LangChain

One /v1 endpoint for every provider. Point your OpenAI client at a new base URL and key, bring your own provider keys, and pay 0% markup on tokens.

LangChain’s OpenAI chat model takes a base URL, so every model in the catalogue works with it.

Python

bash
pip install langchain-openai
python
import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="anthropic/claude-sonnet-5",
    api_key=os.environ["AUTONOMOUSRELAY_API_KEY"],
    base_url="https://autonomousrelay.com/v1",
)
print(llm.invoke("Say hello in one word.").content)

JavaScript

bash
npm install @langchain/openai
typescript
import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  model: "openai/gpt-5.5",
  apiKey: process.env.AUTONOMOUSRELAY_API_KEY,
  configuration: { baseURL: "https://autonomousrelay.com/v1" },
});
console.log((await llm.invoke("Say hello in one word.")).content);
  • Tool calling, structured output and streaming work as with OpenAI. Token usage arrives at the end of a stream; in Python, pass stream_usage=True to see it.
  • LangChain’s OpenAI class drops non-standard response fields, so a model’s separate reasoning text is not returned through it.