ChatLiteLLM and ChatLiteLLMRouter integration

## Set ENV variables
import os

os.environ["OPENAI_API_KEY"] = "your-openai-key"
os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-key"

pip install -qU langchain-litellm

from langchain_litellm import ChatLiteLLM

llm = ChatLiteLLM(model="gpt-5.4-nano", temperature=0.1)

from langchain_litellm import ChatLiteLLMRouter
from litellm import Router

model_list = [
    {
        "model_name": "gpt-5.5",
        "litellm_params": {
            "model": "azure/gpt-5.5",
            "api_key": "<your-api-key>",
            "api_version": "2024-10-21",
            "api_base": "https://<your-endpoint>.openai.azure.com/",
        },
    },
    {
        "model_name": "gpt-5.5",
        "litellm_params": {
            "model": "azure/gpt-5.5",
            "api_key": "<your-api-key>",
            "api_version": "2024-10-21",
            "api_base": "https://<your-endpoint>.openai.azure.com/",
        },
    },
]
litellm_router = Router(model_list=model_list)
llm = ChatLiteLLMRouter(router=litellm_router, model_name="gpt-5.5", temperature=0.1)

response = await llm.ainvoke(
    "Classify the text into neutral, negative or positive. Text: I think the food was okay. Sentiment:"
)
print(response)

content='Neutral' additional_kwargs={} response_metadata={'token_usage': Usage(completion_tokens=2, prompt_tokens=30, total_tokens=32, completion_tokens_details=CompletionTokensDetailsWrapper(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0, text_tokens=None), prompt_tokens_details=PromptTokensDetailsWrapper(audio_tokens=0, cached_tokens=0, text_tokens=None, image_tokens=None)), 'model': 'gpt-3.5-turbo', 'finish_reason': 'stop', 'model_name': 'gpt-3.5-turbo'} id='run-ab6a3b21-eae8-4c27-acb2-add65a38221a-0' usage_metadata={'input_tokens': 30, 'output_tokens': 2, 'total_tokens': 32}

stream = await llm.astream_events("Hello, please explain how antibiotics work", version="v3")
async for token in stream.text:
    print(token, end="")

Antibiotics are medications that fight bacterial infections in the body. They work by targeting specific bacteria and either killing them or preventing their growth and reproduction.

There are several different mechanisms by which antibiotics work. Some antibiotics work by disrupting the cell walls of bacteria, causing them to burst and die. Others interfere with the protein synthesis of bacteria, preventing them from growing and reproducing. Some antibiotics target the DNA or RNA of bacteria, disrupting their ability to replicate.

It is important to note that antibiotics only work against bacterial infections and not viral infections. It is also crucial to take antibiotics as prescribed by a healthcare professional and to complete the full course of treatment, even if symptoms improve before the medication is finished. This helps to prevent antibiotic resistance, where bacteria become resistant to the effects of antibiotics.

import os
from langchain_litellm import ChatLiteLLM

os.environ["VERTEXAI_PROJECT"] = "your-project-id"
os.environ["VERTEXAI_LOCATION"] = "us-central1"

llm = ChatLiteLLM(model="vertex_ai/gemini-2.5-flash", temperature=0)

# Invoke with Google Search tool enabled
response = llm.invoke(
    "What is the current stock price of Google?",
    tools=[{"googleSearch": {}}]
)

# Access citations & metadata
provider_fields = response.response_metadata.get("provider_specific_fields")
if provider_fields:
    # Vertex returns a list; the first item contains the grounding info
    print(provider_fields[0])

stream = llm.stream_events(
    "What is the current stock price of Google?",
    version="v3",
    tools=[{"googleSearch": {}}],
)
for token in stream.text:
    print(token, end="", flush=True)
# Metadata is available on the full output message
output = stream.output
if "provider_specific_fields" in output.response_metadata:
    print("\n[Metadata Found]:", output.response_metadata["provider_specific_fields"])

from langchain_litellm import ChatLiteLLM

llm = ChatLiteLLM(model="openai/gpt-6-astra", use_responses_api=True)
llm_with_tools = llm.bind_tools([{"type": "web_search"}])

response = llm_with_tools.invoke("What was a positive news story from today?")
print(response.text)

from langchain.messages import HumanMessage
from langchain.tools import tool
from langchain_litellm import ChatLiteLLM


@tool
def get_weather(city: str) -> str:
    """Get the weather for a city."""
    return f"It is sunny in {city}."


llm = ChatLiteLLM(
    model="openai/gpt-6-astra",
    use_responses_api=True,
    model_kwargs={
        "extra_body": {"store": False, "include": ["reasoning.encrypted_content"]}
    },
)
llm_with_tools = llm.bind_tools([get_weather])

messages = [
    HumanMessage(
        "Get the weather for the city that hosted the Summer Olympics four years "
        "before London did."
    )
]
ai_message = llm_with_tools.invoke(messages)
reasoning_items = ai_message.additional_kwargs.get("reasoning_items", [])
print([item["id"] for item in reasoning_items])

messages.append(ai_message)
messages.extend(get_weather.invoke(call) for call in ai_message.tool_calls)
response = llm_with_tools.invoke(messages)
print(response.text)

from langchain_litellm import ChatLiteLLMRouter
from litellm import Router

model_list = [
    {
        "model_name": "gpt-6-astra",
        "litellm_params": {"model": "openai/responses/gpt-6-astra"},
    },
]
litellm_router = Router(model_list=model_list)
llm = ChatLiteLLMRouter(router=litellm_router, model_name="gpt-6-astra")
llm_with_tools = llm.bind_tools([{"type": "web_search"}])

response = llm_with_tools.invoke("What was a positive news story from today?")
print(response.text)