Built-in AI for your apps

Turn on Built-in AI in the project's Environment dialog. The app gets two variables:

• MOBO_LLM_BASE_URL — an OpenAI-compatible base URL
• MOBO_LLM_KEY — a key for this project only

Call it from server code:

const res = await fetch(`${process.env.MOBO_LLM_BASE_URL}/chat/completions`, {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.MOBO_LLM_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'mobo-auto', // or mobo-fast / mobo-smart
    messages: [{ role: 'user', content: 'Summarise this review in one line: …' }],
  }),
});

Responses use the OpenAI chat completion format (non-streaming). Each call is charged to the project owner's credits. Turning Built-in AI off revokes the key immediately.