Models - Docs by LangChain (original) (raw)

LLMs are powerful AI tools that can interpret and generate text like humans. They’re versatile enough to write content, translate languages, summarize, and answer questions without needing specialized training for each task. In addition to text generation, many models support:

Models are the reasoning engine of agents. They drive the agent’s decision-making process, determining which tools to call, how to interpret results, and when to provide a final answer. The quality and capabilities of the model you choose directly impact your agent’s baseline reliability and performance. Different models excel at different tasks - some are better at following complex instructions, others at structured reasoning, and some support larger context windows for handling more information. LangChain’s standard model interfaces give you access to many different provider integrations, which makes it easy to experiment with and switch between models to find the best fit for your use case.

Basic usage

Models can be utilized in two ways:

  1. With agents - Models can be dynamically specified when creating an agent.
  2. Standalone - Models can be called directly (outside of the agent loop) for tasks like text generation, classification, or extraction without the need for an agent framework.

The same model interface works in both contexts, which gives you the flexibility to start simple and scale up to more complex agent-based workflows as needed.

Initialize a model

The easiest way to get started with a standalone model in LangChain is to use init_chat_model to initialize one from a chat model provider of your choice (examples below):

response = model.invoke("Why do parrots talk?")

See init_chat_model for more detail, including information on how to pass model parameters.

Key methods

InvokeThe model takes messages as input and outputs messages after generating a complete response. StreamInvoke the model, but stream the output as it is generated in real-time. BatchSend multiple requests to a model in a batch for more efficient processing.

Parameters

A chat model takes parameters that can be used to configure its behavior. The full set of supported parameters varies by model and provider, but standard ones include:

The name or identifier of the specific model you want to use with a provider. You can also specify both the model and its provider in a single argument using the ’:’ format, for example, ‘openai:o1’.

The key required for authenticating with the model’s provider. This is usually issued when you sign up for access to the model. Often accessed by setting an .

Controls the randomness of the model’s output. A higher number makes responses more creative; lower ones make them more deterministic.

Limits the total number of in the response, effectively controlling how long the output can be.

The maximum time (in seconds) to wait for a response from the model before canceling the request.

The maximum number of attempts the system will make to resend a request if it fails due to issues like network timeouts or rate limits.

Using init_chat_model, pass these parameters as inline :

Initialize using model parameters

model = init_chat_model(
    "claude-sonnet-4-5-20250929",
    # Kwargs passed to the model:
    temperature=0.7,
    timeout=30,
    max_tokens=1000,
)

Invocation

A chat model must be invoked to generate an output. There are three primary invocation methods, each suited to different use cases.

Invoke

The most straightforward way to call a model is to use invoke() with a single message or a list of messages.

response = model.invoke("Why do parrots have colorful feathers?")
print(response)

A list of messages can be provided to a chat model to represent conversation history. Each message has a role that models use to indicate who sent the message in the conversation. See the messages guide for more detail on roles, types, and content.

conversation = [
    {"role": "system", "content": "You are a helpful assistant that translates English to French."},
    {"role": "user", "content": "Translate: I love programming."},
    {"role": "assistant", "content": "J'adore la programmation."},
    {"role": "user", "content": "Translate: I love building applications."}
]

response = model.invoke(conversation)
print(response)  # AIMessage("J'adore créer des applications.")

from langchain.messages import HumanMessage, AIMessage, SystemMessage

conversation = [
    SystemMessage("You are a helpful assistant that translates English to French."),
    HumanMessage("Translate: I love programming."),
    AIMessage("J'adore la programmation."),
    HumanMessage("Translate: I love building applications.")
]

response = model.invoke(conversation)
print(response)  # AIMessage("J'adore créer des applications.")

