Skip to content

For Developers

Generate your first image, explore the creative tools, and set up API access — all in about ten minutes.

Go to casola.ai and sign in with GitHub, Google, or Apple. On first login you’ll create an organization — this is where your usage, tokens, and generated media live.

  1. Open the Generate page (/generate).
  2. Choose a model — Flux is a great default for fast, high-quality images.
  3. Write a prompt and hit Generate.

Your result appears in seconds. Every generation is saved to your Library automatically.

  • Chat (/chat) — talk to LLMs like Qwen, LLaMA, and Claude. Supports streaming, multi-turn conversations, and vision (attach an image to the prompt).
  • Studio (/studio) — a unified workspace for all media types. Jump between image, video, voice, and text generation from a single page.

See the Chat guide and Studio guide for more detail.

When you’re ready to generate programmatically:

  1. Go to Tokens (/tokens).
  2. Click Create token, give it a name, and select the User Access scope group.
  3. Copy the token — it’s only shown once.

Use it in a quick test:

Terminal window
curl https://api.casola.ai/openai/v1/images/generations \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model": "flux", "prompt": "a mountain lake at sunrise", "size": "1024x1024"}'

See the API Tokens guide for scope details and best practices.