Replit Ships Model Selector So Developers Stop Overpaying for Simple Fixes
Replit's new Model Selector lets Core and Pro users pick any model — including open-weight ones — and tune how hard it thinks per task.
- Model Selector is live for all Replit Core ($20/mo) and Pro ($100/mo) users, adding open-weight model support to the Agent.
- Effort Control lets you pick Lite, Economy, Power, High Effort, or Turbo per task — so you never overpay for a simple bug fix.
- Open-weight models route through OpenRouter, giving access to 200+ models from Meta, DeepSeek, Mistral, Qwen, and more.
- High Effort mode selectively routes only the hardest sub-tasks to the most capable model, adding up to ~2x cost only where needed.
- Replit co-signed the open-weights letter with Nvidia, Mistral, Y Combinator, and others, signaling a broader commitment to model openness.
- Recommended defaults help users who aren't tracking the fast-moving open-weight landscape pick a good model automatically. Try it on Replit.
Replit just shipped Model Selector, a new feature that lets you choose which AI model powers your Agent session and dial in exactly how much reasoning effort it applies. The headline addition: open-weight models are now first-class citizens alongside Claude, GPT, and Gemini. For anyone who has ever wished they could swap in a cheaper model for a quick fix and a heavier one for a hard architectural problem, this is the feature you've been waiting for.
One knob for intelligence, one for effort
Model Selector has two moving parts. The first is straightforward model choice: you can now pick from a growing catalog that includes both closed frontier models and open-weight alternatives. The second is Effort Control, which maps directly onto Replit's existing Agent mode system.
Agent modes let you control the balance between speed, cost, and capability when using Agent. The current tiers are:
- Lite , optimized for quick edits, using fast, lightweight models for visual tweaks, bug fixes, and other small, scoped changes.
- Economy , best default when you want strong results without burning credits on the most capable models.
- Power , for the most capable standard builds; turn on Turbo when you need the fastest runs.
- High Effort (toggle) , when enabled, Agent performs deeper, more deliberate reasoning and invokes its most capable frontier models, improving outcomes on the most complex tasks.
- Turbo (toggle) , gives 2.5x faster responses using the fastest models, but requests cost about 2x more than Power.