What AI models does Simple Chat use?

Simple Chat uses a combination of leading AI models including Google Gemini and OpenAI GPT for different tasks. You do not manage API keys or pick a model for every customer message—the app routes work to the right model for the job.

That routing is intentional: customer-facing replies benefit from the most capable models, while supporting tasks can use faster models where speed matters more than depth.

Models for different tasks

Primary conversations use the most capable models for accuracy on customer-facing replies. Shoppers get answers that respect nuance in product, policy, and order questions when those replies are generated from your store context.

Faster models handle tasks like translation and context selection where speed matters. Those behind-the-scenes steps keep the experience responsive without sacrificing quality on the messages customers actually read.

Reliability and fallback

The system automatically falls back to alternative models if one is unavailable, ensuring reliability during provider outages. If a primary provider is temporarily down, Simple Chat can continue operating on alternate models rather than leaving conversations stuck.

What this means for merchants

You get up-to-date model capability without operating model infrastructure yourself. Simple Chat handles model choice, routing, and fallback so your team can focus on instructions, tools, and conversation quality—not on which API to call for each message type.