# Budget the run

Lesson 3 of [Choose and run an AI benchmark for a model decision](https://aibenchmarkindex.com/academy/choose-and-run-an-ai-benchmark.md), 15 minutes.

Price the run before you send a request. Then put hard limits in the runner. The base estimate For a simple API evaluation, add two parts. - Input: tasks x average input tokens x input price per million tokens / 1,000,000. - Output: tasks x average output tokens x output price per million tokens / 1…

The rest of this lesson is for learners enrolled in the course. [See how Choose and run an AI benchmark for a model decision works](https://aibenchmarkindex.com/academy/choose-and-run-an-ai-benchmark.md).

Also on the [web page](https://aibenchmarkindex.com/academy/choose-and-run-an-ai-benchmark/budget-the-run).