Picking a Model
features.ai.model controls which model powers the AI Assistant's text
and chat — generating and editing copy, layouts, and design. It is
independent of features.ai.image.model,
which only affects AI image generation and editing.
Recommended: let Unlayer pick
Leave features.ai.model unset and Unlayer picks the best model per
request. Set it only when you need to pin a specific provider or model.
Pin a model
features.ai.model accepts:
- a
"<provider>/<modelId>"pair (e.g."openai/gpt-5.5","anthropic/claude-opus-4-7") — pins both provider and model, unambiguous; - a bare model id (e.g.
"gpt-5.5"); - a provider name (e.g.
"openai","anthropic") — locks the vendor and lets Unlayer pick that provider's default model.
unlayer.init({
features: {
ai: {
enabled: true,
assistant: true,
// Provider only — Unlayer picks that provider's default model:
model: 'anthropic',
// Or pin an exact model:
// model: 'openai/gpt-5.5',
},
},
});
Supported providers: openai, anthropic.
Quality vs. cost
If you do pin a model, here's how the tiers generally compare:
| Tier | Examples | Relative cost | Best for |
|---|---|---|---|
| Frontier | claude-opus-4-7, gpt-5.5 | Higher | Design-heavy work — generating or restyling templates. Strong visual taste and copy quality. |
| Mid-tier | claude-sonnet-4-6, gpt-5.5-mini | Standard | Solid all-rounder. Reasonable design awareness at mainstream rates. |
| Small / fast | claude-haiku-4-5, gpt-5.5-nano | Lower | Short text rewrites only. Avoid for design generation — tends to produce flat, low-taste layouts. |
Related
- Setup — how the assistant is enabled per project.
- Picking an image model — choose the model for AI image generation and editing.
- Custom OpenAI Key — bring your own OpenAI billing.
- Custom Claude Key — bring your own Anthropic billing.
- Pricing — how AI usage is billed.