Reflex.dev ran the numbers and the result is sharp. Computer-use agents cost about 45x more in tokens than the same task done through a structured API call. Source measurement here .

That is not a rounding error. That is the difference between a $20 daily budget lasting a workday and burning out before lunch.

Why the gap is so wide

Computer use is not just "an agent that clicks things." It is a loop with four expensive parts:

Vision tokens. Every screenshot gets fed to the model as image tokens. Screenshots are big. A single 1080p capture can cost more tokens than the entire prompt of an API call.

The screenshot loop. The agent screenshots, reasons, acts, then screenshots again to verify. Every step is a new image. Multi-step workflows compound fast.

Click coordinate generation. The model has to output pixel coordinates for clicks. That is wasted reasoning the API path skips entirely.

Redo loops. When the click misses or the page state shifts, the agent retries.…