = llm_with_tools.invoke("How do I update a web app to TypeScript 5.5?")
Claude can use a code execution tool to execute Python code in a sandboxed environment.
Code execution is supported since langchain-anthropic>=0.3.14
Copy
from langchain_anthropic import ChatAnthropicllm = 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])response = llm_with_tools.invoke( "Calculate the mean and standard deviation of [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]")
Use with Files API
Using the Files API, Claude can write code to access files for data analysis and other purposes. See example below:
Copy
# Upload fileimport anthropicclient = anthropic.Anthropic()file = client.beta.files.upload( file=open("/path/to/sample_data.csv", "rb"))file_id = file.id# Run inferencefrom langchain_anthropic import ChatAnthropicllm = 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])input_message = { "role": "user", "content": [ { "type": "text", "text": "Please plot these data and tell me what you see.", }, { "type": "container_upload", "file_id": file_id, }, ]}llm_with_tools.invoke([input_message])
Note that Claude may generate files as part of its code execution. You can access these files using the Files API:
Copy
# Take all file outputs for demonstration purposesfile_ids = []for block in response.content: if block["type"] == "code_execution_tool_result": file_ids.extend( content["file_id"] for content in block.get("content", {}).get("content", []) if "file_id" in content )for i, file_id in enumerate(file_ids): file_content = client.beta.files.download(file_id) file_content.write_to_file(f"/path/to/file_{i}.png")
The text editor tool can be used to view and modify text files. See docs here for details.
Copy
from langchain_anthropic import ChatAnthropicllm = ChatAnthropic(model="claude-3-7-sonnet-20250219")tool = {"type": "text_editor_20250124", "name": "str_replace_editor"}llm_with_tools = llm.bind_tools([tool])response = llm_with_tools.invoke( "There's a syntax error in my primes.py file. Can you help me fix it?")print(response.text)response.tool_calls
Copy
I'd be happy to help you fix the syntax error in your primes.py file. First, let's look at the current content of the file to identify the error.