Stream

Most models can stream their output content while it is being generated. By displaying output progressively, streaming significantly improves user experience, particularly for longer responses. Calling stream() returns an that yields output chunks as they are produced. You can use a loop to process each chunk in real-time:

As opposed to invoke(), which returns a single AIMessage after the model has finished generating its full response, stream() returns multiple AIMessageChunk objects, each containing a portion of the output text. Importantly, each chunk in a stream is designed to be gathered into a full message via summation:

full = None  # None | AIMessageChunk
for chunk in model.stream("What color is the sky?"):
    full = chunk if full is None else full + chunk
    print(full.text)

# The
# The sky
# The sky is
# The sky is typically
# The sky is typically blue
# ...

print(full.content_blocks)
# [{"type": "text", "text": "The sky is typically blue..."}]

The resulting message can be treated the same as a message that was generated with invoke() – for example, it can be aggregated into a message history and passed back to the model as conversational context.

Advanced streaming topics

Streaming events

LangChain chat models can also stream semantic events using astream_events().This simplifies filtering based on event types and other metadata, and will aggregate the full message in the background. See below for an example.

async for event in model.astream_events("Hello"):

    if event["event"] == "on_chat_model_start":
        print(f"Input: {event['data']['input']}")

    elif event["event"] == "on_chat_model_stream":
        print(f"Token: {event['data']['chunk'].text}")

    elif event["event"] == "on_chat_model_end":
        print(f"Full message: {event['data']['output'].text}")

    else:
        pass

Input: Hello
Token: Hi
Token:  there
Token: !
Token:  How
Token:  can
Token:  I
...
Full message: Hi there! How can I help today?

"Auto-streaming" chat models

LangChain simplifies streaming from chat models by automatically enabling streaming mode in certain cases, even when you’re not explicitly calling the streaming methods. This is particularly useful when you use the non-streaming invoke method but still want to stream the entire application, including intermediate results from the chat model.In LangGraph agents, for example, you can call model.invoke() within nodes, but LangChain will automatically delegate to streaming if running in a streaming mode.

How it works

When you invoke() a chat model, LangChain will automatically switch to an internal streaming mode if it detects that you are trying to stream the overall application. The result of the invocation will be the same as far as the code that was using invoke is concerned; however, while the chat model is being streamed, LangChain will take care of invoking on_llm_new_token events in LangChain’s callback system.Callback events allow LangGraph stream() and astream_events() to surface the chat model’s output in real-time.

Batch

Batching a collection of independent requests to a model can significantly improve performance and reduce costs, as the processing can be done in parallel:

responses = model.batch([
    "Why do parrots have colorful feathers?",
    "How do airplanes fly?",
    "What is quantum computing?"
])
for response in responses:
    print(response)

By default, batch() will only return the final output for the entire batch. If you want to receive the output for each individual input as it finishes generating, you can stream results with batch_as_completed():

Yield batch responses upon completion

for response in model.batch_as_completed([
    "Why do parrots have colorful feathers?",
    "How do airplanes fly?",
    "What is quantum computing?"
]):
    print(response)

For more details on batching, see the reference.

Models can request to call tools that perform tasks such as fetching data from a database, searching the web, or running code. Tools are pairings of:

  1. A schema, including the name of the tool, a description, and/or argument definitions (often a JSON schema)
  2. A function or to execute.

Here’s the basic tool calling flow between a user and a model:

To make tools that you have defined available for use by a model, you must bind them using bind_tools. In subsequent invocations, the model can choose to call any of the bound tools as needed. Some model providers offer that can be enabled via model or invocation parameters (e.g. ChatOpenAI, ChatAnthropic). Check the respective provider reference for details.

from langchain.tools import tool

@tool
def get_weather(location: str) -> str:
    """Get the weather at a location."""
    return f"It's sunny in {location}."


model_with_tools = model.bind_tools([get_weather])  

response = model_with_tools.invoke("What's the weather like in Boston?")
for tool_call in response.tool_calls:
    # View tool calls made by the model
    print(f"Tool: {tool_call['name']}")
    print(f"Args: {tool_call['args']}")

When binding user-defined tools, the model’s response includes a request to execute a tool. When using a model separately from an agent, it is up to you to execute the requested tool and return the result back to the model for use in subsequent reasoning. When using an agent, the agent loop will handle the tool execution loop for you. Below, we show some common ways you can use tool calling.

Structured output

Models can be requested to provide their response in a format matching a given schema. This is useful for ensuring the output can be easily parsed and used in subsequent processing. LangChain supports multiple schema types and methods for enforcing structured output.

