Sensing and computing are important parts that human attempts to perceive and understand the analog world through digital devices. The analog-to-digital converters (ADCs) discretize the analog signals while the data bus transmits digital data between components of a computer. With the increasing of sensor nodes and the application of deep neural networks, the energy and time consumption limits the increment of data throughput. In-sensor computing is a computing paradigm that integrates sensing, storage, and processing in one device without ADCs and data transfer. According to the integration degree, herein, we summarize four levels of in-sensor computing in the field of artificial olfactory. In the first level, we show different functions are conducted by using discrete components. Next, the data conversion and transfer are exempted within the in-memory computing architecture with necessary data encoding. Subsequently, in-sensor computing is integrated into a single device. Finally, multi-modal in-sensor computing is proposed to improve the quality and reliability of the classification results. At the end of this minireview, we also outlook the use of metal nanoparticle devices to achieve such in-sensor computing for bionic olfaction.