Skip to main content
This integration connects OpenAI’s chat models to LangChain.

​
Installation

pip install -U langchain-openai

​
Setup

Set your OpenAI API key as an environment variable: 
export OPENAI_API_KEY="your-api-key"

​
Usage

from langchain_openai import ChatOpenAI

model = ChatOpenAI(
    model="gpt-4o",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
)

messages = [
    ("system", "You are a helpful assistant."),
    ("human", "What is the capital of France?"),
]

response = model.invoke(messages)
print(response.content)

​
Streaming

for chunk in model.stream(messages):
    print(chunk.content, end="")

​
API Reference

​
ChatOpenAI

​
model
str
required
Name of OpenAI model to use (e.g., gpt-4o, gpt-4o-mini, o1, o3-mini).
​
temperature
float
default:"1"
Sampling temperature between 0 and 2. Higher values make output more random, lower values more deterministic.
​
max_tokens
int | None
default:"None"
Maximum number of tokens to generate.
​
logprobs
bool | None
default:"None"
Whether to return log probabilities of output tokens.
​
stream_options
dict
default:"None"
Configure streaming outputs, like whether to return token usage when streaming (e.g., {"include_usage": True}).
​
use_responses_api
bool | None
default:"None"
Whether to use the responses API.
​
timeout
float | tuple[float, float] | None
default:"None"
Timeout for requests in seconds.
​
max_retries
int
default:"2"
Maximum number of retries for failed requests.
​
api_key
str | None
default:"None"
OpenAI API key. If not provided, reads from OPENAI_API_KEY environment variable.
​
base_url
str | None
default:"None"
Base URL for API requests. Only specify if using a proxy or service emulator.
​
organization
str | None
default:"None"
OpenAI organization ID. If not provided, reads from OPENAI_ORG_ID environment variable.

​
Supported Models

  • GPT-4o series: gpt-4o, gpt-4o-mini - Latest multimodal models
  • o-series: o1, o1-mini, o3-mini - Reasoning models with advanced problem-solving
  • GPT-4 Turbo: gpt-4-turbo, gpt-4-turbo-preview - High-intelligence models
  • GPT-3.5 Turbo: gpt-3.5-turbo - Fast, cost-effective model

​
Features

  • Text generation
  • Function/tool calling
  • Vision (multimodal input with GPT-4o)
  • JSON mode
  • Streaming
  • Async support
  • Token usage tracking
  • Prompt caching
ChatOpenAI targets official OpenAI API specifications only. Non-standard response fields added by third-party providers are not extracted. If using a provider like OpenRouter or vLLM, use the corresponding provider-specific package instead.

Build docs developers (and LLMs) love

Get started for freeTalk to us