Assistant CoreAssistant Core
Web App

Chat Model Selection

How to choose the model used for text chat in the Web App.

Overview

In the Web App, the model in the header is the Chat model. It handles text messages, attachments, tool use, Knowledge Base retrieval, and thinking mode in chat.

The Chat model is separate from Settings → Voice. Voice Agent has its own model and voice choices for Standard mode and Realtime mode. See Model and Voice Settings.

Switching Models

Click the model name in the header to open the chat model selector. The list you see depends on your current plan and the models available to the assistant.

On desktop, hover over a model to see:

  • Credit usage
  • Model description
  • Supported input types
  • Supported output types

See AI Models for the full model catalog and Plans & Pricing for plan access.

When to Change the Chat Model

NeedHow to choose
Fast answers and daily tasksUse an efficient model or keep the default
Long analysis, reasoning, or codingChoose a stronger reasoning model if your plan includes it
Files or multimodal contentChoose a model with the right input/output types
Cost controlCheck the credit usage label in the dropdown and see Credits & Usage

Thinking Mode

Some Chat models support thinking levels. When the current model supports it, a Think selector appears in the input bar.

LevelBest for
OffFast responses
LowEveryday questions
MediumMulti-step analysis
HighMath, logic, coding, or tasks that need deeper reasoning

If the selector does not appear, the current Chat model does not support this mode.

Higher thinking levels can consume more credits. See Credits & Usage.

Remembered Selection

Your selected Chat model is remembered for future conversations in the Web App. You can change it anytime from the header.

On this page