LangChain

ChatOpenAI with a custom base URL.

Uses the OpenAI Chat Completions API. LangChain docs

Public

Install langchain-openai, then give ChatOpenAI Pollio's base URL and your key.

Fig. I, hello.py

# pip install -U langchain-openai
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="deepseek/deepseek-v4.1-flash",
    base_url="https://api.pollio.ai/v1",
    api_key="pl-live-...",
    use_responses_api=False,
)
print(llm.invoke("Hello").content)

Private

Start pollio proxy on your machine, then point LangChain at it instead.

Fig. II, hello.py

# pip install -U langchain-openai
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="deepseek/deepseek-v4.1-flash",
    base_url="http://127.0.0.1:8787/v1",
    api_key="pl-live-...",
    use_responses_api=False,
)
print(llm.invoke("Hello").content)

use_responses_api=False keeps LangChain on Chat Completions; some features would otherwise switch it to the Responses API.

Names and logos belong to their owners. No endorsement implied.