Pydantic models provide the richest feature set with field validation, descriptions, and nested structures.

from pydantic import BaseModel, Field

class Movie(BaseModel):
    """A movie with details."""
    title: str = Field(..., description="The title of the movie")
    year: int = Field(..., description="The year the movie was released")
    director: str = Field(..., description="The director of the movie")
    rating: float = Field(..., description="The movie's rating out of 10")

model_with_structure = model.with_structured_output(Movie)
response = model_with_structure.invoke("Provide details about the movie Inception")
print(response)  # Movie(title="Inception", year=2010, director="Christopher Nolan", rating=8.8)

TypedDict provides a simpler alternative using Python’s built-in typing, ideal when you don’t need runtime validation.

from typing_extensions import TypedDict, Annotated

class MovieDict(TypedDict):
    """A movie with details."""
    title: Annotated[str, ..., "The title of the movie"]
    year: Annotated[int, ..., "The year the movie was released"]
    director: Annotated[str, ..., "The director of the movie"]
    rating: Annotated[float, ..., "The movie's rating out of 10"]

model_with_structure = model.with_structured_output(MovieDict)
response = model_with_structure.invoke("Provide details about the movie Inception")
print(response)  # {'title': 'Inception', 'year': 2010, 'director': 'Christopher Nolan', 'rating': 8.8}

For maximum control or interoperability, you can provide a raw JSON Schema.

import json

json_schema = {
    "title": "Movie",
    "description": "A movie with details",
    "type": "object",
    "properties": {
        "title": {
            "type": "string",
            "description": "The title of the movie"
        },
        "year": {
            "type": "integer",
            "description": "The year the movie was released"
        },
        "director": {
            "type": "string",
            "description": "The director of the movie"
        },
        "rating": {
            "type": "number",
            "description": "The movie's rating out of 10"
        }
    },
    "required": ["title", "year", "director", "rating"]
}

model_with_structure = model.with_structured_output(
    json_schema,
    method="json_schema",
)
response = model_with_structure.invoke("Provide details about the movie Inception")
print(response)  # {'title': 'Inception', 'year': 2010, ...}

Example: Message output alongside parsed structure

It can be useful to return the raw AIMessage object alongside the parsed representation to access response metadata such as token counts. To do this, set include_raw=True when calling with_structured_output:

from pydantic import BaseModel, Field

class Movie(BaseModel):
    """A movie with details."""
    title: str = Field(..., description="The title of the movie")
    year: int = Field(..., description="The year the movie was released")
    director: str = Field(..., description="The director of the movie")
    rating: float = Field(..., description="The movie's rating out of 10")

model_with_structure = model.with_structured_output(Movie, include_raw=True)  
response = model_with_structure.invoke("Provide details about the movie Inception")
response
# {
#     "raw": AIMessage(...),
#     "parsed": Movie(title=..., year=..., ...),
#     "parsing_error": None,
# }

Example: Nested structures

Supported models

LangChain supports all major model providers, including OpenAI, Anthropic, Google, Azure, AWS Bedrock, and more. Each provider offers a variety of models with different capabilities. For a full list of supported models in LangChain, see the integrations page.

Advanced topics

Model profiles

LangChain chat models can expose a dictionary of supported features and capabilities through a .profile attribute:

model.profile
# {
#   "max_input_tokens": 400000,
#   "image_inputs": True,
#   "reasoning_output": True,
#   "tool_calling": True,
#   ...
# }

Refer to the full set of fields in the API reference. Much of the model profile data is powered by the models.dev project, an open source initiative that provides model capability data. These data are augmented with additional fields for purposes of use with LangChain. These augmentations are kept aligned with the upstream project as it evolves. Model profile data allow applications to work around model capabilities dynamically. For example:

  1. Summarization middleware can trigger summarization based on a model’s context window size.
  2. Structured output strategies in create_agent can be inferred automatically (e.g., by checking support for native structured output features).
  3. Model inputs can be gated based on supported modalities and maximum input tokens.

