DEVSAIO

LangChain.js with a custom OpenAI-compatible endpoint

Configure ChatOpenAI in LangChain.js to use DEVSAIO, with streaming and a simple prompt template.

DEVSAIO team · 1 min read
Share on X

In LangChain.js, the base URL goes inside the configuration object.

Install

bash
npm install @langchain/openai @langchain/core

Usage

ts
import { ChatOpenAI } from "@langchain/openai";
import { ChatPromptTemplate } from "@langchain/core/prompts";

const llm = new ChatOpenAI({
  model: "claude-sonnet-4-6",
  apiKey: process.env.DEVSAIO_API_KEY,
  configuration: { baseURL: "https://devsaio.lol/v1" },
  temperature: 0.2,
});

const prompt = ChatPromptTemplate.fromMessages([
  ["system", "You are a helpful assistant that answers in {language}."],
  ["user", "{question}"],
]);

const chain = prompt.pipe(llm);
const res = await chain.invoke({ language: "Spanish", question: "What is a webhook?" });
console.log(res.content);

Streaming

ts
const stream = await llm.stream("Explain closures in JavaScript with one example.");
for await (const chunk of stream) process.stdout.write(String(chunk.content));

Notes

  • Keep the key in an environment variable on the server; never in browser code.
  • Any model id from the model list works in model.
Try it with one API key

Claude, GPT, Gemini, DeepSeek, image and video models through one OpenAI- and Anthropic-compatible endpoint. Prepaid, pay only for what you use.

Keep reading