Standard Compute
Getting started

Connect your agent in two minutes.

Standard Compute is a drop-in OpenAI-compatible API. Sign up, copy three values, and point your agent at them — no rebuild, no SDK change. Here's everything you need on one page.

1
Create a free account

Sign up with your email — no credit card. Every new account starts on the free tier so you can try real compute first.

2
Grab your API key

Your key, endpoint, and model live in the dashboard. Copy the key once and store it in your secrets manager.

3
Point your agent at it

One base-URL swap. Works with any OpenAI-compatible agent — OpenClaw, Hermes, Pi, OpenCode, Cline, Aider, and more.

The three values, and where they go

agent.config.ts+3 −3
const client = new OpenAI({
  baseURL: "https://api.openai.com/v1",  baseURL: "https://api.stdcmpt.com/v1",  apiKey: process.env.OPENAI_API_KEY,  apiKey: process.env.STANDARD_COMPUTE_KEY,});

await client.chat.completions.create({
  model: "gpt-5.2",  model: "standardcompute",  // the router takes it from here  messages,
});

Credentials

Free tier
Base URL
https://api.stdcmpt.com/v1
API key
sc_live_········Get yours →
Model
standardcompute

Store your key in your platform's secrets store rather than hardcoding it.

●

Or just hand it to your agent

Most people never touch a config file. Paste the three values into your AI agent and tell it to set itself up — it edits its own provider config, sets the default model, and restarts. Copy the prompt below, drop in your key, and send it.

Set up Standard Compute as my model provider and make it the default.
Base URL: https://api.stdcmpt.com/v1
API key: <paste your key here>
Model: standardcompute
Edit my agent's provider config accordingly, keep everything else, and restart.

Agent-specific paste-in guides live on the setup guides page.