Updating or overwriting profile data

Model profile data can be changed if it is missing, stale, or incorrect.**Option 1 (quick fix)**You can instantiate a chat model with any valid profile:

custom_profile = {
    "max_input_tokens": 100_000,
    "tool_calling": True,
    "structured_output": True,
    # ...
}
model = init_chat_model("...", profile=custom_profile)

The profile is also a regular dict and can be updated in place. If the model instance is shared, consider using model_copy to avoid mutating shared state.

new_profile = model.profile | {"key": "value"}
model.model_copy(update={"profile": new_profile})

**Option 2 (fix data upstream)**The primary source for the data is the models.dev project. This data is merged with additional fields and overrides in LangChain integration packages and are shipped with those packages.Model profile data can be updated through the following process:

  1. (If needed) update the source data at models.dev through a pull request to its repository on GitHub.
  2. (If needed) update additional fields and overrides in langchain_<package>/data/profile_augmentations.toml through a pull request to the LangChain integration package`.
  3. Use the langchain-model-profiles CLI tool to pull the latest data from models.dev, merge in the augmentations and update the profile data:
pip install langchain-model-profiles

langchain-profiles refresh --provider <provider> --data-dir <data_dir>

This command:

For example: from libs/partners/anthropic in the LangChain monorepo:

uv run --with langchain-model-profiles --provider anthropic --data-dir langchain_anthropic/data

Multimodal

Certain models can process and return non-textual data such as images, audio, and video. You can pass non-textual data to a model by providing content blocks.

See the multimodal section of the messages guide for details. can return multimodal data as part of their response. If invoked to do so, the resulting AIMessage will have content blocks with multimodal types.

response = model.invoke("Create a picture of a cat")
print(response.content_blocks)
# [
#     {"type": "text", "text": "Here's a picture of a cat"},
#     {"type": "image", "base64": "...", "mime_type": "image/jpeg"},
# ]

See the integrations page for details on specific providers.

Reasoning

Many models are capable of performing multi-step reasoning to arrive at a conclusion. This involves breaking down complex problems into smaller, more manageable steps. If supported by the underlying model, you can surface this reasoning process to better understand how the model arrived at its final answer.

Depending on the model, you can sometimes specify the level of effort it should put into reasoning. Similarly, you can request that the model turn off reasoning entirely. This may take the form of categorical “tiers” of reasoning (e.g., 'low' or 'high') or integer token budgets. For details, see the integrations page or reference for your respective chat model.

Local models

LangChain supports running models locally on your own hardware. This is useful for scenarios where either data privacy is critical, you want to invoke a custom model, or when you want to avoid the costs incurred when using a cloud-based model. Ollama is one of the easiest ways to run models locally. See the full list of local integrations on the integrations page.

Prompt caching

Many providers offer prompt caching features to reduce latency and cost on repeat processing of the same tokens. These features can be implicit or explicit:

Cache usage will be reflected in the usage metadata of the model response.

Server-side tool use

Some providers support server-side tool-calling loops: models can interact with web search, code interpreters, and other tools and analyze the results in a single conversational turn. If a model invokes a tool server-side, the content of the response message will include content representing the invocation and result of the tool. Accessing the content blocks of the response will return the server-side tool calls and results in a provider-agnostic format:

Invoke with server-side tool use

from langchain.chat_models import init_chat_model

model = init_chat_model("gpt-4.1-mini")

tool = {"type": "web_search"}
model_with_tools = model.bind_tools([tool])

response = model_with_tools.invoke("What was a positive news story from today?")
response.content_blocks

[
    {
        "type": "server_tool_call",
        "name": "web_search",
        "args": {
            "query": "positive news stories today",
            "type": "search"
        },
        "id": "ws_abc123"
    },
    {
        "type": "server_tool_result",
        "tool_call_id": "ws_abc123",
        "status": "success"
    },
    {
        "type": "text",
        "text": "Here are some positive news stories from today...",
        "annotations": [
            {
                "end_index": 410,
                "start_index": 337,
                "title": "article title",
                "type": "citation",
                "url": "..."
            }
        ]
    }
]

This represents a single conversational turn; there are no associated ToolMessage objects that need to be passed in as in client-side tool-calling. See the integration page for your given provider for available tools and usage details.

