How to run your first OpenAI-compatible API call with curl, Python, and Node.js

OriginStartAI released an open-source repository with curl, Python, and Node.js examples for making the first OpenAI-compatible API call. The repo covers streaming, JSON structured output, migration notes, and common errors like 401 Unauthorized and model not found. Developers can test their endpoint, key, and model configuration with a minimal request before integrating into production workflows.

When you are testing an OpenAI-compatible API endpoint, the fastest path is not to wire it into a full app immediately. Start with one small request, confirm the base URL, API key, model name, and response shape, then move the working call into your product. I put together a compact examples repo for that exact first-call workflow: https://github.com/OriginStartAI/openai-compatible-api-examples https://github.com/OriginStartAI/openai-compatible-api-examples It includes curl, Python, Node.js, streaming responses, JSON structured output, migration notes, and a small error reference. Keep credentials out of source code and use environment variables: ORIGINSTARTAI API KEY=your api key here ORIGINSTARTAI BASE URL=https://your-api-base-url/v1 ORIGINSTARTAI MODEL=your enabled model The important parts are simple: base url or baseURL points to your OpenAI-compatible endpoint. api key or apiKey is your provider key. model must be enabled for your account.Curl is useful because it removes SDK behavior from the equation: curl "$ORIGINSTARTAI BASE URL/chat/completions" \ -H "Authorization: Bearer $ORIGINSTARTAI API KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "'"$ORIGINSTARTAI MODEL"'", "messages": {"role": "user", "content": "Say hello from OriginStartAI"} }' If this works, your endpoint, key, and model are probably configured correctly. python from openai import OpenAI import os client = OpenAI api key=os.environ "ORIGINSTARTAI API KEY" , base url=os.environ "ORIGINSTARTAI BASE URL" , response = client.chat.completions.create model=os.environ "ORIGINSTARTAI MODEL" , messages= {"role": "user", "content": "Write one friendly onboarding sentence."} , print response.choices 0 .message.content python import OpenAI from "openai"; const client = new OpenAI { apiKey: process.env.ORIGINSTARTAI API KEY, baseURL: process.env.ORIGINSTARTAI BASE URL, } ; const response = await client.chat.completions.create { model: process.env.ORIGINSTARTAI MODEL, messages: { role: "user", content: "Write one friendly onboarding sentence." } , } ; console.log response.choices 0 .message.content ; 401 Unauthorized : the key is missing, expired, or copied incorrectly. model not found : the model name is not enabled for the account. insufficient credits : add API balance before testing more requests.Once the first call works, replace the sample prompt with one real workflow from your product: support replies, summaries, SEO outlines, structured JSON extraction, or internal automation. Repo: https://github.com/OriginStartAI/openai-compatible-api-examples https://github.com/OriginStartAI/openai-compatible-api-examples Start here: https://originstartai.com?utm source=github&utm medium=community&utm campaign=openai compatible examples https://originstartai.com?utm source=github&utm medium=community&utm campaign=openai compatible examples New user offer: recharge $5 and get $5 extra API credits.