Skip to main content
Get from zero to your first API call in under 5 minutes.

Step 1: Create Your Account

1

Sign up

Visit runcrate.ai and click Get started. Sign up with GitHub, Google or Discord, or with an email and password. With GitHub, no credit card is needed to use free models. If you sign up with Google, you need a card on file to use them.
2

Complete onboarding

Four short steps: where you found us, what you want to run, whether you work solo or with a team, and a line that connects your coding agent. Choosing a team adds a step to invite teammates.
3

Turn on free usage

The call in Step 3 runs on a free model, so you can finish this quickstart without paying. How free usage starts depends on how you signed up:
  • GitHub: no credit card is needed, and nothing to top up. A GitHub account that is too new waits first, and the API keys page shows the date free usage starts.
  • Google: you need a card on file to use free models. Add it in the Free inference section of the API keys page. Free usage comes first, and anything beyond it is charged to your card by automatic top-up.
  • Email or Discord: use Sign in with GitHub on the API keys page. If your GitHub email is your account’s, GitHub is added to it; otherwise it signs in to a Runcrate account of its own.
Free usage is limited and resets every week. runcrate.ai/inference/free lists the free models and the rules. You need credit only for paid models, GPUs and storage, and for usage beyond your free allowance. Add it under Dashboard → Billing.

Step 2: Get Your API Key

Navigate to Dashboard → Keys → API Keys tab and click Create API Key. Copy the key immediately — it’s shown only once. Your key looks like: rc_live_xxxxxxxxxxxxxxxx

Base URL

The API base URL is https://api.runcrate.ai/v1. Use it with your key in the OpenAI SDKs and in any tool that asks for an OpenAI-compatible endpoint. The API keys page in the dashboard shows it too, with a copy button.

Step 3: Make Your First Call

Working in a coding agent? Paste this one line into it. It adds the OpenAI SDK, puts your key in the env file, writes one function and calls it once, asking you for your key and the model as it goes.
To write it yourself, use the code below. The Runcrate Models API is OpenAI-compatible. Base URL: https://api.runcrate.ai/v1
Install the OpenAI SDK: pip install openai (Python) or npm install openai (JavaScript).

Step 4: Try the Playground

Don’t want to write code yet? Use the Model Playground in the dashboard:
  1. Go to Dashboard → Models
  2. Click any model
  3. Start chatting, generating images, or creating videos — right in your browser
The playground shows auto-generated code examples (curl, Python, JavaScript) for every request you make.

What Else Can You Do?

Generate Images

Create images with FLUX, Stable Diffusion, and more

Generate Videos

Create videos with Veo 3, Kling, Seedance, and more

Deploy a GPU Instance

Launch a full GPU environment with SSH access

Browse All Models

Explore open and frontier models across 8 categories