Model selection

ImageGPT intelligently routes your requests to the best AI model for each task. You can let the system choose automatically or manually select a specific model.

Auto mode (default)

By default, ImageGPT is in Auto mode. The system analyzes your request and automatically selects the most suitable model based on:

• The type of task (generate, edit, video, etc.)
• Your prompt content (text in images, complexity, style)
• Model capabilities and quality
• Your credit balance

This is the recommended mode for most users as it optimizes for the best results.

Manual model selection

For full control, you can manually select a specific model from the model selector dropdown. When you select a model:

• ImageGPT will only use that model for generation
• No other models will be considered
• If the selected model doesn’t support your request (e.g., an image generation model can’t edit images), you’ll be asked to switch to Auto or select a different model

Model selector location

The model selector is located in the chat input area. Click on it to:

• Switch between Auto and manual selection
• Search for models by name
• See credit costs for each model

When to use each mode