Pick the right model for the task

🎯Goal. Choose between the frontier models Cursor offers, and understand why the choice affects both quality and cost.

1. 1Open the model picker in the chat/Agent bar. Cursor gives you access to all major frontier models — Claude, GPT, and Gemini — switchable per task.
2. 2Match the model to the job: a heavier model for tricky multi-file reasoning, a faster one for routine edits. Auto lets Cursor choose for you.
3. 3Remember that different models have different API costs, so your model choice changes how quickly your included usage is consumed — not just the quality of the answer.

✓You'll see. The same request handled by different models, and a clearer sense of which one to reach for on a given task.

💳Cost. Model selection directly affects spend: a pricier model eats included usage faster. On Pro ($20/mo) you get generous included usage for Auto and Composer to absorb everyday switching.

💡Takeaway. Cursor isn't tied to one model — pick the model that fits the task, knowing it's also a cost lever.