Rate limiting

Many chat model providers impose a limit on the number of invocations that can be made in a given time period. If you hit a rate limit, you will typically receive a rate limit error response from the provider, and will need to wait before making more requests. To help manage rate limits, chat model integrations accept a rate_limiter parameter that can be provided during initialization to control the rate at which requests are made.

Initialize and use a rate limiter

LangChain in comes with (an optional) built-in InMemoryRateLimiter. This limiter is thread safe and can be shared by multiple threads in the same process.

from langchain_core.rate_limiters import InMemoryRateLimiter

rate_limiter = InMemoryRateLimiter(
    requests_per_second=0.1,  # 1 request every 10s
    check_every_n_seconds=0.1,  # Check every 100ms whether allowed to make a request
    max_bucket_size=10,  # Controls the maximum burst size.
)

model = init_chat_model(
    model="gpt-5",
    model_provider="openai",
    rate_limiter=rate_limiter  
)

Base URL or proxy

For many chat model integrations, you can configure the base URL for API requests, which allows you to use model providers that have OpenAI-compatible APIs or to use a proxy server.

Base URL

Many model providers offer OpenAI-compatible APIs (e.g., Together AI, vLLM). You can use init_chat_model with these providers by specifying the appropriate base_url parameter:

model = init_chat_model(
    model="MODEL_NAME",
    model_provider="openai",
    base_url="BASE_URL",
    api_key="YOUR_API_KEY",
)

Proxy configuration

For deployments requiring HTTP proxies, some model integrations support proxy configuration:

from langchain_openai import ChatOpenAI

model = ChatOpenAI(
    model="gpt-4o",
    openai_proxy="http://proxy.example.com:8080"
)

Log probabilities

Certain models can be configured to return token-level log probabilities representing the likelihood of a given token by setting the logprobs parameter when initializing the model:

model = init_chat_model(
    model="gpt-4o",
    model_provider="openai"
).bind(logprobs=True)

response = model.invoke("Why do parrots talk?")
print(response.response_metadata["logprobs"])

Token usage

A number of model providers return token usage information as part of the invocation response. When available, this information will be included on the AIMessage objects produced by the corresponding model. For more details, see the messages guide.

You can track aggregate token counts across models in an application using either a callback or context manager, as shown below:

from langchain.chat_models import init_chat_model
from langchain_core.callbacks import UsageMetadataCallbackHandler

model_1 = init_chat_model(model="gpt-4o-mini")
model_2 = init_chat_model(model="claude-haiku-4-5-20251001")

callback = UsageMetadataCallbackHandler()
result_1 = model_1.invoke("Hello", config={"callbacks": [callback]})
result_2 = model_2.invoke("Hello", config={"callbacks": [callback]})
callback.usage_metadata

{
    'gpt-4o-mini-2024-07-18': {
        'input_tokens': 8,
        'output_tokens': 10,
        'total_tokens': 18,
        'input_token_details': {'audio': 0, 'cache_read': 0},
        'output_token_details': {'audio': 0, 'reasoning': 0}
    },
    'claude-haiku-4-5-20251001': {
        'input_tokens': 8,
        'output_tokens': 21,
        'total_tokens': 29,
        'input_token_details': {'cache_read': 0, 'cache_creation': 0}
    }
}

from langchain.chat_models import init_chat_model
from langchain_core.callbacks import get_usage_metadata_callback

model_1 = init_chat_model(model="gpt-4o-mini")
model_2 = init_chat_model(model="claude-haiku-4-5-20251001")

with get_usage_metadata_callback() as cb:
    model_1.invoke("Hello")
    model_2.invoke("Hello")
    print(cb.usage_metadata)

{
    'gpt-4o-mini-2024-07-18': {
        'input_tokens': 8,
        'output_tokens': 10,
        'total_tokens': 18,
        'input_token_details': {'audio': 0, 'cache_read': 0},
        'output_token_details': {'audio': 0, 'reasoning': 0}
    },
    'claude-haiku-4-5-20251001': {
        'input_tokens': 8,
        'output_tokens': 21,
        'total_tokens': 29,
        'input_token_details': {'cache_read': 0, 'cache_creation': 0}
    }
}

