Pro modes

Dyad Pro members get access to these exclusive modes.

Turbo Edits

Turbo Edits offloads routine code changes from the state-of-the-art model to a faster, more affordable model specialized in editing code.

Benefits

• Up to 50% faster code generation, especially for large files
• Up to 2× cheaper, saving your AI credits

How to use

Once you enable Turbo Edits, you can continue using Dyad as you normally would. Dyad will intelligently decide when to use Turbo Edits—such as when you're making targeted changes to an existing file. For larger changes, Dyad will default to regular edits to ensure the quality of the AI output is maintained.

How it works

Turbo Edits is powered by a secondary, lightweight model that excels at processing edits quickly. This allows the primary model (i.e., the one you have selected) to handle the heavy lifting while offloading routine tasks to the faster, cheaper model to generate the full file change.

Smart Context

Smart Context automatically includes the most relevant files from your codebase in the chat context. This makes responses more efficient and is especially helpful for large projects.

Benefits

• Significant cost savings, especially as your project grows
• Enables Dyad to edit larger codebases

How to use

Once enabled, Smart Context works seamlessly in the background. Dyad will automatically pull the most relevant files into the chat context without any extra effort from you.

How it works

To power Smart Context, Dyad uses a lightweight model to identify the most relevant files from your codebase and feeds them into the larger model. This approach is far more efficient than naively including the entire codebase in the context—which is expensive and doesn't scale well.

Smart Auto

Smart Auto automatically chooses the most efficient AI model for your task—helping you balance speed, cost, and quality without manually switching models.

Benefits

• Lower AI credit usage by using faster, cheaper models for simple tasks
• Automatically uses leading models for complex tasks
• No need to manage models manually

How to use

Enable Smart Context and set your model to Auto. Dyad will take care of the rest—choosing between lightweight and high-end models based on the complexity of the task you're asking.

How it works

Smart Auto uses a classification engine to assess the complexity of each task before running it. For simple tasks—like UI changes or small bug fixes—it uses a fast, cost-effective model like Gemini Flash 2.5. For complex tasks—like architectural changes, security-related work, or multi-system logic—it automatically switches to a more powerful model like Gemini Pro 2.5.

When the complexity is unclear, Dyad will default to the higher-quality model to ensure the best possible outcome.