Home/Docs/Quickstart/JavaScript / Node.js

JavaScript / Node.js gateway beta quickstart

The OpenAI JS SDK works against VerticalAPI without modification. Install with npm, set baseURL and apiKey, pass your provider key via defaultHeaders. Same code in browser, Node, Deno, Bun.

5-step validation

From beta docs to a verified test

  1. Read the gateway beta documentation

    Confirm current access, supported providers, compatibility and limits.

  2. Prepare scoped credentials

    Follow your provider's current key-handling guidance and avoid production credentials during evaluation.

  3. Install the JavaScript / Node.js SDK

    npm install openai

  4. Run the example below

    Use the documented base URL and required headers, then verify the returned shape for this beta path.

  5. Validate the result

    Check response shape, model behavior, limits and total cost against the provider before production.

Working example

JavaScript / Node.js — first call

quickstart.javascriptJavaScript / Node.js
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.verticalapi.com/v1',
  apiKey: 'vapi_...',
  defaultHeaders: { 'X-Provider-Key': 'sk-...' }
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',  // or claude-sonnet-4-5, gemini-2.5-pro
  messages: [{ role: 'user', content: 'Hello, world' }],
});
console.log(response.choices[0].message.content);

Model IDs and provider support can drift. Check the source-dated model directory and current beta documentation before changing the model or provider header.

Troubleshooting

Common errors and fixes

CORS error in browser
Don't expose your VerticalAPI key client-side. Proxy through your own /api endpoint and inject the key server-side. The dashboard offers per-domain keys with origin restrictions for legitimate browser-direct setups.
TypeError: fetch is not defined (Node < 18)
Upgrade to Node 18+ which has built-in fetch, or pass a polyfilled fetch in the SDK config.
Streaming not flushing chunks
Use response = await client.chat.completions.create({stream: true, ...}); for await (const chunk of response) { ... } — the OpenAI SDK supports async iteration on streams.
Next steps

Where to go from here

Pick a model in the source-dated directory. Compare two in the decision comparisons. Review the benchmark evidence policy before trusting performance claims.

Other languages

Quickstarts in other languages

Python

5-line Python quickstart

Read →
curl

5-line curl quickstart

Read →
Go

5-line Go quickstart

Read →
Ruby

5-line Ruby quickstart

Read →