Send your first request.

Keep the OpenAI SDK you already use. Create a key, set one base URL, and start streaming responses through Standard Thinking.

5 MIN READLAST UPDATED AUG 12, 2026

1. Create an API key

Sign in to the dashboard, open API keys, and create a project-scoped key. The secret is shown once.

KEEP IT SECRET

Never expose an API key in browser code or commit it to a repository. Load it from a server-side environment variable.

ENVIRONMENT VARIABLESTANDARD_API_KEY=st_live_••••••••••••

2. Set the Base URL

Pass your key as a Bearer token and direct the SDK to the Standard Thinking endpoint.

BASEhttps://api.standardthinking.ai/v1

3. Send a chat request

Select a language below. Each example streams a response from standard-reason-72b.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.STANDARD_API_KEY,
  baseURL: "https://api.standardthinking.ai/v1",
});

const response = await client.chat.completions.create({
  model: "standard-reason-72b",
  messages: [{ role: "user", content: "Explain this architecture." }],
  stream: true,
});

4. List available models

Use GET /v1/models to retrieve model IDs and availability for your project.

GET/v1/models200 JSON
curl https://api.standardthinking.ai/v1/models \
  -H "Authorization: Bearer $STANDARD_API_KEY"

Next steps

Explore the full API reference for streaming events, parameters, rate limits, and error handling.

Open API referenceBrowse models