Skip to main content
The Model selector lets Replit choose a model automatically or lets you select an available model yourself.

​
Auto

Auto is Replit’s intelligent model routing and default model selection. It chooses an appropriate model for each task, balancing quality and cost. Auto considers the work you request and its complexity. A focused request can use a lower-cost model, while complex work may need a more capable model. Replit can select a different model as the task changes.
Free Mode always uses Auto. Builders in Free Mode cannot use the Model selector or choose a model manually.

​
Choose a model manually

Builders on Core and Pro can turn Auto off and choose an available model in Power Mode or Max Mode.
  1. Open the Agent settings dropdown in the chat input.
  2. Choose Power Mode or Max Mode.
  3. Turn off Auto.
  4. Select Primary model, then choose a model from the list.
Agent settings popover showing Lite, Economy, and Power modes, a Primary model list, and an Effort slider

The model selector popover, with Lite, Economy, and Power modes and the Primary model list. Captured in Replit Design; the same control appears in the Agent settings dropdown.

Your selection applies to your next message; you can change it at any time.

​
Models by mode

The built-in catalog maps selectable models to Power Mode and Max Mode as follows:
Free Mode does not have a selectable model list. The list in your Model selector is the source of truth for your account. Model selection is rolling out, and the available models can vary by rollout, organization settings, and authorization. Some fast variants require Turbo access, Replit’s paid speed feature for Pro and Enterprise plans. If you don’t see Primary model, the Model selector isn’t available for your account yet.

​
Effort

Effort is a per-model control, not a separate mode. It sets how much reasoning the selected model spends on each response, from Low to Max. Each model shows its recommended setting, and you can raise it only when a task calls for it.
The Primary model list with Claude Fable 5 selected and the Effort slider set to Medium, described as balanced reasoning for everyday tasks

The Effort slider below the model list, set to Medium.

Use the level descriptions as your guide: At higher Effort, Agent performs deeper, more deliberate reasoning and invokes its most capable frontier models, improving outcomes on the most complex tasks. Agent applies that extra power selectively. It routes to the more capable models only when a request is genuinely hard, not on every run.
Because Agent only reaches for the most capable model on the hardest work, higher Effort adds cost up to ~2x on the toughest tasks. It often adds little or nothing on simpler tasks. Raise it for complex problems, and keep it low for routine changes.

​
Compare models

Compare models runs your next prompt across several models at once, so you can judge results side by side instead of guessing which model fits. It’s in beta. To turn it on, expand Advanced settings at the bottom of the Agent modes popover and switch on Compare models.
Comparing models is only supported with Chat.
Advanced settings expanded with the Compare models Beta toggle switched off, described as creating up to 4 variants with your next prompt

The Compare models toggle under Advanced settings.

With the toggle on, add up to 4 models to the comparison.
The Agent modes popover with Compare models on and four removable model slots: Kimi K3, Claude Fable 5, Claude Opus 5, and GPT-5.6 Sol. The chat send button reads Compare 4

Four models selected for comparison, with the send button reading Compare 4.

Your next prompt then runs once per selected model, and each produces its own variant to compare.
Each model in a comparison runs a separate agent and uses credits, so a Compare 4 run costs about as much as four single runs.

​
Model selection in Build and Design

Build and Design keep separate model selections. This page covers selecting a model for Agent builds. To explore visual directions with Design’s model selector, see Explore with different models.