Connect an AI Provider

A fresh install of Brilliant starts in Playground mode: the built-in AI chat replays bundled demo conversations end-to-end (prompts, tool calls, on-canvas edits) so you can feel out how the agent behaves before committing to anything. It stays on automatically until you connect a provider.

To send your own prompts, you need a model provider connected. You have two paths:

• Bring your own API key from Anthropic, OpenAI, Google, or OpenRouter. Pay-per-use, billed by the provider.

• Route through your Claude Code subscription if you already have one. No separate API key required; Brilliant uses the Claude Code CLI to talk to Anthropic on your behalf.

Both are managed from the same place: Settings → AI Providers. The moment you connect one, Playground mode flips off and your prompts start going through for real.

If you'd rather drive Brilliant from an external editor like Cursor or Claude Code instead of the integrated chat, you don't need to connect a provider here. Head to Connect an Agent instead.

1. Open Settings → AI Providers

Two ways in:

• Click the connection indicator at the left of the AI chat input in the bottom toolbar. A checkmark means a provider is connected; an X means none is. Either way, clicking it jumps straight to the AI Providers pane.

• Press ⌘, to open Settings, then pick AI Providers in the sidebar.

Hovering the indicator also pops out a small status list, but it's display-only. Every action lives in the Settings pane.

2. Connect a provider

Option A: Bring your own API key

For Anthropic, OpenAI, Google, or OpenRouter, click Add API key on the row, paste the key, and confirm. The status dot turns green and the row swaps to a connected state.

• Anthropic: direct API access to Claude models.

• OpenAI: direct API access to GPT models.

• Google: direct API access to Gemini models.

• OpenRouter: a meta-provider with a single key for dozens of models across vendors. Useful if you want to try different models without juggling keys.

You can connect more than one. Switch between them later from the model picker in the chat itself.

Option B: Use Claude Code

If you already have Claude Code installed and signed in on a Pro, Max, Team, or Enterprise plan, the Claude Code row will show as connected the moment you open the pane. Nothing else to do; Brilliant routes through the CLI and bills against your existing Claude subscription. (On a free tier the row reads as not connected, since the CLI can't drive the integrated chat there.)

If you don't have it yet, install it and sign in from your terminal first:

1. Follow the Claude Code install guide for your OS.

2. Run claude once and complete the browser sign-in flow.

3. Reopen Settings → AI Providers in Brilliant. The Claude Code row picks up the existing login.

Once connected

Send a prompt from the AI chat input. Brilliant uses whichever provider you selected, and you can swap providers any time by reopening the pane.

About Playground mode

Playground mode is what you saw the first time you launched Brilliant. It's not a sandbox model or a trial: it's a replay of bundled demo conversations, so you can scrub through a real session (prompts, tool calls, on-canvas edits) without an API key or a network call. The connection indicator in the bottom toolbar stays unlit while it's on.

The mode flips off automatically the moment you connect any provider above. You can also toggle it back on manually from the bottom of the AI Providers pane if you want to revisit the demos later.

Note on Quiver

The same pane also has a Quiver row. Quiver isn't a chat model. It's the API behind Brilliant's AI vector generation and image-to-SVG conversion. Connecting it unlocks those features but has nothing to do with the chat.

Next

• Design with the built-in agent: Your First AI Chat walks through prompting, element references, and iterating.

• Drive Brilliant from your editor: Connect an Agent sets up Claude Code, Cursor, Codex, and others.