Go from sign-up to your first API call in under five minutes. This guide walks you through account creation, key generation, and connecting Standard Compute to your agent.
Head to the Standard Compute website and click Sign Up. You can register with your email address. Once your account is confirmed you will be taken straight to the Dashboard.
All new accounts start on the free tier so you can test the API before committing to a plan. No credit card is required to get started.
From the Dashboard, navigate to the API Keys section and click Create New Key. Give your key a descriptive name such as "OpenClaw Production" or "OpenCode Staging" so you can identify it later.
Your full API key is shown only once at the time of creation. Copy it and store it somewhere secure — a password manager or an environment variable in your deployment. If you lose the key, you can revoke it and create a new one at any time.
The Standard Compute API is fully compatible with the OpenAI chat completions format. The only change you need to make in your existing setup is swapping the base URL to https://api.stdcmpt.com/v1 and using your Standard Compute API key instead of an OpenAI key.
If you are using the OpenAI Python or Node SDK, set the base_url (Python) or baseURL (Node) parameter when initializing the client. If you are using an agent, look for the "Base URL" or "API Base" field in its provider settings.
You can test the API with a simple curl command: curl -X POST https://api.stdcmpt.com/v1/chat/completions -H "Authorization: Bearer sk-your-api-key" -H "Content-Type: application/json" -d '{"model": "standard", "messages": [{"role": "user", "content": "Say hello"}]}'.
If everything is configured correctly you will receive a JSON response containing a choices array with the model's reply. The response format is identical to what you would get from the OpenAI API, so any code that parses OpenAI responses will work without modification.
Try experimenting with different models ("fast", "standard", or "premium") and parameters like temperature and max_tokens to see how they affect the output.
For OpenClaw and Hermes Agent, use the paste-in setup guides in your Dashboard — they point the base URL at Standard Compute for you. That is the entire setup.
For Make (formerly Integromat), use the HTTP module to send a POST request to https://api.stdcmpt.com/v1/chat/completions. Add your Authorization header and pass the request body as JSON. Map the response to downstream modules as needed.
For Pi, OpenCode, Cline, Aider and other agents, open the agent's provider or model settings, choose the OpenAI-compatible option, and set the Base URL to https://api.stdcmpt.com/v1 with your key and model = standardcompute.
Step-by-step guides for each platform are available in your Dashboard under the Quick Start section. Each guide includes screenshots and a ready-to-import template.
Install with one command. Open a terminal, paste the command below, and press Enter. It will ask for your API key and do the rest.
curl -fsSL https://api.stdcmpt.com/install.sh | bashirm https://api.stdcmpt.com/install.ps1 | iexThat's it. Restart OpenClaw and standardcompute will be ready to use.
Explore the full API Documentation to learn about streaming responses, error handling, and advanced parameters. Check the Models page to understand which model tiers are available on your plan.
If you run into any issues or have questions, reach out to us at contact@standardcompute.com. We typically respond within a few hours on business days.