Model Selection

Click the model button in the bottom toolbar to choose your AI model. Pieces offers a streamlined selection process with three modes for each provider:

Mode Speed Quality Best For
Fast Fastest Good Quick questions, simple lookups, code completion, rapid iteration
Balanced Moderate Better General tasks, summaries, explanations, everyday coding help
Extra Thinking Slower Best Complex reasoning, debugging, architecture decisions, multi-step analysis
Start with **Fast** for most tasks—it handles the majority of questions well. Switch to **Extra Thinking** when you need deeper analysis or the Fast response isn't sufficient. Click the `model button` in the *bottom toolbar* to open the model selector. Under *Built-In Models*, hover over **Claude**, **Gemini**, or **GPT** to see the available modes. Click **Fast**, **Balanced**, or **Extra Thinking** based on your task.

Your chat history stays intact when you switch models—new messages use the selected model while previous responses remain unchanged.

Cloud Models

Pieces connects to cloud models from OpenAI, Anthropic, and Google. Cloud models offer faster responses and advanced reasoning capabilities.

Some cloud models are available to Pieces Pro users only. To unlock premium models, see [Pieces Pro](/paid-plans).

For a full list of available cloud models, see Cloud Models.

Next Steps

Learn how to filter your searches by Apps, Time, and Modality to scope which memories are used in your conversations.