What models does Replit use?

So Anthropic has been the sort of workhorse for over a year right now. It's just like the core agent loop because it can run for a long time coherently. But the few things have changed.Google's Gemini models are the best at price performance. For example, you know, given their price, where do they sit on the parita frontier, right. For example, tasks like court search, we might create a sub agent that is cheaper and has good enough performance and we offload that from the main core loop, right.And I wrote t ...