UberLLM

LangChain

LangChain's ChatOpenAI (from langchain-openai) points at UberLLM with a base_url and api_key. Everything else — chains, agents, tools, streaming — works unchanged.

Install

pip install langchain langchain-openai

Python

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="deepseek/deepseek-v3.1",
    base_url="https://api.uberllm.dev/v1",
    api_key=os.environ["UBERLLM_API_KEY"],
)

print(llm.invoke("Say hello in one sentence.").content)

base_url takes precedence over the OPENAI_API_BASE / OPENAI_BASE_URL environment variables, so an explicit kwarg is the most reliable.

Streaming

for chunk in llm.stream("Count to five."):
    print(chunk.content, end="", flush=True)

Tools / agents

Because ChatOpenAI talks the OpenAI tool-calling format, bind_tools and the agent executors work as-is against any tool-capable UberLLM model:

from langchain_core.tools import tool

@tool
def get_weather(city: str) -> str:
    "Return the weather for a city."
    return f"Sunny in {city}."

agent_llm = llm.bind_tools([get_weather])
print(agent_llm.invoke("What's the weather in Paris?").tool_calls)

JavaScript / TypeScript

import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  model: "deepseek/deepseek-v3.1",
  apiKey: process.env.UBERLLM_API_KEY,
  configuration: { baseURL: "https://api.uberllm.dev/v1" },
});

const res = await llm.invoke("Say hello in one sentence.");
console.log(res.content);

Notes

  • Append :floor or :nitro to the model id for cheapest / fastest routing (Models & routing).
  • No inference markup; you pay the provider's token price (Pricing).