Invocation config

When invoking a model, you can pass additional configuration through the config parameter using a RunnableConfig dictionary. This provides run-time control over execution behavior, callbacks, and metadata tracking. Common configuration options include:

response = model.invoke(
    "Tell me a joke",
    config={
        "run_name": "joke_generation",      # Custom name for this run
        "tags": ["humor", "demo"],          # Tags for categorization
        "metadata": {"user_id": "123"},     # Custom metadata
        "callbacks": [my_callback_handler], # Callback handlers
    }
)

These configuration values are particularly useful when:

Key configuration attributes

Identifies this specific invocation in logs and traces. Not inherited by sub-calls.

Labels inherited by all sub-calls for filtering and organization in debugging tools.

Custom key-value pairs for tracking additional context, inherited by all sub-calls.

Handlers for monitoring and responding to events during execution.

Maximum recursion depth for chains to prevent infinite loops in complex pipelines.

Configurable models

You can also create a runtime-configurable model by specifying configurable_fields. If you don’t specify a model value, then 'model' and 'model_provider' will be configurable by default.

from langchain.chat_models import init_chat_model

configurable_model = init_chat_model(temperature=0)

configurable_model.invoke(
    "what's your name",
    config={"configurable": {"model": "gpt-5-nano"}},  # Run with GPT-5-Nano
)
configurable_model.invoke(
    "what's your name",
    config={"configurable": {"model": "claude-sonnet-4-5-20250929"}},  # Run with Claude
)

Configurable model with default values

We can create a configurable model with default model values, specify which parameters are configurable, and add prefixes to configurable params:

first_model = init_chat_model(
        model="gpt-4.1-mini",
        temperature=0,
        configurable_fields=("model", "model_provider", "temperature", "max_tokens"),
        config_prefix="first",  # Useful when you have a chain with multiple models
)

first_model.invoke("what's your name")

first_model.invoke(
    "what's your name",
    config={
        "configurable": {
            "first_model": "claude-sonnet-4-5-20250929",
            "first_temperature": 0.5,
            "first_max_tokens": 100,
        }
    },
)

See the init_chat_model reference for more details on configurable_fields and config_prefix.

Using a configurable model declaratively

We can call declarative operations like bind_tools, with_structured_output, with_configurable, etc. on a configurable model and chain a configurable model in the same way that we would a regularly instantiated chat model object.

from pydantic import BaseModel, Field


class GetWeather(BaseModel):
    """Get the current weather in a given location"""

        location: str = Field(..., description="The city and state, e.g. San Francisco, CA")


class GetPopulation(BaseModel):
    """Get the current population in a given location"""

        location: str = Field(..., description="The city and state, e.g. San Francisco, CA")


model = init_chat_model(temperature=0)
model_with_tools = model.bind_tools([GetWeather, GetPopulation])

model_with_tools.invoke(
    "what's bigger in 2024 LA or NYC", config={"configurable": {"model": "gpt-4.1-mini"}}
).tool_calls

[
    {
        'name': 'GetPopulation',
        'args': {'location': 'Los Angeles, CA'},
        'id': 'call_Ga9m8FAArIyEjItHmztPYA22',
        'type': 'tool_call'
    },
    {
        'name': 'GetPopulation',
        'args': {'location': 'New York, NY'},
        'id': 'call_jh2dEvBaAHRaw5JUDthOs7rt',
        'type': 'tool_call'
    }
]

model_with_tools.invoke(
    "what's bigger in 2024 LA or NYC",
    config={"configurable": {"model": "claude-sonnet-4-5-20250929"}},
).tool_calls

[
    {
        'name': 'GetPopulation',
        'args': {'location': 'Los Angeles, CA'},
        'id': 'toolu_01JMufPf4F4t2zLj7miFeqXp',
        'type': 'tool_call'
    },
    {
        'name': 'GetPopulation',
        'args': {'location': 'New York City, NY'},
        'id': 'toolu_01RQBHcE8kEEbYTuuS8WqY1u',
        'type': 'tool_call'
    }
]